Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
searching-files
Finding files on Linux and macOS machines
majiayu000/claude-skill-registry 163
-
spec-interviewer
Realiza entrevistas profundas para extraer especificaciones completas de proyectos
majiayu000/claude-skill-registry 163
-
dreaming
Think expansively and imaginatively without practical constraints. Use when brainstorming ambitious ideas, exploring what's possible, challenging assumptions, envisioning ideal futures, or when the user needs to break out of incremental thinking and imagine boldly.
majiayu000/claude-skill-registry 163
-
commit.lint
Formats and lints code with ruff using a sub-agent. Use after tests pass to ensure code style compliance.
majiayu000/claude-skill-registry 163
-
simplification-principles
Apply simplification principles (Occam's Razor) when debugging complex issues, evaluating competing theories, or simplifying designs. Not for ignoring necessary complexity or oversimplifying.
majiayu000/claude-skill-registry 163
-
security-threat-model
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
majiayu000/claude-skill-registry 163
-
researching-codebase
This skill should be used when the user asks to "research the codebase", "understand how X works", "explore the code", "gather context", "investigate the implementation", "analyze the architecture", or invokes the rpikit:research command. Provides methodology for thorough interrogation and codebase exploration before planning or implementation.
majiayu000/claude-skill-registry 163
-
Visionary Team
Strategic AI council for product vision, innovation, and future planning
majiayu000/claude-skill-registry 163
-
book-marketing
Diagnose book marketing copy problems and generate platform-optimized blurbs, descriptions, taglines, and query pitches. Use when marketing copy feels weak, when descriptions aren't converting, or when starting marketing from scratch.
majiayu000/claude-skill-registry 163
-
Music Composition Reference
Use this skill when DESIGNING music content - choosing keys, chord progressions, tempos for specific contexts.
**Triggers:** "chord progression", "what key for", "tempo for", "music theory", "leitmotif", "adaptive music", "loop design", "listener fatigue", "hours of play", "background music", "supportive music", "music mix space".
**Pipeline position: DESIGN (1 of 3)**
- For tracker file creation: use `tracker-music` plugin
- For instrument synthesis: use `zx-procgen:procedural-instruments`
**Load references when:**
- Chord progressions by emotion → `references/chord-progressions.md`
- Adaptive music patterns → `references/adaptive-patterns.md`
- Genre-specific templates → `references/genre-templates.md`
majiayu000/claude-skill-registry 163
-
supabase-typing-architect
Supabase TypeScript typing specialist for multi-schema databases. Diagnoses and fixes type issues without touching business logic.
Use when:
- "Lovable ei näe Supabase-tyyppejä" (Lovable can't see Supabase types)
- "RPC:t ei ole tyypitetty" (RPCs are not typed)
- "Monorepo + Supabase types sekoilee" (monorepo type confusion)
- "as any on levinnyt RPC-kutsuihin" (as any spreading in RPC calls)
- "Types.ts löytyy mutta TS ei tunnista sitä" (types.ts exists but TS doesn't recognize it)
- TypeScript errors on supabase.rpc() calls
- Missing types for bible_schema, notifications, admin, or other non-public schemas
- Import path issues with @/integrations/supabase/types
NOT for: Writing business logic, creating components, general TypeScript help.
majiayu000/claude-skill-registry 163
-
dbt-migration-vertica
Convert Vertica DDL to dbt models compatible with Snowflake. This skill should be used when converting views, tables, or stored procedures from Vertica to dbt code, generating schema.yml files with tests and documentation, or migrating Vertica SQL to follow dbt best practices.
majiayu000/claude-skill-registry 163
-
carmenta-copy
Use when writing user-facing copy, error messages, UI text, empty states, onboarding, or reviewing voice/tone
majiayu000/claude-skill-registry 163
-
optimization.experiment_brief
Prepare an experiment brief outlining hypothesis, design, success metrics, and operational plan.
majiayu000/claude-skill-registry 163
-
repomix
Repository packaging for AI/LLM analysis. Capabilities: pack repos into single files, generate AI-friendly context, codebase snapshots, security audit prep, filter/exclude patterns, token counting, multiple output formats. Actions: pack, generate, export, analyze repositories for LLMs. Keywords: Repomix, repository packaging, LLM context, AI analysis, codebase snapshot, Claude context, ChatGPT context, Gemini context, code packaging, token count, file filtering, security audit, third-party library analysis, context window, single file output. Use when: packaging codebases for AI, generating LLM context, creating codebase snapshots, analyzing third-party libraries, preparing security audits, feeding repos to Claude/ChatGPT/Gemini.
majiayu000/claude-skill-registry 163
-
competitor-audit
Analyze competitor's ad strategy by researching their Facebook Ad Library presence, TikTok Top Ads, identifying longest-running ads (likely winners), and extracting angles, hooks, and frameworks. Use when entering a new market, researching what's working, or building competitive intelligence.
majiayu000/claude-skill-registry 163
-
lseg-data
This skill should be used when the user asks to "access LSEG data", "query Refinitiv", "get market data from Refinitiv", "download fundamentals from LSEG", "access ESG scores", "convert RIC to ISIN", or needs the LSEG Data Library Python API.
majiayu000/claude-skill-registry 163
-
generate-story-bank
Generate interview-ready stories using HPARL format (Hook, Principles, Action, Results, Learnings). Transforms achievements into compelling narratives for behavioral interviews.
majiayu000/claude-skill-registry 163
-
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
majiayu000/claude-skill-registry 163
-
ln-113-backend-docs-creator
Creates 2 backend docs (api_spec.md, database_schema.md). L3 Worker invoked CONDITIONALLY when hasBackend or hasDatabase detected.
majiayu000/claude-skill-registry 163
-
ln-711-npm-upgrader
Upgrades npm/yarn/pnpm dependencies with breaking change handling
majiayu000/claude-skill-registry 163
-
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI
majiayu000/claude-skill-registry 163
-
cloudflare-worker-deployment
Use this skill whenever the user wants to deploy, configure, or refine deployment of a Hono/TypeScript backend (or similar Worker) to Cloudflare Workers/Pages using Wrangler, including wrangler.toml, environments, bindings, and basic release workflows.
majiayu000/claude-skill-registry 163
-
senior-backend
Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.
majiayu000/claude-skill-registry 163