Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
business-intelligence
Expert business intelligence covering dashboard design, data visualization, reporting automation, and executive insights delivery.
majiayu000/claude-skill-registry 163
-
task-master
AI-powered task management for structured, specification-driven development. Use this skill when you need to manage complex projects with PRDs, break down tasks into subtasks, track dependencies, and maintain organized development workflows across features and branches.
majiayu000/claude-skill-registry 163
-
quantum-mechanics
Quantum mechanics from wave-particle duality through entanglement and measurement. Covers the photoelectric effect, de Broglie wavelength, Heisenberg uncertainty principle, the Schrodinger equation (time-dependent and time-independent), wave functions and probability, quantum states and superposition, the hydrogen atom (energy levels, quantum numbers), spin, Pauli exclusion principle, quantum tunneling, Feynman path integrals (conceptual), QED basics, entanglement (Bell's theorem), the measurement problem, and Dirac notation. Use when analyzing phenomena at atomic or subatomic scales where classical physics breaks down.
majiayu000/claude-skill-registry 163
-
api-baas-vercel-kv
Serverless Redis-compatible key-value store via Upstash REST API -- edge-compatible, automatic JSON serialization, TTL-based caching
majiayu000/claude-skill-registry 163
-
code-review-ai-ai-review
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
majiayu000/claude-skill-registry 163
-
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
majiayu000/claude-skill-registry 163
-
connect
Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.
majiayu000/claude-skill-registry 163
-
llm-pretraining
Plan and execute large language model pretraining from data preparation to checkpoint management
majiayu000/claude-skill-registry 163
-
pr-rene-kuhm-opencode-ohmyopencod
Crear Pull Requests con template, descripción automática y checklist. Integración con GitHub.
majiayu000/claude-skill-registry 163
-
react-hook-form
Performant React forms with minimal re-renders and built-in validation
majiayu000/claude-skill-registry 163
-
secrets
Secret management patterns for the Kubernetes homelab platform.
Covers secret-generator, ExternalSecret, app-secrets module, and cross-namespace replication.
Use when: (1) Adding secrets for a new application, (2) Deciding between secret-generator
and ExternalSecret, (3) Configuring cross-namespace secret replication, (4) Creating
persistent secrets via the app-secrets Terragrunt module, (5) Debugging secret sync failures.
Triggers: "secret", "ExternalSecret", "secret-generator", "aws ssm", "parameter store",
"kubernetes-replicator", "replicate secret", "app-secrets", "persistent secret",
"cross-namespace secret", "secret not syncing", "ClusterSecretStore"
majiayu000/claude-skill-registry 163
-
evaluation
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
majiayu000/claude-skill-registry 163
-
research-review
Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
majiayu000/claude-skill-registry 163
-
projects
This skill should be used when the user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.
majiayu000/claude-skill-registry 163
-
different-name
A skill with a name that doesn't match the directory.
majiayu000/claude-skill-registry 163
-
promo-director
Generates 15-second vertical promo videos for social media from mastered audio. Use after mastering is complete and before release, when the user wants social media content.
majiayu000/claude-skill-registry 163
-
vulnerability-scan
Scan for specific vulnerabilities in dependencies and configurations
majiayu000/claude-skill-registry 163
-
autonomous-agent-patterns
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool APIs, implementing permission systems, or creating autonomous coding assistants.
majiayu000/claude-skill-registry 163
-
create-custom-viewer
Develop a custom JavaScript viewer extending DG.JsViewer with properties, rendering, and interactivity
majiayu000/claude-skill-registry 163
-
hotfix
Emergency production fix — branch, fix, test, merge, release in minimal steps (Marcus workflow)
majiayu000/claude-skill-registry 163
-
moai-cc-claude-md
Claude Code Markdown integration, documentation generation, and structured content patterns. Use when generating documentation, managing markdown content, or creating structured reports.
majiayu000/claude-skill-registry 163
-
context-fundamentals
This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
majiayu000/claude-skill-registry 163
-
Technical Writer (Docs & Assets)
Generates world-class documentation with automated screenshots and GIFs using Playwright.
majiayu000/claude-skill-registry 163
-
spec-driven-lifecycle
Coordinates spec-driven development lifecycle from Epic -> Sprint -> Story -> Architecture -> Development -> QA -> Release with structural anti-skip enforcement. Manages story lifecycle across 11 workflow states, enforces 4 quality gates, and orchestrates skill invocation. Replaces spec-driven-lifecycle as the unified lifecycle coordinator. Use when starting sprints, managing story workflow progression, auditing deferrals, running sprint retrospectives, or coordinating multi-story releases. Always use this skill when /orchestrate, /create-sprint, or /audit-deferrals is invoked.
majiayu000/claude-skill-registry 163