Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
vigilante-issue-implementation-on-bazel
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Bazel monorepo.
majiayu000/claude-skill-registry 163
-
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
majiayu000/claude-skill-registry 163
-
prompt-enricher
Phase 0.2 — Enriches the raw user prompt with discovered constraints, ambiguities, likely edge cases, and suggested scope boundaries. Runs after context-gatherer, before idea-explorer questions. Generates enriched-prompt.md in the state directory.
majiayu000/claude-skill-registry 163
-
fetching-library-docs
Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings.
Fetches code examples, API references, and usage patterns for published libraries (React,
Next.js, Prisma, etc). Use when users ask "how do I use X library", need code examples,
want API syntax, or are learning a framework's official API. Triggers: "Show me React hooks",
"Prisma query syntax", "Next.js routing API". NOT for exploring repo internals/source code
(use researching-with-deepwiki) or local files.
majiayu000/claude-skill-registry 163
-
fix-line-endings-check-bash
Fix line endings AND check bash syntax in one step (recommended). Use after creating or editing bash scripts.
majiayu000/claude-skill-registry 163
-
plugin-hook-system
Generate hook-based plugin extension system with event emitter patterns.
majiayu000/claude-skill-registry 163
-
wordpress-elementor
Edit Elementor pages and manage templates on WordPress sites. Workflow: identify page, choose editing method (browser or WP-CLI), execute, verify. Use when editing Elementor pages, updating text in Elementor widgets, applying or managing Elementor templates, or making content changes to pages built with Elementor page builder.
majiayu000/claude-skill-registry 163
-
Playwright Browser Automation
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
majiayu000/claude-skill-registry 163
-
ap2-human-present-flow
Implement the AP2 human-present transaction flow — the checkout process where the user is actively present to confirm cart details and payment method selection. The primary VDC in this flow is the Cart Mandate. Use when building interactive agentic checkout with user in the loop.
majiayu000/claude-skill-registry 163
-
telegram-bot-builder
Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.
majiayu000/claude-skill-registry 163
-
docs-init
(ePost) Scan codebase and generate comprehensive documentation
majiayu000/claude-skill-registry 163
-
Global Coding Style
Maintain consistent code formatting, naming conventions, type safety, and automated code quality standards across PHP and TypeScript/JavaScript. Use this skill when writing or editing any PHP files (.php), TypeScript/JavaScript files (.ts, .tsx, .js, .jsx), when implementing type declarations and return types, when running code formatters (Laravel Pint, Ultracite) or linters, when running static analysis tools (Larastan), when naming variables, functions, classes, or files, when applying DRY principles, when removing dead code, or when preparing code for review or commit.
majiayu000/claude-skill-registry 163
-
ablation-planner
Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.
majiayu000/claude-skill-registry 163
-
voice-gate
majiayu000/claude-skill-registry 163
-
labarchive-integration
Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.
majiayu000/claude-skill-registry 163
-
lex
Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.
majiayu000/claude-skill-registry 163
-
backend
Servers, routes, APIs, and backend architecture. Activated when Claude creates server-side code, API routes, or Express/Fastify/Next.js API handlers.
majiayu000/claude-skill-registry 163
-
llm-tuning-patterns
LLM Tuning Patterns
majiayu000/claude-skill-registry 163
-
hexagonal-architecture-layers-java
Hexagonal architecture layering for Java services with strict boundaries. Trigger: When structuring Java apps by Domain/Application/Infrastructure, or refactoring toward clean architecture.
majiayu000/claude-skill-registry 163
-
stitch-mcp-list-screens
Lists all screens in a Stitch project. Use this after generate_screen_from_text to find the screenId of the newly generated screen, then call stitch-mcp-get-screen to retrieve it.
majiayu000/claude-skill-registry 163
-
deep-analysis
Deep codebase exploration and synthesis using parallel task agents with dynamic planning. Use when asked for "deep analysis", "analyze codebase", "explore and analyze", "investigate codebase", or "deep understanding".
majiayu000/claude-skill-registry 163
-
devils-advocate
Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments, identify weak points, and challenge assumptions before editorial polish (mandatory for Writer → Devil's Advocate pairing protocol)
majiayu000/claude-skill-registry 163
-
k6-load-testing
Comprehensive k6 load testing skill for API, browser, and scalability testing. Write realistic load scenarios, analyze results, and integrate with CI/CD.
majiayu000/claude-skill-registry 163
-
cass
Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.
majiayu000/claude-skill-registry 163