Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
dependency-injection-fastapi
Implement FastAPI dependency injection with Depends(), security dependencies, database session management, request-scoped deps, and testing with overrides. Use when the user builds FastAPI endpoints, manages database connections, implements auth, or asks about dependency injection. Trigger when you see repeated setup logic in endpoint functions that should be extracted to dependencies.
majiayu000/claude-skill-registry 163
-
songsee
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
majiayu000/claude-skill-registry 163
-
implementing-e2e-testing
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
majiayu000/claude-skill-registry 163
-
alphaear-sentiment
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.
majiayu000/claude-skill-registry 163
-
email-systems
Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders.
majiayu000/claude-skill-registry 163
-
typescript-expert
TypeScript and JavaScript expert with deep knowledge of type-level programming, performance optimization, monorepo management, migration strategies, and modern tooling.
majiayu000/claude-skill-registry 163
-
llm-patterns
AI-first application patterns, LLM testing, prompt management
majiayu000/claude-skill-registry 163
-
schema-markup
Design, validate, and optimize schema.org structured data for eligibility, correctness, and measurable SEO impact. Use when the user wants to add, fix, audit, or scale schema markup (JSON-LD) for rich results. This skill evaluates whether schema should be implemented, what types are valid, and how to deploy safely according to Google guidelines.
majiayu000/claude-skill-registry 163
-
theharvester
Passive email, subdomain, and IP harvesting from public sources using theHarvester. Use when: gathering corporate email lists, enumerating subdomains passively, pre-engagement recon, finding exposed employee contacts without triggering alerts.
majiayu000/claude-skill-registry 163
-
prometheus-configuration
Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules.
majiayu000/claude-skill-registry 163
-
motherduck-build-dashboard
Build a live MotherDuck dashboard as a Dive. Use when composing one shareable KPI, trend, and breakdown story over existing MotherDuck data, especially when the result should stay a saved workspace artifact rather than a full application.
majiayu000/claude-skill-registry 163
-
integration-nextjs-app-router
PostHog integration for Next.js App Router applications
majiayu000/claude-skill-registry 163
-
product-review
Product-taste review that challenges 'are we building the right thing?' Four modes: EXPAND (dream big), HOLD (maximum rigor), REDUCE (strip to essentials), DESIGN (UX-first). Run before /spec or standalone. Use DESIGN mode for UI-heavy features.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
agent-architecture
Agent skill for architecture - invoke with $agent-architecture
majiayu000/claude-skill-registry 163
-
security-auditor
MASTER SECURITY: OWASP Top 10, SAST/DAST, PenTest, Auth/JWT Audit, Data Encryption, Incident Response. Use for Code Security, Armor config, and Audits.
majiayu000/claude-skill-registry 163
-
agentforge-browser-tooling
Work on browser automation support in AgentForge, including the browser tool abstraction and Playwright-backed execution.
majiayu000/claude-skill-registry 163
-
frontend-ui-ux
Designer-turned-developer who crafts stunning UI/UX even without design mockups
majiayu000/claude-skill-registry 163
-
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
majiayu000/claude-skill-registry 163
-
seo-monitor
Batch monitor SEO health across all active client sites. Checks for regressions, starts fresh crawls for stale data, and generates a summary report. Trigger with 'seo monitor', 'check all seo', 'seo batch check', 'weekly seo', or 'monitor sites'.
majiayu000/claude-skill-registry 163
-
development-workflow
detailed development workflow with modular patterns for git, code review, testing, documentation, and deployment
majiayu000/claude-skill-registry 163
-
debug-helper
Systematic debugging strategies, troubleshooting methodologies, and problem-solving techniques for code and system issues. Use when the user encounters bugs, errors, or unexpected behavior and needs help diagnosing and resolving problems.
majiayu000/claude-skill-registry 163
-
existing-solution-map
majiayu000/claude-skill-registry 163