Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
supabase-expert
This skill should be used when working with Supabase database operations in the MyJKKN project, including creating modules, updating schemas, writing RLS policies, creating database functions, implementing Auth SSR, or developing Edge Functions. Automatically triggers when user mentions 'database', 'table', 'SQL', 'Supabase', 'migration', 'RLS', 'policy', or 'Edge Function'.
majiayu000/claude-skill-registry 163
-
planning
Use when you need to plan technical solutions that are scalable, secure, and maintainable.
majiayu000/claude-skill-registry 163
-
browser-testing-playwright
A skill for setting up and running end-to-end browser tests using Playwright. It includes guidance on project setup, the Page Object Model, user flow testing, visual regression, cross-browser configuration, and CI integration. Use this when a user wants to implement browser-based E2E testing.
majiayu000/claude-skill-registry 163
-
human-extractor
GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users need to extract human presence from videos, analyze dashcam footage for people detection, perform investigative analysis of human subjects in recordings, or classify individuals with optional head covering detection.
majiayu000/claude-skill-registry 163
-
refactor-simplify-branching
[Code Quality] Simplifies complex conditionals: deep nesting, long if-else chains, switch sprawl. Use when control flow is hard to follow or has high cyclomatic complexity.
majiayu000/claude-skill-registry 163
-
org
Org-mode manual (25K lines info).
majiayu000/claude-skill-registry 163
-
github-actions-debugging
Debug and fix GitHub Actions CI/CD failures
majiayu000/claude-skill-registry 163
-
sop-code-review
Comprehensive code review workflow coordinating quality, security, performance, and documentation reviewers. 4-hour timeline for thorough multi-agent review.
majiayu000/claude-skill-registry 163
-
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
majiayu000/claude-skill-registry 163
-
youtube-seo-optimizer
Optimize YouTube videos for search and discovery. Generates SEO-optimized titles, descriptions, tags, hashtags, and chapters. Includes keyword research and competitor analysis. Use when publishing videos, improving discoverability, or optimizing existing content.
majiayu000/claude-skill-registry 163
-
optimize-costs
Analyze Cloudflare architecture and predict monthly costs with optimization recommendations. Use this skill when the user asks about costs, billing, pricing, or wants to understand their Cloudflare spend. Works with wrangler configs, observability data, and AI Gateway logs.
majiayu000/claude-skill-registry 163
-
agent-native-reviewer
Use this agent when reviewing code changes to ensure features are agent-native - any action a user can take, an agent can also take, and anything a user can see, an agent can see. Triggers on requests like "agent-native review", "AI accessibility check".
majiayu000/claude-skill-registry 163
-
gamma-local-dev-loop
Set up efficient local development workflow for Gamma.
Use when configuring hot reload, mock responses,
or optimizing your Gamma development experience.
Trigger with phrases like "gamma local dev", "gamma development setup",
"gamma hot reload", "gamma mock", "gamma dev workflow".
majiayu000/claude-skill-registry 163
-
design-engineer-mindset
Understand the Design Engineer role - bridging design and implementation. Learn to think about design as code, understand rendering pipelines, optimize animation performance, and ensure design fidelity through implementation. Use when translating designs to code, optimizing performance, or ensuring quality through development.
majiayu000/claude-skill-registry 163
-
json-render-ui-oaustegard-claude-skills-768ccf84
majiayu000/claude-skill-registry 163
-
bch-development
Bitcoin Cash (BCH) API implementation rules. Critical pattern for embedding Bitcoin struct and overriding BCH-specific methods. Use when working on BCH-related code in internal/infrastructure/api/btc/bch/.
majiayu000/claude-skill-registry 163
-
sitl-arm-sensei-hacker-inav-claude-2
Arm INAV SITL via MSP protocol for automated testing
majiayu000/claude-skill-registry 163
-
writing-press-releases
Generates professional press releases with headline, dateline, inverted pyramid structure, and boilerplate. Use when the user asks about press releases, media announcements, news releases, PR distribution, or journalist outreach.
majiayu000/claude-skill-registry 163
-
Building Blocks
Guide for creating new AEM Edge Delivery blocks or modifying existing blocks. Use this skill whenever you are creating a new block from scratch or making significant changes to existing blocks that involve JavaScript decoration, CSS styling, or content model changes.
majiayu000/claude-skill-registry 163
-
validate-ai
Test AI meal plan generation with keto compliance and structural validation
majiayu000/claude-skill-registry 163
-
reflection-interview
Interactive interview for journal entry reflections. Covers all 5 research sub-questions (Workflow, Autorschaft, Iteration, Scheitern, Ästhetik) aligned with the main research question.
majiayu000/claude-skill-registry 163
-
writing-docs
Expert at writing high-quality documentation for code, APIs, and projects. Auto-invokes when generating docstrings, creating README files, writing API documentation, adding code comments, or producing any technical documentation. Provides language-specific templates and best practices for effective documentation writing.
majiayu000/claude-skill-registry 163
-
hughes-property-based-testing
Test software in the style of John Hughes, inventor of QuickCheck and property-based testing. Emphasizes specifying properties that should hold for all inputs, generating random test cases, and shrinking failures to minimal examples. Use when testing algorithms, data structures, parsers, serializers, or any code with clear invariants.
majiayu000/claude-skill-registry 163
-
cli-dontizi-codegeass
majiayu000/claude-skill-registry 163