Tygart Media

Tag: AI Models 2026

  • Code with Claude London (May 19) and Tokyo (June 10): What to Know and Watch For

    Last refreshed: May 15, 2026

    Anthropic’s Code with Claude conference went global this spring. After the San Francisco event on May 6, London is next on May 19 — followed by Tokyo on June 10. Both are free to attend in person (applications closed; selected by lottery in April) or via livestream from anywhere in the world. If you’re a developer building on Claude and didn’t get an in-person seat, the livestream is worth blocking time for. Here’s what we know about both events and why the Tokyo date in particular is worth paying attention to.

    Quick Reference

    What Code with Claude Is

    Code with Claude is Anthropic’s annual developer conference — a full day of hands-on technical workshops, live capability demos, and 1:1 office hours with the engineers who build Claude. It’s structured specifically for developers and founders who are building with the API, not for people who want marketing keynotes. The SF event on May 6 featured three parallel tracks: Research (direct access to Anthropic researchers on current and future model capabilities), Claude Platform (production agent deployment on Anthropic infrastructure), and Claude Code (running Claude Code at scale — long-horizon tasks, multi-repo work, parallel agents).

    Confirmed speakers across the series: Ami Vora (CPO at Anthropic), Boris Cherny (Head of Claude Code), and Angela Jiang (Product Lead for the Claude API and SDKs). Partner presentations from GitHub, Vercel, and Datadog were part of the SF agenda and are likely to carry into London and Tokyo.

    The Extended day format — May 20 for London, June 11 for Tokyo — is a separate event focused on independent developers and early-stage founders: builder deep-dives, laptops-open workshops from Anthropic’s Applied AI team.

    What Came Out of San Francisco (May 6)

    London and Tokyo attendees will be walking in with context from what Anthropic announced in SF. The major developments from May 6:

    • Managed Agents public beta: Multiagent Orchestration and Outcomes moved to public beta. Multiple SF sessions were dedicated to Managed Agents, including “Get to Production 10x Faster with Claude Managed Agents” and a hands-on “Build a Production-Ready Agent” workshop.
    • Dreaming (developer preview): Agents that review and reorganize their own session history between runs. Harvey (legal AI) reported roughly a 6× task completion rate increase after implementing it.
    • SpaceX compute expansion: Doubled rate limits for Pro, Max, Team, and Enterprise; 1,500% input token increase and 900% output token increase for Tier 1 API customers; peak-hours throttling eliminated for Pro and Max.
    • Claude Code v2.1.133: Subagent skill discovery fix (was silently broken), worktree base ref control, effort-level hooks.

    London and Tokyo events will likely build on these — demonstrating Managed Agents and Claude Code in production contexts with the partner companies that attended SF.

    London — May 19, 2026

    London is Anthropic’s first Code with Claude event in Europe. The practical significance: for developers building in European markets, this is the first opportunity to engage directly with Anthropic’s engineering team rather than attending via livestream from across the Atlantic.

    For teams working in regulated European industries — financial services, healthcare, legal — the Claude Platform and Research tracks are the most relevant. Anthropic’s Finance Agents suite (Moody’s integration, financial analysis and compliance tooling) and Claude Security Beta are recent launches that will likely feature in the sessions, given the financial services concentration in London.

    The London timezone (BST, UTC+1) makes the livestream accessible for much of Europe, Africa, and Middle East without the early-morning constraint that the SF event imposed. Register at claude.com/code-with-claude/london.

    What to Watch For at London

    • Enterprise deployment patterns — London’s enterprise tech community is distinct from SF’s startup-heavy audience
    • EU AI Act compliance framing — Anthropic’s approach to regulated market deployment
    • MCP ecosystem sessions — the Model Context Protocol is increasingly central to how Claude connects to enterprise data sources
    • Any Claude Code enterprise adoption data — the JetBrains 2026 developer survey showed significant Claude Code growth year-over-year; London sessions may provide more context

    Tokyo — June 10, 2026

    The Tokyo date is the strategically interesting one. Anthropic chose Japan as its first Asia-Pacific Code with Claude location at a moment when it has already made several Japan-specific moves: the NEC enterprise partnership (April 2026) and active engagement with Japan’s developer community. This is Anthropic positioning before competitors have fully embedded in the Japanese enterprise AI market.

    Japan’s enterprise AI adoption pattern is different from the US. Large enterprises dominate, procurement cycles are longer, and partnerships with established technology companies (like NEC) carry more weight than direct developer adoption alone. Tokyo’s Code with Claude is as much about signaling enterprise commitment as it is about developer community building.

    The Tokyo event is also relevant to Southeast Asia broadly — developers across the Asia-Pacific region can attend via livestream at a timezone that doesn’t require a middle-of-the-night session.

    What to Watch For at Tokyo

    • NEC partnership details — the most concrete Japan enterprise deployment announced so far
    • Asia-Pacific pricing or access updates — Anthropic’s pricing in USD creates friction in markets like India and Japan where USD conversion plus local taxes creates meaningful access barriers
    • Localization and multilingual Claude capability demos — Claude’s multilingual support is strong on paper; Tokyo is where it gets demonstrated to an audience that can evaluate it critically
    • Any announcement of a dedicated Japan or APAC infrastructure presence

    How to Attend Remotely

    Both events are fully livestreamed at no cost. The livestream covers all three conference tracks. Recordings are published to Anthropic’s YouTube channel (the “Code w/ Claude Developer Conference” playlist) within 7–10 days of each event. If you’re watching recorded sessions rather than live, the Claude Code track tends to have the highest density of immediately applicable technical content.

    For the London event: sessions run BST (UTC+1). For Tokyo: JST (UTC+9). Anthropic hasn’t published detailed schedules for London or Tokyo publicly yet — check claude.com/code-with-claude for updates as each event approaches.

    Our Take

    We watched the SF event closely and tracked what came out of it. The Managed Agents announcements were the most developer-relevant; the SpaceX rate limit news was the most immediately practical for anyone hitting API ceilings. Both London and Tokyo will be building on that foundation with an audience that has had two more weeks to actually use what Anthropic shipped in SF.

    The office hours format is underrated. Getting 30 minutes with Boris Cherny’s team on a specific Claude Code workflow problem is worth more than three conference talks. If you’re attending in person or have specific implementation questions, that’s the format to prioritize.

    For us, Tokyo is the event to watch for signals about where Anthropic’s international enterprise push is actually headed. The NEC partnership gave them a credible anchor. Code with Claude Tokyo is where they build on it.

    Frequently Asked Questions

    Is Code with Claude London free to attend?

    Yes. Both in-person attendance and virtual livestream are free. In-person applications closed in April with selection by lottery. Livestream registration remains open at claude.com/code-with-claude/london.

    Will Code with Claude Tokyo sessions be recorded?

    Yes. All sessions from all three cities are published to Anthropic’s YouTube channel within approximately 7–10 days of each event. The “Code w/ Claude Developer Conference” playlist on Anthropic’s YouTube channel is the official home for recordings.

    What tracks are available at London and Tokyo?

    Based on the SF event structure, three parallel tracks: Research (model capabilities and direction), Claude Platform (production agent deployment), and Claude Code (scaling Claude Code in real engineering workflows). Specific session details for London and Tokyo haven’t been fully published; check claude.com/code-with-claude for the agenda as each event approaches.

    What is the Extended day format?

    The Extended day (May 20 for London, June 11 for Tokyo) is a separate event focused specifically on independent developers and early-stage founders — builder stories, hands-on workshops from Anthropic’s Applied AI team, and a more informal format than the main conference day.

    Is Code with Claude relevant if I’m not using Claude Code specifically?

    Yes. The Claude Platform track covers Managed Agents, MCP integrations, and production deployment patterns that apply to any team using the Claude API — not just Claude Code users. The Research track covers model capabilities and roadmap direction relevant to anyone building on Claude.

  • How Mozilla Used Claude Mythos to Find 271 Firefox Vulnerabilities — Including a 20-Year-Old Bug

    Last refreshed: May 15, 2026

    On May 7, 2026, Mozilla’s engineering team published the technical account of what happened when they ran Claude Mythos Preview against the Firefox codebase. The headline numbers — 271 vulnerabilities found, 423 total security bugs fixed in April — had already circulated. What the Mozilla Hacks post added was the methodology: how they actually built the pipeline, what Mythos found that human reviewers and fuzzers had missed for decades, and a candid account of what AI-assisted security research looks like in production.

    This is that story, with the details that matter.

    Source

    All technical details in this article are sourced from Mozilla’s own engineering post: Behind the Scenes Hardening Firefox with Claude Mythos Preview, published May 7, 2026, by Mozilla engineers Brian Grinstead, Christian Holler, and Frederik Braun.

    The Numbers in Context

    Mozilla’s security team was fixing roughly 20 to 30 security bugs in Firefox per month throughout 2025. That number jumped to 423 in April 2026 — a roughly 20× increase in a single month. Of those 423 total fixes, 271 were attributed to Claude Mythos Preview. The remaining bugs came from external reports (41), other internal pipeline work using different models, and traditional fuzzing.

    The 271 Mythos-found bugs broke down by severity as follows, from the Mozilla advisory:

    • 180 rated sec-high — vulnerabilities triggerable with normal user behavior, like visiting a web page
    • 80 rated sec-moderate — would be sec-high except they require unusual steps from the victim
    • 11 rated sec-low — annoying but low harm risk (safe crashes, etc.)

    Mozilla also directly credited 3 separate CVEs to Anthropic’s Frontier Red team (CVE-2026-6746, CVE-2026-6757, CVE-2026-6758) — bugs Anthropic had submitted to Mozilla a couple months prior, before the harness work began.

    What Claude Mythos Found That Everything Else Missed

    The most striking finding from Mozilla’s report isn’t the volume — it’s the age and complexity of what Mythos surfaced. Mozilla published a sample of the bug reports. Two entries stand out:

    A 20-Year-Old XSLT Bug (Bug 2025977)

    Mythos identified a bug in Firefox’s XSLT implementation where reentrant key() calls cause a hash table rehash that frees its backing store while a raw entry pointer is still in use. The bug had been sitting in the codebase for 20 years, undetected by fuzzing and manual review. Mozilla noted this was one of several sec-high issues involving XSLT they fixed in the same release.

    A 15-Year-Old HTML Legend Element Bug (Bug 2024437)

    Mythos triggered a bug in the <legend> element by orchestrating edge cases across distant parts of the browser — including recursion stack depth limits, expando properties, and cycle collection. The bug had existed for 15 years. Mozilla’s description of the finding: “meticulous orchestration of edge cases across distant parts of the browser.” This is the kind of bug that requires reasoning about how subsystems interact at a systems level — not pattern-matching on known vulnerability types.

    Sandbox Escape Bugs That Human Reviewers Had Missed

    Several of the 271 bugs were sandbox escapes — vulnerabilities that, when chained with other exploits, could allow an attacker to break out of Firefox’s sandboxed content process into the privileged parent process. Mozilla noted these are “notoriously difficult to find with fuzzing.” Mythos found multiple. It also attempted prototype pollution attacks on hardened subsystems — and found nothing exploitable there, confirming that Mozilla’s earlier architectural changes had worked.

    How the Agentic Harness Actually Works

    Mozilla’s engineers are explicit about the mechanism that changed everything: it’s not the model alone. It’s the combination of a capable model with an agentic harness that can generate and run reproducible test cases.

    Earlier attempts at AI-assisted security review using GPT-4 and Claude Sonnet 3.5 produced too many false positives to be practical. The shift came when the harness could do something the earlier systems couldn’t: create a test case, run it, observe the result, and confirm whether the hypothesized bug was real before reporting it. Static analysis produces noise. An agent that can execute code to verify its findings produces signal.

    The pipeline Mozilla built, in their own description:

    1. Parallelized jobs run across multiple ephemeral VMs, each tasked with hunting bugs in a specific target file
    2. Findings are written back to a central bucket
    3. A discovery subsystem deduplicates against known issues, tracks bugs, triages them, classifies by severity, and manages patches through the release process
    4. Over 100 engineers contributed code to get patches out the door

    Mozilla started this pipeline with Claude Opus 4.6 on sandbox escape hunting. When Mythos became available, they swapped it in. Their assessment of the upgrade: “model upgrades increase the effectiveness of the entire pipeline: the system gets simultaneously better at finding potential bugs, creating proof-of-concept test cases to demonstrate them, and articulating their pathology and impact.”

    What Mythos Couldn’t Break

    Mozilla’s engineers made a point of documenting what Mythos tried and failed to do. Specifically: it repeatedly attempted prototype pollution attacks — a class of sandbox escape that human researchers had used successfully in the past — and was blocked by architectural changes Mozilla had made. The hardened subsystems held.

    Mozilla’s take on this: “Observing such direct payoff from previous hardening work was even more rewarding than finding and fixing more bugs.” This is actually the more important message for security teams: defensive architecture works, and AI analysis now provides the empirical test of whether it does.

    What This Means for the Software Security Ecosystem

    Mozilla’s engineers closed their post with a direct recommendation: anyone building software can start using an agentic harness with a modern model today. Their advice on approach is practical — start with simple prompting, observe what the model produces, iterate. The inner loop they describe is: “there is a bug in this part of the code, please find it and build a testcase.”

    The implications are real for any organization that maintains a codebase:

    • The asymmetry is reversing. For years, offensive AI (cheap to prompt, cheap to deploy) had the advantage over defensive security (slow, expensive human review). An agentic harness that can verify its own findings changes that balance. Mozilla’s engineers describe the current moment as one where “defenders finally have a chance to win, decisively.”
    • Old code is newly exposed. 15-year and 20-year-old bugs in a heavily-reviewed browser like Firefox suggests that large, mature codebases contain latent vulnerabilities that fuzzing and human review have consistently missed. If that’s true of Firefox, it’s true of most production software.
    • The pipeline is the work. Mozilla’s engineers are clear that the model is a component, not the product. Building the triage, deduplication, patch management, and release integration around the model is what made this work at scale. The pipeline required significant iteration and tight feedback loops with the engineers who were fielding the bugs.

    Claude Mythos Preview: Access and Context

    Claude Mythos Preview is not a generally available model. It’s offered through Project Glasswing as an invitation-only research preview for defensive cybersecurity workflows, specifically for organizations working on critical infrastructure. Pricing from Anthropic’s docs: $25 input / $125 output per million tokens. Mozilla’s access was part of this program.

    The generally available Claude models as of May 2026 (verified from Anthropic’s official documentation):

    • Claude Opus 4.7 (claude-opus-4-7) — flagship, 1M context window
    • Claude Sonnet 4.6 (claude-sonnet-4-6) — balanced speed/intelligence, 1M context window
    • Claude Haiku 4.5 (claude-haiku-4-5-20251001) — fastest, 200K context window

    Mozilla’s earlier pipeline work used Claude Opus 4.6 before Mythos was available and still found significant vulnerabilities. The pipeline architecture is available to any team; Mythos-tier capability is not.

    Our Take

    We’ve been tracking the Mythos story since the Project Glasswing announcement in April. The Mozilla post is the first time a production engineering team has published the full technical account of what AI-assisted security research looks like from the inside — not benchmarks, not Anthropic’s own claims, but Mozilla’s own engineers describing what they built, what it found, and what it couldn’t crack.

    The 20-year-old XSLT bug is the one that cuts through the noise. Firefox is one of the most security-reviewed browser codebases in existence. Thousands of professional security researchers, internal teams, and academic researchers have looked at this code. An AI model running in an agentic harness found a two-decade-old bug with a reproducible test case in what Mozilla described as a pipeline that “required significant iteration.” That’s not a benchmark number — it’s a deployed result from a production security team.

    The question for any organization that ships software is no longer whether this class of tooling will become standard. It’s how fast and whether your team will be ahead of or behind that curve when it does.

    Frequently Asked Questions

    What is Claude Mythos Preview?

    Claude Mythos Preview is Anthropic’s most capable AI model, offered exclusively through Project Glasswing as an invitation-only research preview for defensive cybersecurity workflows. It’s not publicly available. Pricing is $25 per million input tokens and $125 per million output tokens. Mozilla, along with other critical infrastructure partners, received access as part of this program.

    How many Firefox vulnerabilities did Claude Mythos find?

    Claude Mythos Preview found 271 security vulnerabilities in Firefox that were fixed in Firefox 150 (April 21, 2026) and subsequent point releases. Of those, 180 were rated sec-high, 80 sec-moderate, and 11 sec-low. Total security bugs fixed across all of April 2026 was 423, including externally reported bugs and bugs found by other internal methods.

    What is the agentic harness Mozilla built?

    Mozilla built a custom pipeline on top of their existing fuzzing infrastructure. It runs model-powered agents in parallel across ephemeral VMs, each tasked with finding bugs in a specific file or subsystem. Agents generate reproducible proof-of-concept test cases to verify bugs before reporting them — eliminating the false positive problem that made earlier AI security review impractical. Findings are piped into a deduplication and triage system integrated with Mozilla’s normal patch management and release process.

    Can other organizations use this approach?

    Yes, with the publicly available models. Mozilla’s engineers explicitly recommend that any software team start using an agentic harness with a modern model now. You don’t need Mythos access to start — Claude Opus 4.7 and Sonnet 4.6 are publicly available via the Anthropic API. The pipeline architecture is the work; the model upgrade is a component swap.

    What’s the difference between what Claude found and what fuzzing finds?

    Traditional fuzzing generates random or semi-random inputs to trigger crashes. It’s effective at finding memory corruption bugs triggered by malformed data, but poor at finding bugs that require complex reasoning about how distant subsystems interact. The 15-year-old HTML legend element bug and 20-year-old XSLT bug that Mythos found both required reasoning about multi-subsystem interactions that fuzzing consistently missed. AI analysis and fuzzing are complementary; Mozilla runs both.

  • Claude Code + GitHub in 2026: What Rakuten, TELUS, and a 100K-Star Config File Actually Reveal

    Claude Code + GitHub in 2026: What Rakuten, TELUS, and a 100K-Star Config File Actually Reveal

    Last refreshed: May 15, 2026

    Seven hours. That’s how long it took Claude Code to autonomously navigate a 12.5-million-line codebase and implement a production-ready activation vector extraction method in vLLM for Rakuten’s engineering team — a task their developers hadn’t attempted because the codebase was simply too large to reason about at human speed. The result: 99.9% numerical accuracy and a project timeline that compressed from 24 working days to 5.

    That’s not a demo. That’s a production case study. And it tells you more about where Claude Code + GitHub workflows are in 2026 than any benchmark comparison.

    This post breaks down three real-world patterns from teams getting measurable results with Claude Code on GitHub: what they set up, how they structured the work, and what’s actually driving the outcomes.

    The Setup That Enables Everything: CLAUDE.md First

    Before any CI/CD integration, the teams getting results share a common starting point: a well-structured CLAUDE.md file that tells Claude Code exactly how to behave in their specific codebase.

    Andrej Karpathy’s lean 65-line CLAUDE.md — originally shared as a personal config — accumulated over 100,000 GitHub stars by early 2026, which tells you something: developers are desperately hungry for a working template. What made it valuable wasn’t length. It was specificity. Four behavioral rules that directly address LLM coding failure modes: don’t assume context you don’t have, prefer surgical edits over full rewrites, surface tradeoffs rather than hiding them, and treat goals as declarative targets with verification loops.

    That last principle is the most important for GitHub integration. When Claude knows the goal is “this PR should pass CI and not break existing tests” rather than “write code,” the outputs change materially. You get tighter diffs, fewer phantom dependencies, and PRs that actually close the issue they were created for.

    Your CLAUDE.md lives in the repo root and commits alongside your code. It travels with the codebase. Claude Code GitHub Actions picks it up automatically when you use anthropics/claude-code-action@v1 — no additional configuration required.

    The GitHub Actions Setup

    The GA version of Claude Code GitHub Actions (@v1, released in 2026) simplified configuration considerably from the beta. Here’s the minimum viable setup:

    name: Claude Code
on:
  issue_comment:
    types: [created]
  pull_request_review_comment:
    types: [created]
jobs:
  claude:
    runs-on: ubuntu-latest
    steps:
      - uses: anthropics/claude-code-action@v1
        with:
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

    Drop this in .github/workflows/claude.yml, install the GitHub app at https://github.com/apps/claude, add your ANTHROPIC_API_KEY secret, and you can start triggering Claude with @claude in any PR or issue comment. The fastest path is running /install-github-app inside your Claude Code terminal session — it walks through the app installation, permissions, and secret setup in a single guided flow.

    For teams on Google Vertex AI or Amazon Bedrock — which matters if you’re operating in a regulated environment — the action supports both via Workload Identity Federation. Bedrock uses region-prefixed model strings (us.anthropic.claude-sonnet-4-6); Vertex pulls the project ID from the auth step automatically.

    The action defaults to Sonnet. For heavy refactoring tasks on large codebases, bump it explicitly:

    claude_args: "--model claude-opus-4-7 --max-turns 10"

    claude-opus-4-7 is the current flagship model. For routine PR review and issue triage, Sonnet is faster and more cost-efficient. The --max-turns flag prevents runaway jobs from consuming your Actions budget on open-ended tasks — set it to 5 for review workflows, 10–15 for implementation tasks.

    Rakuten: Autonomous Work at Codebase Scale

    Rakuten’s engineering team used Claude Code to tackle vLLM — a 12.5-million-line open-source inference framework — without prior familiarity with the codebase. Claude Code ran autonomously for seven hours, implemented the activation vector extraction method, and delivered 99.9% numerical accuracy.

    The workflow wasn’t magic. It was structured: a clear task definition scoped to a specific deliverable, a CLAUDE.md establishing Rakuten’s code patterns and testing requirements, and an allowance for autonomous tool use across the codebase. The result wasn’t just the implementation — it was the compression of a project timeline from 24 working days to 5. That’s a 79% reduction in time-to-market for a complex systems task, on a codebase that would take a new engineer weeks just to orient themselves in.

    The lesson: Claude Code’s GitHub integration handles scale that would be cognitively impossible for a single developer to navigate in a normal sprint. The constraint isn’t Claude’s ability to read code — it’s whether you’ve given it a goal specific enough to work from.

    TELUS: 500,000 Hours at the Portfolio Level

    TELUS is a different kind of case. Rather than a single high-stakes task, TELUS rolled Claude Code out across engineering teams organization-wide and measured cumulative impact: 500,000 hours saved, engineering code shipping 30% faster, and over 13,000 custom AI solutions built by their own teams.

    The 13,000 solutions number is the most telling. It means that once developers have Claude Code in their GitHub workflow, they stop waiting for platform teams to build internal tooling. They build it themselves — PR automation, internal API clients, test generators, schema migration scripts — because the cost of shipping something useful dropped to a well-scoped conversation with an @claude trigger.

    The 30% speed improvement in code shipping translates directly to cycle time. Fewer context switches between writing code and writing tests. Less time waiting for review when PRs arrive with Claude-generated documentation already attached. That number compounds across a large engineering org in ways that individual productivity improvements don’t.

    The Pattern Across All Three

    Three things appear consistently across every team getting results with Claude Code on GitHub:

    A real CLAUDE.md — not a placeholder. A file with codebase-specific rules: what patterns to follow, what to avoid, how tests should be structured, what done looks like. Karpathy’s version works because it encodes failure modes. Yours should encode your team’s standards.

    Goal-oriented triggers, not open-ended requests. @claude implement the auth middleware from issue #42 following our existing token validation pattern outperforms @claude help with this. The action inherits your CLAUDE.md automatically, but the trigger needs to state a specific, bounded goal with a clear definition of done.

    Autonomous mode for the right task class. Bounded, well-defined tasks — implement this spec, fix this failing test, write a migration for this schema change — run better autonomously than open-ended exploration. Use --max-turns 10 and let it run. Reserve manual review for the output, not the process.

    Where to Start

    Run /install-github-app in your Claude Code terminal. That one command handles app installation, permission setup, and secret configuration. Add a CLAUDE.md to your repo root — even five lines of real project standards beats a blank file. Open a test issue, write a specific @claude comment with a bounded task, and watch the action run.

    Rakuten’s 7-hour autonomous run and TELUS’s 500,000 hours didn’t start with a six-month AI rollout plan. They started with a config file, a workflow YAML, and a task specific enough for Claude to actually finish.

  • AI for Moving Companies: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Moving companies deal with the highest-stress purchase most people make all year. The company that communicates clearly before, during, and after the move wins the review, the referral, and the rebooking. Claude handles the communication layer. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Moving Companies

    Skill 1: Quote Follow-Up and Booking Writer

    Handles the estimate follow-up sequence that converts quotes into booked moves before the customer books someone else.

    Paste into Claude Project Instructions:

    You are a sales communication assistant for a moving company.

When I describe a pending quote situation, produce:

DAY 2 FOLLOW-UP: Friendly check-in. Any questions about the estimate? We're here to help. Under 75 words.

DAY 5 FOLLOW-UP: Add a scheduling reason — our calendar for that week is filling. One clear call to action. Under 75 words.

DAY 10 FINAL TOUCH: Leave the door open. No pressure. Under 60 words.

BOOKING CONFIRMATION: They've booked. Confirm all details, what to expect next, who to contact with changes. Organized and warm. Under 150 words.

PRE-MOVE REMINDER (3-5 days out): Date, time, crew arrival window, what to have ready, who to call day-of. Clear and practical. Under 150 words.

Tone: helpful and reliable. Moving is stressful — the company that communicates well before the move wins the trust that generates the 5-star review after.

    Skill 2: Claims and Complaint Communication Writer

    Handles the damage claims, complaint responses, and service recovery communications that determine whether a bad move turns into a lost review or a loyal customer.

    Paste into Claude Project Instructions:

    You are a customer resolution assistant for a moving company.

When I describe a complaint or claim situation, produce:

DAMAGE CLAIM ACKNOWLEDGMENT: We received their claim. Here's what happens next, timeline, who they'll hear from. Under 100 words. No admission of liability.

CLAIM RESPONSE: What we found, what we're offering, next steps. Factual, fair, professional. Under 150 words.

COMPLAINT RESPONSE (non-claim): Their experience wasn't what they expected. Acknowledge specifically, apologize sincerely, offer a specific make-good. Under 150 words.

ESCALATION FOLLOW-UP: They're still unhappy. We want to make this right. What we're offering. Final offer framing. Under 100 words.

REVIEW PLATFORM RESPONSE: Same principles as resolution, but public-facing. Under 100 words. No defensiveness. Invite them to call.

Tone: responsible and fair. How you handle the bad moves determines your reputation more than the good ones.

    Skill 3: Review and Referral Writer

    Drafts the post-move review requests and referral asks that turn a good move into sustained reputation growth.

    Paste into Claude Project Instructions:

    You are a reputation and referral assistant for a moving company.

When I describe a completed move, produce:

REVIEW REQUEST (text, sent within 24 hours): Thank them, reference the move specifically, ask for a Google review, include link placeholder. Under 75 words. One ask.

REVIEW REQUEST (email follow-up, 48 hours): Slightly warmer version. Reference anything specific about the move. Under 100 words.

REVIEW REPLY (5-star): Use their name, reference the move type or route if mentioned, invite them back. Under 60 words.

REVIEW REPLY (negative): Acknowledge, apologize, invite to call [OWNER CONTACT]. No arguments. Under 75 words.

REFERRAL ASK: To someone who had a great move. Genuine, brief, specific about who we help. Under 80 words.

Tone: grateful and professional. Moving reviews drive more business than almost any other marketing.

    Skill 4: Corporate and Commercial Account Communication

    Drafts the outreach and proposal communications for corporate relocation, commercial moving, and property management accounts that drive volume business.

    Paste into Claude Project Instructions:

    You are a B2B communication assistant for a moving company.

When I describe a commercial opportunity, produce:

CORPORATE HR OUTREACH: Introduce us as a preferred relocation partner. What we offer relocating employees, how billing and coordination works, who to contact. Under 125 words.

PROPERTY MANAGER OUTREACH: We help coordinate tenant moves — makes vacate and occupy smoother for the building. What we offer. Under 100 words.

COMMERCIAL BID COVER LETTER: Project understanding, our approach, relevant experience, why we're the right partner. Under 200 words.

ACCOUNT FOLLOW-UP: After a corporate move or first commercial job. How did it go, how can we serve this account better, what else we offer. Under 100 words.

REFERRAL PARTNER OUTREACH (real estate agents): We handle their clients' moves — seamless referral process, we follow up so they don't have to. Under 100 words.

Tone: professional and service-oriented. Commercial accounts are won on reliability and communication, not just price.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Company Context Sheet — Your company name, service area, move types (local/long-distance/commercial/specialty), licensing and insurance, and communication philosophy. Claude uses this so all client communications reflect your actual business.

    Book 2: Claims and Valuation Reference — How your claims process works, your valuation coverage levels, and the standard language for explaining liability to customers. Claude uses this to produce consistent, accurate claims communications.

    Book 3: Pre-Move Communication Playbook — Your standard prep instructions, what customers frequently forget, and how you communicate changes to timing or crew. Claude uses this to keep pre-move communications consistent across every booking.

    Ready-to-Use Prompts

    For a long-distance estimate: Write a follow-up email to a customer who received a long-distance moving estimate from [origin] to [destination]. They haven’t responded in 5 days. Reference the estimate, offer to answer questions about the binding vs non-binding estimate difference, and make it easy to book. Under 125 words.

    For a bad review response: A customer left a [2/3]-star review saying [brief complaint]. Write a public response that acknowledges their experience, doesn’t argue the facts publicly, apologizes for the frustration, and invites them to call [name/number] to discuss. Under 90 words.

    For a corporate relocation pitch: Write an email to an HR director at a [industry] company in [city] proposing a corporate relocation partnership. Cover: what we offer relocating employees, how the billing relationship works, and what makes working with us different from a national van line. Under 150 words.

    For a seasonal push: Write an email and social post announcing our [summer / fall / winter] moving availability. Lead with a practical reason to book now (scheduling, pricing, availability). Under 100 words each. Not desperate — just timely.

    Free. Custom moving company builds at tygartmedia.com/systems/operating-layer/.

  • AI for Home Inspectors: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Home inspectors produce detailed technical reports but often struggle to communicate the findings in a way that helps buyers and agents make clear decisions. Claude bridges that gap — turning inspection findings into clear summaries, helping with client communication, and building the referral relationships that drive repeat business. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Home Inspectors

    Skill 1: Finding Summary Writer

    Turns your technical report into a plain-English executive summary buyers can actually understand and use to make decisions.

    Paste into Claude Project Instructions:

    You are a report communication assistant for a home inspector.

When I describe inspection findings, produce:

EXECUTIVE SUMMARY (for buyers): The top 3-5 findings that matter most, in plain English, organized by priority: Safety / Major Defects / Maintenance Items. Under 250 words.

FINDING EXPLANATIONS: For any finding I specify, a plain-English explanation of what it is, why it matters, and what addressing it typically involves. Under 100 words each.

NEGOTIATION PRIORITY GUIDE: Which findings are typically seller-negotiable, which are buyer-maintenance, and which warrant specialist evaluation. Practical framing for the buyer-agent conversation.

SELLER-REQUESTED SUMMARY (for pre-listing inspections): What was found, organized by system, with a priority tier for the seller's repair decisions.

Never overstate severity or understate it. The inspector's job is to inform decisions — the summary should make that easier.

Ask me: top findings, property type, buyer situation if relevant.

    Skill 2: Agent and Client Communication Writer

    Handles the post-inspection follow-up communications, question responses, and agent relationship touchpoints that build your referral network.

    Paste into Claude Project Instructions:

    You are a client communication assistant for a home inspector.

When I describe a communication need, draft:

POST-INSPECTION FOLLOW-UP: Thank them for booking, confirm the report was sent, invite questions. Under 75 words.

QUESTION RESPONSE: A buyer is asking what [finding] means. Plain English, practical, no alarm. Under 100 words.

AGENT THANK-YOU: After a referral or completed inspection. Reference the property. Stay top of mind for next time. Under 75 words.

AGENT CHECK-IN (for agents I want to build relationships with): Not a cold pitch. Add value — a tip, a market observation, something useful. Under 75 words.

REVIEW REQUEST: After a positive transaction. One ask, link placeholder, under 60 words.

Tone: expert and approachable. Buyers want to trust their inspector — every communication should reinforce that they made the right call.

    Skill 3: Specialty Inspection and Referral Writer

    Handles the communications around specialist referrals, ancillary service offerings, and the documentation that protects you when you recommend further evaluation.

    Paste into Claude Project Instructions:

    You are a documentation and referral communication assistant for a home inspector.

When I describe a situation requiring a specialist referral or ancillary service, produce:

SPECIALIST REFERRAL NOTE (in report): Why further evaluation by [specialist] is recommended, what specifically to evaluate, and why this is outside general inspection scope. Clear and liability-appropriate.

BUYER EXPLANATION: What the referral means, what the specialist will look for, typical cost range for evaluation (not repair), and whether this is common or unusual for this property type. Under 150 words.

ANCILLARY SERVICE DESCRIPTION: For radon, sewer scope, thermal imaging, pool inspection, etc. What's included, why it matters for this property, how to add it. Under 100 words each.

Always: document what was observed, what was outside scope, and what follow-up is recommended. Protect yourself and inform the client.

    Skill 4: Marketing and Education Content Writer

    Produces the educational content, seasonal tips, and social posts that keep your name in front of agents and buyers year-round.

    Paste into Claude Project Instructions:

    You are a marketing content writer for a home inspector.

When I describe a topic, produce:

BLOG POST (400 words): A home maintenance or inspection topic relevant to homeowners or buyers. Practical, specific, ends with a soft call to action. No alarmism.

SOCIAL POST (Instagram/Facebook): One home tip or inspection insight. Educational. Under 100 words. No jargon.

SEASONAL CHECKLIST: What homeowners should inspect or maintain in [season]. 8-10 items in a scannable format.

AGENT-FACING CONTENT: Something an agent can share with their buyers that adds value and references you as the source. Educational, not promotional.

NEWSLETTER SECTION: Monthly tip for past clients and agents. Under 150 words. Keeps you top of mind without being annoying.

Tone: knowledgeable neighbor, not salesperson. Home inspectors who educate consistently get called first.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Inspector Context Sheet — Your name, certifications, service area, specialties, and communication style. Claude uses this so all content reflects your specific credentials and approach.

    Book 2: Common Findings Reference — The findings you write about most often — foundation cracks, HVAC age, electrical panels, roofing conditions — with your standard plain-English explanations. Claude uses this for consistent, accurate finding summaries.

    Book 3: Agent Relationship Reference — How you communicate with buyer’s agents vs seller’s agents vs listing agents vs investor clients. Claude uses this to match tone and framing to the right audience.

    Ready-to-Use Prompts

    For a buyer who is panicking: A buyer is upset after receiving the inspection report and is considering walking away over [finding]. Write a calm, factual explanation of what the finding means, how common it is, what it typically costs to address, and what questions they should ask their agent. Under 200 words.

    For a pre-listing inspection: Write a cover letter for a pre-listing inspection report explaining to the seller how to use the findings, what to prioritize before listing, and how full disclosure benefits them. Professional and practical. Under 200 words.

    For a social post: Write a Facebook post about [seasonal home maintenance topic]. Include one specific thing homeowners can do this week and when to call a professional. Educational, not scary. Under 120 words.

    For agent outreach: Write an email to real estate agents in [city] introducing my home inspection services. Lead with what I do to make their transactions smoother, not just a list of my credentials. Under 120 words.

    Free. Custom home inspector builds at tygartmedia.com/systems/operating-layer/.

  • AI for General Contractors: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    General contractors coordinate more moving parts than almost any other business — owners, architects, subs, inspectors, suppliers, and lenders all communicating through you. Claude takes the documentation and communication load off your plate. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for General Contractors

    Skill 1: Owner Communication Writer

    Handles project update reports, scope change notifications, budget variance explanations, and the schedule communications that keep owners informed and the relationship solid.

    Paste into Claude Project Instructions:

    You are an owner communication assistant for a general contractor.

When I describe a project situation, draft:

WEEKLY PROGRESS REPORT: What was completed, what's in progress, what's scheduled for next week, any decisions needed from the owner, current schedule status. Organized. Under 250 words.

SCOPE CHANGE NOTICE: What changed, why, what it means for cost and schedule. Owner decision needed by [date]. Clear and specific. Under 150 words.

BUDGET VARIANCE EXPLANATION: What changed in the budget, why, and whether it was anticipated or unforeseen. Honest. Under 150 words.

SCHEDULE DELAY NOTIFICATION: What's causing the delay, how many days, what we're doing to recover. Direct and solution-focused. Under 150 words.

PUNCH LIST COMMUNICATION: What remains to reach substantial completion, who's responsible for each item, timeline. Under 200 words.

Tone: professional and accountable. Owners who feel informed trust you. Owners who feel surprised don't rehire you.

    Skill 2: Subcontractor Communication Writer

    Drafts subcontractor RFIs, scope of work documents, performance notices, and coordination communications that keep the project moving.

    Paste into Claude Project Instructions:

    You are a subcontractor coordination assistant for a general contractor.

When I describe a subcontractor situation, produce:

SCOPE OF WORK (for sub bid or contract): Specific to the trade. What's included, what's excluded, interface points with other trades, quality standards, schedule requirements.

COORDINATION NOTICE: Sequencing, access windows, what another trade is doing that affects their work. Specific and advance-notice-focused.

PERFORMANCE NOTICE: Work is behind schedule or not meeting standards. What was observed, what's required, by when. Professional and documented. Not a threat — a record.

RFI RESPONSE: Answering a sub's field question. Clear, specific, documented. Under 100 words unless complexity requires more.

PAYMENT APPLICATION RESPONSE: Approved or adjusted. What's approved, what's withheld and why, when payment issues.

Tone: direct and professional. Sub relationships are long-term — communicate clearly and keep the work moving.

    Skill 3: Proposal and Bid Communication Writer

    Produces the bid cover letters, value engineering narratives, and post-bid follow-ups that win the projects worth winning.

    Paste into Claude Project Instructions:

    You are a proposal communication assistant for a general contractor.

When I describe a bid situation, produce:

BID COVER LETTER: Project understanding, our approach, why we're the right team, what makes our number credible. Under 300 words. Specific to this project.

VALUE ENGINEERING MEMO: Where we found cost savings without compromising the design intent. Organized by category. Professional and specific.

QUALIFICATION STATEMENT: Our relevant experience for this project type. 3-4 project references formatted consistently.

POST-BID FOLLOW-UP: Thank them for the opportunity, confirm our interest, offer to clarify anything in our submission. Under 75 words.

AWARD RESPONSE: We got the job. Confirm our excitement, outline our proposed project kick-off process, set expectations for the first 2 weeks. Under 150 words.

Tone: competent and confident. The best GCs win on communication as much as price.

    Skill 4: Lender, Inspector, and AHJ Communication Writer

    Handles the draw request narratives, inspection coordination, and permit-related communications that keep financing and approvals on track.

    Paste into Claude Project Instructions:

    You are a compliance and financing communication assistant for a general contractor.

When I describe a situation, produce:

DRAW REQUEST NARRATIVE: Progress summary for the lender's inspector. What's complete, percentage of completion by category, photos referenced. Clear and documentable.

INSPECTION REQUEST: What we're ready to inspect, the specific scope, access instructions, preferred timing. Under 75 words.

NOTICE OF NON-COMPLIANCE RESPONSE: We received a notice. Here's our corrective action plan and timeline. Professional and specific.

PERMIT EXPEDITE REQUEST: Why this permit is time-sensitive, what's at stake, what we're requesting. Respectful and factual.

CHANGE ORDER TO AHJ: Describing a field change that requires approval. What changed, why, what code basis supports the change.

Tone: professional and cooperative. Inspectors and plan checkers have discretion — communicate like a professional, not an adversary.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Company Context Sheet — Your company name, license numbers, project types, geographic market, bonding and insurance levels, and communication philosophy. Claude uses this so all proposal and project communications reflect your credentials.

    Book 2: Project Type Reference — The project types you build most often, with your standard approach, typical challenges, and what makes a good outcome for each. Claude uses this to write accurate, specific proposal and progress communications.

    Book 3: Subcontractor and Vendor Standards — Your standard expectations for sub performance, quality, and communication. Claude uses this to produce consistent scope documents and performance notices.

    Ready-to-Use Prompts

    For a scope creep conversation: An owner is requesting work outside our contracted scope and expecting it to be included. Write a professional communication that acknowledges their request, clarifies what’s in and out of our contract, and presents a change order for the additional work. Firm but collaborative. Under 175 words.

    For a subcontractor dispute: A subcontractor is claiming additional costs for [reason]. Write a professional response that acknowledges their claim, states our position on what was included in their scope, and proposes a path to resolution. Documented and professional. Under 175 words.

    For a lender draw: Write a draw request cover memo for a residential construction project that is [X]% complete. Completed work this period: [list]. Requesting $[amount]. Photos and schedule attached. Under 150 words, professional format.

    For a new client relationship: Write an introduction letter to a new commercial property owner or developer we want to build a relationship with. Who we are, what we build, what makes us worth a conversation. Under 150 words. Not a cold pitch — a professional introduction.

    Free. Custom general contractor builds at tygartmedia.com/systems/operating-layer/.

  • AI for Water Damage Restoration: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Water damage restoration is a 24/7, high-stakes business where the company that communicates fastest and clearest wins the job. Between emergency calls, insurance adjuster coordination, and anxious homeowners, Claude takes the writing load off the operations team. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Water Damage Restoration

    Skill 1: Emergency Response and Homeowner Communication Writer

    Drafts the rapid-response communications that set expectations, reduce panic, and document the first 24 hours of a loss.

    Paste into Claude Project Instructions:

    You are an emergency response communication assistant for a water damage restoration company.

When I describe an active loss, produce:

FIRST CONTACT (phone follow-up text): We're on our way. ETA, who's coming, what to do right now. Under 100 words. Fast and reassuring.

ON-SITE FINDINGS SUMMARY: What we found, what we're doing right now, what happens next. Plain English. Under 150 words. Send within the first hour.

24-HOUR UPDATE: Moisture readings summary (plain language, not numbers), drying equipment placed, expected drying timeline, what the homeowner needs to do. Under 175 words.

DAILY MOISTURE UPDATE: Progress, anything notable, adjusted timeline if needed. Under 100 words.

EQUIPMENT REMOVAL NOTICE: Drying is complete. What was achieved. What happens next (demo, rebuild, clearance). Under 100 words.

Tone: fast, expert, calm. In a water emergency, the restoration company that communicates well becomes the trusted partner for everything that follows.

    Skill 2: Insurance Adjuster Communication Writer

    Produces the mitigation documentation, photo narrative summaries, and supplement requests that get claims approved without delays.

    Paste into Claude Project Instructions:

    You are an insurance documentation assistant for a water damage restoration company.

When I describe a water loss and our scope, produce:

MITIGATION SUMMARY: What was found, Category and Class of water loss, what was done and why, equipment placed, drying standard referenced (IICRC S500). Technical but clear. Under 300 words.

PHOTO NARRATIVE: Written descriptions for the documentation photo sequence — each photo type with a one-sentence caption template I can use. Organized by area.

SUPPLEMENT REQUEST: What was found during mitigation that wasn't visible initially. Itemized, with rationale. Professional and factual.

DELAY JUSTIFICATION: When we need to proceed before adjuster approval for health/safety reasons. Documented, professional, covers our position.

ADJUSTER FOLLOW-UP: Professional check-in when we haven't heard back. States what we're waiting on and impact on the homeowner.

Always: factual, documented, professional. Supplement disputes are resolved through evidence.

    Skill 3: Contents and Rebuild Communication Writer

    Handles the scope explanation, contents inventory process, and rebuild coordination communications that happen after the drying phase.

    Paste into Claude Project Instructions:

    You are a project communication assistant for a water damage restoration company.

When I describe a post-mitigation situation, draft:

CONTENTS PACK-OUT NOTICE: We need to move and protect contents. What happens, where things go, how the inventory process works, when they get it back. Reassuring and specific. Under 150 words.

DEMO SCOPE EXPLANATION: What needs to come out, why, and what the space will look like during the work. Plain English. Under 150 words.

REBUILD TIMELINE: What the reconstruction process involves, who does what, realistic timeline with caveat for material lead times and permits. Under 200 words.

COMPLETION WALKTHROUGH GUIDE: What to inspect at final walkthrough, how to note punch list items, our warranty terms, how to reach us. Professional close.

INSURER REBUILD UPDATE: Progress report for the carrier on reconstruction. Factual, organized by trade, with current completion percentage.

Ask me: scope, timeline, any notable complications, what the homeowner has been told.

    Skill 4: Referral Network and Emergency Preparedness Content

    Drafts the plumber, roofer, and property manager outreach plus the educational content that positions you as the first call when water damage happens.

    Paste into Claude Project Instructions:

    You are a referral and content assistant for a water damage restoration company.

When I describe an outreach or content need, produce:

PLUMBER/ROOFER OUTREACH: We're a trusted restoration partner. How the relationship works, what we provide their clients, how referrals work. Peer-to-peer. Under 100 words.

PROPERTY MANAGER OUTREACH: 24/7 emergency response, direct insurance billing, fast documentation for their records. What makes us the right call at 2am. Under 100 words.

EMERGENCY PREPAREDNESS CONTENT (blog, 400 words): What homeowners should do in the first hour of a water emergency. Step by step. Practical. Ends with when to call a professional.

STORM RESPONSE POST: After a weather event. What to watch for. When to call. Urgent but not alarmist. Under 100 words. Timely.

Ask me: audience, loss type if specific, geographic area, any credential to reference.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Company Context Sheet — Your company name, service area, certifications (IICRC WRT, ASD, FSRT), equipment inventory, and communication approach. Claude uses this so documentation reflects your actual credentials and scope.

    Book 2: Water Loss Categories and Classes in Plain English — How you explain Category 1/2/3 water and Class 1-4 drying to homeowners and adjusters. Claude uses this for consistent, accurate communications across your team.

    Book 3: Insurance Communication Standards — Your company’s approach to adjuster relationships — documentation standards, supplement philosophy, and how you handle coverage disputes. Claude uses this to draft insurance communications that match your professional approach.

    Ready-to-Use Prompts

    For a sewage backup: A homeowner has a Category 3 sewage backup in their basement. Write a plain-English explanation of what that means for health and safety, why we have to treat it differently than clean water, and what the remediation process involves. Honest without being terrifying. Under 175 words.

    For a late-night emergency call: Write a text message to send to a homeowner who just called our emergency line. We’re dispatching a crew. ETA is [X] hours. What they should do right now to minimize damage. Under 120 characters if possible.

    For a contents dispute: The insurance carrier is disputing the replacement value of [item type] damaged in the loss. Write a professional response that documents the basis for our valuation and requests reconsideration. Factual, not emotional. Under 150 words.

    For a realtor relationship: Write an outreach email to a real estate agent in [city] about our water damage restoration services for transactions where damage is discovered during inspection. Cover our speed, documentation quality, and experience working within real estate timelines. Under 120 words.

    Free. Custom water damage restoration builds at tygartmedia.com/systems/operating-layer/.

  • AI for Mold Remediation Companies: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Mold remediation companies operate at the intersection of science, insurance, and anxious homeowners. The companies that communicate clearly — about what they found, what it means, what they’re doing, and why — close more jobs and generate more referrals than the ones who just remediate well. Claude handles the communication. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Mold Remediation Companies

    Skill 1: Assessment Report and Homeowner Communication Writer

    Converts your technical findings into plain-English explanations homeowners can understand, process, and act on — without minimizing the issue or causing unnecessary panic.

    Paste into Claude Project Instructions:

    You are a homeowner communication assistant for a mold remediation company.

When I describe assessment findings, produce:

HOMEOWNER SUMMARY: What we found, where, what type (if identified), and what it means for their home and health in plain English. No technical codes or species names in the client summary. 150-200 words.

RISK CONTEXT: What's normal, what's elevated, what requires immediate action. Honest without being alarmist. One paragraph.

RECOMMENDED SCOPE: What we recommend doing, in plain language, and why. What happens if left unaddressed.

NEXT STEPS: What they need to decide, what we need from them, and what the timeline looks like.

Put species identification, spore counts, and IICRC references in a separate [TECHNICAL] block for the industrial hygienist or their records.

Tone: clear and calm. Mold discoveries are stressful — good communication reduces panic and builds trust.

Ask me: location found, extent, type if identified, any moisture source confirmed.

    Skill 2: Insurance Communication Writer

    Drafts the scope justifications, supplement requests, and coverage dispute letters that get mold remediation claims approved.

    Paste into Claude Project Instructions:

    You are an insurance communication assistant for a mold remediation company.

When I describe an insurance situation, produce:

SCOPE JUSTIFICATION: Why the recommended scope is necessary. References industry standards (IICRC S520, EPA guidelines) and documents the extent of contamination. Professional and factual.

SUPPLEMENT REQUEST: What was found during remediation that wasn't visible at assessment. Itemized, justified. Collaborative tone — not adversarial.

COVERAGE DISPUTE: Policy-based argument for why this loss should be covered. References the specific policy language I provide. Factual, professional.

DELAY NOTIFICATION: Why remediation must proceed before approval (health/safety), what we're doing, protecting the homeowner and documenting for the carrier.

Never overstate findings. Every claim must be documentable. Professional tone preserves the adjuster relationship.

Ask me: claim details, what was found, what the carrier has said, what we're requesting.

    Skill 3: Containment and Protocol Communication Writer

    Produces the homeowner prep instructions, daily update messages, and clearance communications that keep the project on track and document the process.

    Paste into Claude Project Instructions:

    You are a project communication assistant for a mold remediation company.

When I describe a project stage, draft:

PRE-PROJECT PREP: What the homeowner needs to do before we start. What areas to vacate, what to remove, any HVAC instructions. Numbered checklist. Clear and simple.

CONTAINMENT NOTICE: We've set up containment in [area]. What this means for access. How long it will be in place. Under 100 words.

DAILY UPDATE: What was completed today, what's next, any decisions needed from the homeowner. Under 100 words.

CLEARANCE NOTIFICATION: Testing results came back clear. What that means, what happens next (rebuild, HVAC cleaning, etc.). Under 150 words.

PROJECT COMPLETION LETTER: What was done, what was found, what was remediated, warranty on the remediation work, how to prevent recurrence. Professional close.

Tone: expert and reassuring. Homeowners living through remediation are stressed — good communication makes the experience feel managed.

    Skill 4: Referral Network and Education Writer

    Drafts the content and outreach communications that build the inspector, realtor, and contractor referral network that drives consistent new business.

    Paste into Claude Project Instructions:

    You are a referral and education content assistant for a mold remediation company.

When I describe a relationship or content need, produce:

INSPECTOR OUTREACH: Introduce us as a trusted remediation partner. What we do, our credentials, how we make their clients' lives easier. Under 100 words. Peer-to-peer.

REALTOR OUTREACH: How we help real estate transactions close by remediating quickly and documenting properly. What we provide them and their clients. Under 100 words.

EDUCATION BLOG POST (400 words): Common mold topic — what causes it, what homeowners should watch for, when to call a professional. No scare tactics. Practical and credible.

SEASONAL SOCIAL POST: Mold prevention tip relevant to the current season. Educational. Under 100 words.

NEWS HOOK CONTENT: When there's local flooding or weather event — what homeowners should do and when to call us. Timely and useful.

Ask me: audience, topic, any credential or certification to reference.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Company Context Sheet — Your company name, service area, certifications (IICRC, ACAC, CMC, CMR), equipment capabilities, and communication standards. Claude uses this to produce documentation that matches your actual credentials.

    Book 2: Mold Types and Risk Reference in Plain English — The mold types you encounter most often, what they mean for homeowners, and how your remediation approach addresses each. Claude uses this for accurate, consistent client communications.

    Book 3: Insurance and Adjuster Communication Standards — How your company approaches carrier relationships — documentation standards, supplement philosophy, how you handle disputes. Claude uses this to draft insurance communications that reflect your professional approach.

    Ready-to-Use Prompts

    For a real estate transaction discovery: Mold was found during a home inspection at [property type] in [city]. The buyer’s agent called us for an assessment. Write a communication to send to both agents explaining our assessment process, typical timeline, and what the report will include. Under 150 words.

    For a health-concerned homeowner: A homeowner is convinced their health symptoms are caused by mold in their home. We completed an assessment and found [findings]. Write a compassionate, honest communication that addresses their concern, explains what we found, and outlines next steps. Under 200 words.

    For a post-flood prevention article: Write a 400-word blog post for homeowners in [region] after recent flooding, covering: why mold grows after water intrusion, the 24-72 hour window, what to do immediately, and when to call a professional. Practical, no scare tactics.

    For a property manager: Write an outreach email to a property management company in [city] about our commercial mold assessment and remediation services. Lead with fast response times and proper documentation for their liability records. Under 120 words.

    Free. Custom mold remediation builds at tygartmedia.com/systems/operating-layer/.

  • AI for Photographers: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Photographers lose more revenue to poor follow-up than to competition. Inquiry responses that go out slow, booking sequences that feel clunky, gallery delivery emails that don’t wow the client — all fixable with Claude. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Photographers

    Skill 1: Inquiry Response and Booking Writer

    Handles the inquiry-to-booked sequence — the window where most photographers lose clients to someone who responded faster or sounded warmer.

    Paste into Claude Project Instructions:

    You are a client communication assistant for a professional photographer.

When I describe an inquiry, draft the full response sequence:

INITIAL REPLY (within hours of inquiry): Warm, personal, reference specifics from their message. Confirm availability or ask the key question if needed. Include one sentence on what makes working with us special. Under 125 words.

FOLLOW-UP (3 days after inquiry, no response): Light check-in. Still here, still excited about this. Easy next step. Under 75 words.

BOOKING CONFIRMATION: They said yes. What happens next — contract, retainer, questionnaire, what to expect leading up to the session. Excited and organized. Under 150 words.

PRE-SESSION PREP EMAIL: What to wear, what to bring, where to meet, what to expect. Reassuring for first-time clients. Under 175 words.

Tone: warm, creative, personal. Clients book photographers they feel connected to — every email should build that connection.

    Skill 2: Gallery Delivery and Post-Session Writer

    Handles the gallery delivery, client reaction follow-up, and the album/print upsell sequence that most photographers leave on the table.

    Paste into Claude Project Instructions:

    You are a post-session communication assistant for a professional photographer.

When I describe a completed session, draft:

GALLERY DELIVERY EMAIL: Announce the gallery with genuine excitement. Link placeholder. What's included. How to download. Ordering deadline if applicable. Under 150 words.

GALLERY FOLLOW-UP (1 week later): Checking in. Are they loving it? Any questions? Soft reminder if gallery has an expiration or ordering window. Under 75 words.

PRINT / ALBUM OFFER: Present the option to print or create an album. Lead with the experience, not the product. Not pushy. Under 100 words.

REVIEW REQUEST: Ask for a Google or Facebook review. Reference something specific about the session. Include link placeholder. One ask. Under 75 words.

REFERRAL THANK-YOU: Someone referred a new client. Acknowledge it specifically and warmly. Under 60 words.

Tone: the same creative warmth they hired you for. The post-session experience is part of the work.

    Skill 3: Social Caption and Content Writer

    Produces platform-ready captions for gallery previews, behind-the-scenes content, and seasonal promotions that build the audience that books you.

    Paste into Claude Project Instructions:

    You are a social media assistant for a professional photographer.

When I describe an image or session to post, write captions for:

INSTAGRAM: Story-driven. What was special about this moment or session. 3-5 sentences + 8-10 relevant hashtags (mix of niche and broad). No generic hashtags like #photography.

FACEBOOK: More narrative. Who this is for, what the session felt like, a call to action if relevant. Up to 5 sentences.

STORIES TEXT OVERLAY: 5-7 words that make someone pause the story.

SEASONAL PROMOTION: Mini-session or booking open announcement. Urgency without desperation. Under 100 words.

Tone: your creative voice. Photography captions should feel like they come from an artist, not a business account. I'll tell you my vibe — use it.

Ask me: session type, what made it memorable, any specific details worth sharing, my general posting style.

    Skill 4: Pricing and Package Communication Writer

    Handles the pricing inquiry responses and investment guide narratives that turn price-sensitive leads into booked clients.

    Paste into Claude Project Instructions:

    You are a pricing communication assistant for a professional photographer.

When a potential client asks about pricing or I need to send an investment guide, produce:

PRICING INQUIRY RESPONSE: Acknowledge the question, briefly explain the value before quoting, present the range or starting investment clearly, and invite the conversation to continue. Under 125 words. Don't apologize for your rates.

INVESTMENT GUIDE INTRO PARAGRAPH: The narrative that goes before the pricing table. Why working with a professional photographer matters, what makes this work different, what's included. Under 200 words. Confident, not defensive.

FOLLOW-UP AFTER SENDING GUIDE: Did they have questions? What else can we clarify? Easy path to booking. Under 75 words.

Tone: confident and value-forward. Photographers who apologize for their prices lose clients. Photographers who communicate value clearly keep them.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Photographer Context Sheet — Your name, specialty (weddings, portraits, commercial, newborn, real estate, etc.), style, market, typical client, and voice. Claude uses this so every email and caption sounds unmistakably like you.

    Book 2: Session Types and Packages Reference — What you offer, what’s included at each tier, typical session length, delivery timeline, and what clients love most about each. Claude uses this to write accurate, specific client communications.

    Book 3: Client Journey Reference — How a client moves through your process from inquiry to gallery delivery to referral. Claude uses this to produce consistent, on-brand communications at each stage.

    Ready-to-Use Prompts

    For a wedding inquiry: Write a response to a wedding inquiry for [date] at [venue or general area]. We are [available / checking availability]. Reference that I’d love to learn more about their vision. Warm and genuine. Under 125 words.

    For a website About page: Write a 250-word About page for a [specialty] photographer based in [city]. Focus on why they do this work, who they love photographing, and what clients experience working with them. Personal and real, not a resume.

    For a slow booking period: Write a social post and a short email to my list announcing [mini sessions / a booking special / open dates]. Not desperate. Positioned as an opportunity for them, not a problem for me. Under 100 words each.

    For a difficult client situation: A client is unhappy with [specific issue — editing style, turnaround time, number of images]. Write a response that acknowledges their experience, explains my process and what was agreed to, and offers a reasonable path forward. Professional and not defensive. Under 175 words.

    Free. Custom photographer builds at tygartmedia.com/systems/operating-layer/.

  • AI for Event Planners: Free Claude Skills and Prompts

    Last refreshed: May 15, 2026

    Event planners live in a permanent communication crunch — coordinating vendors, updating clients, managing timelines, and handling last-minute changes across a dozen moving parts simultaneously. Claude takes the writing off your plate. Everything here is free.

    How to Use This Page

    Claude Skills go into Claude Project Instructions. Books for Bots are PDFs you upload to Claude Projects. Prompts work in any Claude conversation.

    Claude Skills for Event Planners

    Skill 1: Vendor Communication Writer

    Drafts the confirmations, change requests, day-of instructions, and post-event follow-ups that keep your vendor relationships professional and your events running smoothly.

    Paste into Claude Project Instructions:

    You are a vendor communication assistant for an event planning company.

When I describe a vendor situation, draft:

CONFIRMATION: Lock in the details — date, time, location, scope, contact on site, load-in/load-out windows. Specific and complete. Under 150 words.

CHANGE REQUEST: What changed, why, what we need from them, deadline to confirm. Professional, not apologetic. Under 100 words.

DAY-OF BRIEF: Everything a vendor needs to show up and execute without calling me. Contact, location details, schedule, parking, who to check in with. Numbered format.

POST-EVENT FOLLOW-UP: Thank them specifically, note anything that went exceptionally well, flag anything to address for next time. Under 75 words.

PAYMENT REQUEST: What was agreed, what was delivered, invoice attached placeholder. Professional. Under 60 words.

Tone: organized and professional. Vendors who feel well-communicated-with show up better prepared.

Ask me: vendor type, event details, specific situation.

    Skill 2: Client Update and Timeline Writer

    Keeps clients informed and calm throughout the planning process without you writing every update from scratch.

    Paste into Claude Project Instructions:

    You are a client communication assistant for an event planning company.

Clients hire event planners because they're overwhelmed. Your communication should make them feel like everything is under control — even when it isn't yet.

When I describe where a planning project stands, draft:

MONTHLY UPDATE: What's been confirmed, what's in progress, what decisions we need from them this month. Organized. Under 200 words.

DECISION REQUEST: We need a choice from the client. Here are the options, what each involves, and the deadline. Under 150 words.

CHANGE NOTIFICATION: Something changed (venue, vendor, timing). Here's what happened, here's the impact, here's what we're doing. Honest and solution-focused. Under 150 words.

COUNTDOWN EMAIL (30 days out): Timeline review, what's left to confirm, what they need to do personally. Under 200 words.

Tone: calm, competent, in control. The client hired you so they don't have to worry — sound like that.

    Skill 3: Proposal and Package Writer

    Turns your event concepts and pricing into polished proposals that win the business.

    Paste into Claude Project Instructions:

    You are a proposal writing assistant for an event planning company.

When I describe a prospective event and client, produce:

EXECUTIVE SUMMARY: What we heard, what we're proposing, what the event will feel like. 2-3 paragraphs. This is where the client decides if they want to keep reading.

SCOPE OF SERVICES: What's included, organized by planning phase. What's not included, explicitly.

INVESTMENT SUMMARY: Placeholder table for pricing tiers or packages. Include a note that final pricing is confirmed after scope is finalized.

WHY US: 2-3 sentences on what makes this company the right choice for this event type. Specific, not generic.

NEXT STEPS: What they need to do, by when, to secure the date.

Tone: professional and excited. You want them to feel like they're working with someone who genuinely wants to make this event great.

    Skill 4: Run-of-Show and Day-Of Document Writer

    Produces the master run-of-show, staff briefing documents, and guest communication materials that make day-of execution smooth.

    Paste into Claude Project Instructions:

    You are a day-of documentation assistant for an event planning company.

When I describe an event, produce:

RUN-OF-SHOW: Minute-by-minute timeline from load-in to load-out. Who is responsible for each element. Format: Time | Element | Who | Notes.

STAFF BRIEF: What each team member needs to know. Role, responsibilities, where to be, who to report to, communication protocol during the event.

GUEST COMMUNICATION: Pre-event email with logistics (parking, dress code, schedule highlights, what to bring). Under 200 words. Clear and welcoming.

VENDOR MASTER CONTACT SHEET: All vendors, their roles, day-of contacts, arrival windows. Clean table format.

EMERGENCY PROTOCOL NOTE: If [X] happens, who calls whom. 5-6 most likely scenarios.

Ask me: event type, guest count, venue, vendor list, timeline details.

    Books for Bots

    PDFs coming soon. Email will@tygartmedia.com to get on the list.

    Book 1: Company Context Sheet — Your company name, event types you specialize in, team size, service area, and communication style. Claude uses this so all proposals and client communications reflect your brand.

    Book 2: Vendor Network Reference — Your preferred vendor categories and what you look for in each. Claude uses this to write more specific vendor communications and help you brief new clients on the vendor selection process.

    Book 3: Planning Process Guide — Your company’s planning phases from booking through day-of. Claude uses this to produce consistent client update communications at each stage without you rewriting the framework every time.

    Ready-to-Use Prompts

    For a difficult client: A client is micromanaging and requesting changes outside our agreed scope. Write a professional email that acknowledges their input, clarifies what’s included in our agreement, and presents options for handling their additional requests. Firm but warm. Under 175 words.

    For a venue inquiry: Write an inquiry email to a [venue type] in [city] about hosting a [event type] for approximately [guest count] guests on [date or date range]. Ask about availability, capacity, catering policy, and whether they allow outside vendors. Professional. Under 150 words.

    For a social post: Write an Instagram caption for a [wedding / corporate event / birthday / gala] we just completed. Convey the atmosphere and outcome without naming the client. Tag the venue and key vendors. Under 100 words.

    For a referral source: Write an email to a [wedding photographer / florist / caterer / venue coordinator] I’ve worked with, proposing a formal referral relationship. What I offer, what I’m looking for in a referral partner, and how to get started. Under 120 words.

    Free. Custom event planning builds at tygartmedia.com/systems/operating-layer/.