Your CLAUDE.md is how Claude Code understands your project. A good one makes everything faster. A bad one wastes tokens on every single message.

Submit ISC2 CPE credits on cpe.isc2.org. Use when the user wants to log continuing education activities for CISSP, CCSP, or other ISC2 certifications.

Manages YouTube channels and videos via the YouTube Data API v3, using the `scripts/yt.py` helper and the official `google-api-python-client` SDK. All operations are authenticated with OAuth2 and cred

Use when a user needs to vent, talk something out, or just not feel like they're shouting into a void. Active listening with gentle reflection — not therapy, not silence, just a friend who pays attention.

Design AI-powered customer service automation systems. Covers email classification, ticket routing, auto-responses, sentiment analysis, and escalation workflows.

legal-how-to

mp-dig

pine-function-lookup

property-quick-comps

reduced-listings

rightmove-quick-search

thread-reply

Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.

>

This skill is a self-correcting creative agency and a startup within an agent.

A comprehensive, field-agnostic skill for tailoring resumes, cover letters, and interview prep to any job posting. Built to eliminate the generic-AI smell and produce evidence-based application materi

Meet CAN-SPAM, GDPR, and CASL email requirements. Use when sending commercial email, implementing unsubscribe, managing consent, or classifying transactional vs commercial messages.

Classify inbound email replies by intent and route them appropriately. Use when building reply handling for outreach, support, or transactional email - detecting interested, not interested, OOO, bounce, unsubscribe, forwarded, and question replies.

Choose and configure an agent-native inbox provider for AI agents that send and receive email. Use when giving an AI agent its own email address, setting up two-way agent email communication, comparing agent inbox platforms, or adding guardrails to autonomous email workflows.

Process email bounces and protect sender reputation. Use when handling hard/soft bounces, building suppression lists, configuring retry strategies, or investigating high bounce rates.

Design automated email sequences and drip campaigns. Use when building onboarding flows, nurture sequences, re-engagement campaigns, or follow-up automation.

Design product notification emails. Use when building activity alerts, digests, status updates, or managing notification frequency and user preferences.

Build welcome and activation email sequences. Use when designing signup flows, driving users to key actions, converting trials to paid, or reducing early churn.

Design and send transactional emails. Use when building password resets, receipts, shipping notifications, account alerts, or separating transactional from marketing streams.

Use when building or understanding agent-to-agent communication systems. Explains the A2A protocol for inter-agent coordination above MCP.

Use when deploying agents in regulated industries or needing compliance guidance. Covers EU AI Act, NIST AI RMF, and ISO 42001 for agent operators.

Use when estimating or optimising LLM costs for agent operations. Framework for calculating actual monthly spend including hidden multipliers.

Use when deploying a new agent into production. Checklist for onboarding agents.

Use when hardening agents before deployment. 10-point pre-deployment security checklist.

Use when building self-diagnostic capabilities into agents. A prompt agents can run to diagnose themselves.

Use when designing alignment into agent architecture. Structural alignment — building it in, not bolting it on.

Use when securing autonomous agent deployments. Quick security reference for autonomous agents.

Use when making agents feel present rather than scripted. The 25-line fix for AI personas that break character.

Use when building an MCP server from zero. Step-by-step guide to creating Model Context Protocol servers.

Use when coordinating agents without a central controller. Stigmergic coordination patterns.

Use when defending against prompt injection attacks. The Airlock Pattern and five attack surfaces.

Use when applying proven system prompt patterns to agents. 7 patterns every agent operator needs.

Use when implementing multi-agent chat handoff in Telegram. The handoff pattern for chat systems.

Use when learning about stigmergic coordination for AI agents. Coordination through environment, not command.

>

>

compose-ui

High-fidelity distilled literary persona for 韓愈

High-fidelity distilled literary persona for 蘇軾

High-fidelity distilled literary persona for Ernest Hemingway

High-fidelity distilled literary persona for William Shakespeare

Multi-turn conversation with an external reasoning model (DeepSeek Reasoner, o1, o3) via any OpenAI-compatible API. Session persistence, pushback workflow, and structured reports. Use for proof verification, reasoning tasks, or getting a second opinion.

Search for any used or new car near a given zip code using the Auto.dev listings API. Filter by make, model, year, price, mileage, fuel type, and radius. Score and rank results. Activate when the user asks to find a car, search listings, look up vehicles, or check what cars are available near them.

Use this skill when the user asks about Pokemon card grading, value, or whether a card is worth grading/slabbing. Triggers: 'should I grade', 'should I slab', 'is this card worth grading', 'pokemon card value', 'PSA grade', 'card worth', 'grade or not', 'shouldislab', 'slab check'. Looks up card data, pricing (raw vs graded), estimates grading ROI, and gives a clear slab-or-skip verdict. Do NOT use for: non-Pokemon TCG cards, general Pokemon game questions, deck building, or card generation.

Verifies phone numbers via SMS OTP using the Sendly Verify API. Sends codes, checks codes, handles expiry, and provides hosted verification sessions. Applies for phone verification, OTP, 2FA, or passwordless login flows.