Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
helm-production-patterns
Implement production deployment strategies including secrets management, blue-green deployments, canary releases, and upgrade procedures. Use when deploying charts to production, implementing secrets management, setting up blue-green or canary deployments, configuring chart testing strategies, or planning upgrade and rollback procedures.
majiayu000/claude-skill-registry 163
-
market-sizing-analysis
This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.
majiayu000/claude-skill-registry 163
-
form-components-vassovass-scl-v3
majiayu000/claude-skill-registry 163
-
mcaf-skill-curation
Create, update, and validate repository skills under your agent’s skills directory (Codex: `.codex/skills/`, Claude: `.claude/skills/`) so they match the real codebase and `AGENTS.md` rules; tune YAML `description` triggers, apply feedback, and generate `<available_skills>` metadata blocks.
majiayu000/claude-skill-registry 163
-
nextjs-api-routes
Apply when building API endpoints in Next.js App Router using Route Handlers.
majiayu000/claude-skill-registry 163
-
Critical Peer Personality
Professional, skeptical communication style focused on critical thinking and coaching. Never over-enthusiastic, always verifies before agreeing, challenges ideas constructively. Use when you want a persona to act as an expert peer who coaches rather than serves.
majiayu000/claude-skill-registry 163
-
prompt-optimizer
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models can better understand and execute. This skill applies comprehensive prompt engineering best practices to enhance prompt quality, clarity, and effectiveness.
majiayu000/claude-skill-registry 163
-
publish-release
Publish a new release to GitHub Packages. Use when ready to release, after tests pass and version is updated. Creates git tag and pushes to trigger GitHub Actions.
majiayu000/claude-skill-registry 163
-
rds
AWS RDS relational database service for managed databases. Use when provisioning databases, configuring backups, managing replicas, troubleshooting connectivity, or optimizing performance.
majiayu000/claude-skill-registry 163
-
claudish-usage
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
majiayu000/claude-skill-registry 163
-
agent-ops-focus-scan
Analyze issues to identify the next work item and update focus.md. Enforces issue-first workflow and confidence-based batch limits.
majiayu000/claude-skill-registry 163
-
nuxt-production
Nuxt 4 production optimization: hydration, performance, testing with Vitest,
deployment to Cloudflare/Vercel/Netlify, and v4 migration.
Use when: debugging hydration mismatches, optimizing performance and Core Web Vitals,
writing tests with Vitest, deploying to Cloudflare Pages/Workers/Vercel/Netlify,
or migrating from Nuxt 3 to Nuxt 4.
Keywords: hydration, hydration mismatch, ClientOnly, SSR, performance,
lazy loading, lazy hydration, Vitest, testing, deployment, Cloudflare Pages,
Cloudflare Workers, Vercel, Netlify, NuxtHub, migration, Nuxt 3 to Nuxt 4
majiayu000/claude-skill-registry 163
-
agent-workflow
Expert system for designing and architecting AI agent workflows based on proven Meta methodologies. Use when users need to build AI agents, create agent workflows, solve problems using agentic systems, integrate multiple tools into agent architectures, or need guidance on agent design patterns. Helps translate business problems into structured agent solutions with clear scope, tool integration, and multi-layer architecture planning.
majiayu000/claude-skill-registry 163
-
makefile-dogfooder
majiayu000/claude-skill-registry 163
-
add-agent-property
Add a new property to the AI agents database. Use when the user wants to add, create, or introduce a new column, property, field, or feature to track across all agents in the comparison matrix. Handles all four required steps - database updates, groups.json, table display, and GitHub issue templates.
majiayu000/claude-skill-registry 163
-
managing-media
Implements media and file management components including file upload (drag-drop, multi-file, resumable), image galleries (lightbox, carousel, masonry), video players (custom controls, captions, adaptive streaming), audio players (waveform, playlists), document viewers (PDF, Office), and optimization strategies (compression, responsive images, lazy loading, CDN). Use when handling files, displaying media, or building rich content experiences.
majiayu000/claude-skill-registry 163
-
bitbucket
Manage repositories, check pipelines, review PRs, and collaborate on Bitbucket
majiayu000/claude-skill-registry 163
-
research
Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.
majiayu000/claude-skill-registry 163
-
cc-integration-practices
Audit integration strategy and daily build processes (CHECKER) or select optimal integration approach and configure CI/CD (APPLIER). Use when integrating components, planning integration order, setting up build processes, or diagnosing integration failures. Triggers on: integration hell, late-stage defects, unclear integration order, no daily build, broken builds, Big Bang integration, smoke test stale. Produce integration strategy recommendations, build process configuration, 13-item checklist assessment with severity ratings.
majiayu000/claude-skill-registry 163
-
pumpfun
Complete PumpFun Protocol guide for building token launches, bonding curves, and AMM integrations on Solana. Covers Pump Program (token creation, buy/sell on bonding curves), PumpSwap AMM (liquidity pools, swaps), fee structures, creator fees, and SDK integration.
majiayu000/claude-skill-registry 163
-
atlas14-spatial-variance
Analyze spatial variability of NOAA Atlas 14 precipitation frequency estimates
within HEC-RAS model domains using intelligent extent-based downloading.
Helps determine whether uniform rainfall assumptions are appropriate for
rain-on-grid modeling by calculating min/max/mean/range statistics within
2D flow areas or project extents.
Uses NOAA CONUS NetCDF with HTTP byte-range requests for 99.9% data reduction
compared to traditional state-level ZIP downloads.
Primary sources:
- ras_commander/precip/CLAUDE.md (lines 118-629) - Complete workflows
- ras_commander/precip/Atlas14Grid.py - API reference
- ras_commander/precip/Atlas14Variance.py - Variance analysis API
- examples/725_atlas14_spatial_variance.ipynb - Working demonstration
majiayu000/claude-skill-registry 163
-
Gemini CLI Helper
Run Gemini CLI commands from Claude with correct Node version. Use when user asks to run Gemini CLI, test Gemini traces, or debug Gemini telemetry.
majiayu000/claude-skill-registry 163
-
kubernetes-specialist
majiayu000/claude-skill-registry 163
-
V3 CLI Modernization
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
majiayu000/claude-skill-registry 163