Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
thought-leadership
Creates value-packed, niche-specific, thought leadership newsletters (800-1,500 words) with irresistible subject lines, skimmable headers, and actionable content. Uses proven frameworks for headlines, introductions, and sectioning. Use when user mentions "write newsletter", "thought leadership content", "weekly newsletter", or wants to create educational, value-driven newsletter content.
majiayu000/claude-skill-registry 163
-
swot-pestle-analysis
Strategic environmental analysis using SWOT, PESTLE, and Porter's Five Forces. Creates structured assessments with Mermaid visualizations for competitive positioning and strategic planning.
majiayu000/claude-skill-registry 163
-
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
majiayu000/claude-skill-registry 163
-
threejs-agents-model-optimizer
Use when optimizing 3D models for web delivery: reducing file size, compressing meshes, optimizing textures, or generating LOD. Provides a complete GLTF optimization pipeline using Draco, KTX2, mesh simplification, and gltf-transform. Keywords: optimize model, reduce file size, Draco compression, KTX2, gltf-transform, mesh simplification, LOD, GLTF optimize, bundle size.
majiayu000/claude-skill-registry 163
-
playwright-expert
Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing.
majiayu000/claude-skill-registry 163
-
Test-Driven Development
This skill should be used when the user asks to "implement TDD", "write tests first", "follow RED-GREEN-REFACTOR", "use test-driven development", "create failing tests", or mentions TDD workflow patterns.
majiayu000/claude-skill-registry 163
-
airflow-dag-patterns
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
majiayu000/claude-skill-registry 163
-
create-agent-skill
Create or edit Claude Code skills with expert guidance on structure and best practices
majiayu000/claude-skill-registry 163
-
supply-chain-security
Typosquatting detection, install script analysis, dependency confusion prevention, and phantom dependency detection for npm/pip.
majiayu000/claude-skill-registry 163
-
session-handoff
Compresses the current session state into a handoff document for seamless
continuation in the next session. Captures progress, decisions, blockers,
and next steps. Use at the end of a session or when context is getting large.
majiayu000/claude-skill-registry 163
-
arcanea-design-system
The complete Arcanean Design System - cosmic visual language, academy themes, component patterns, and design tokens for magical interfaces
majiayu000/claude-skill-registry 163
-
create-pr
Create a GitHub PR with a well-formatted description including summary, categorized changes, and attention areas
majiayu000/claude-skill-registry 163
-
project-task-manager
Use AgentPMT external API to run the Project Task Manager tool with wallet signatures, credits purchase, or credits earned from jobs.
majiayu000/claude-skill-registry 163
-
code-review-medium
Standard code review for medium PRs (100-500 lines). Includes code quality, security basics, and test coverage analysis.
majiayu000/claude-skill-registry 163
-
claude-review
Review code changes using Hyperlane Warp UI coding standards. Use when reviewing PRs, checking your own changes, or doing self-review before committing.
majiayu000/claude-skill-registry 163
-
github
Use the GitHub CLI (`gh`) to inspect and manage repositories, pull requests, issues, workflows, releases, and API calls from the terminal. Use when a user asks to use `gh`/GitHub CLI, run GitHub repo or PR workflows, automate GitHub Actions from shell, or troubleshoot `gh` authentication and configuration.
majiayu000/claude-skill-registry 163
-
sentry-load-scale
Manage scale Sentry for high-traffic applications.
Use when optimizing for high event volumes,
managing costs at scale, or tuning for performance.
Trigger with phrases like "sentry high traffic", "scale sentry",
"sentry high volume", "sentry millions events".
majiayu000/claude-skill-registry 163
-
onboarding-ux
Audit and generate in-app user guidance — onboarding flows, empty states, tooltips, feature tours, contextual help, defaults, and inline hints. Browses the app to find where new users would get stuck, then produces the actual content and code to fix it. Pairs with ux-audit: audit finds problems, this skill builds the solutions. Triggers: 'onboarding', 'help content', 'empty states', 'user guidance', 'first run experience', 'feature tour', 'app is confusing', 'new user experience', 'make the app welcoming'.
majiayu000/claude-skill-registry 163
-
tdd
Test-driven development — write failing test first, then implement (red-green-refactor)
majiayu000/claude-skill-registry 163
-
buhi
Audible notifications for Claude Code tasks and user confirmations. Use this skill when the user wants to (1) test the notification sound by running /buhi, (2) hear the notification sound manually, or (3) get help with configuring automatic sound playback on task completion and user confirmation requests using Claude Code's hook system (Stop hook and PreToolUse hook with AskUserQuestion matcher). The skill automatically detects whether it's installed globally or locally and configures the appropriate settings.json file with absolute paths.
majiayu000/claude-skill-registry 163
-
midnight-tooling:midnight-compatibility
Use when checking Midnight version compatibility, understanding pragma language_version, verifying compiler and runtime version relationships, or troubleshooting version mismatch errors between Midnight components.
majiayu000/claude-skill-registry 163
-
output-style-builder
Creates structured output formats (JSON/YAML/Markdown-KV/XML) and response style scope configurations via accuracy-token tradeoff analysis. Use when defining agent schemas, building CLAUDE.md output sections, configuring hierarchy overrides, or standardizing serialization patterns across agents/commands.
majiayu000/claude-skill-registry 163
-
ai-generated-readme-banners
Create professional ultra-wide cinematic banners for GitHub READMEs using Flux and Ideogram models with typography options
majiayu000/claude-skill-registry 163
-
clean-code
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
majiayu000/claude-skill-registry 163