Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ReasoningBank Adaptive Learning with AgentDB
majiayu000/claude-skill-registry 163
-
plugin-validator
生成したプラグイン全体の整合性・完全性を検証する。プラグイン検証時、品質チェック時、またはユーザーがプラグイン検証、整合性確認、完全性チェック、品質保証、バリデーションに言及した際に使用する。
majiayu000/claude-skill-registry 163
-
openai-agents
Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors.
Use when: building agents with tools, voice agents with WebRTC, multi-agent workflows, or troubleshooting MaxTurnsExceededError, tool call failures, reasoning defaults, JSON output leaks.
majiayu000/claude-skill-registry 163
-
devops
Deploy and manage cloud infrastructure on Cloudflare (Workers, R2, D1, KV, Pages, Durable Objects, Browser Rendering), Docker containers, and Google Cloud Platform (Compute Engine, GKE, Cloud Run, App Engine, Cloud Storage). Use when deploying serverless functions to the edge, configuring edge computing solutions, managing Docker containers and images, setting up CI/CD pipelines, optimizing cloud infrastructure costs, implementing global caching strategies, working with cloud databases, or building cloud-native applications.
majiayu000/claude-skill-registry 163
-
51-helm-charts
Create your Helm chart skill in one prompt, then learn to improve it throughout the chapter
majiayu000/claude-skill-registry 163
-
html-standards
HTML standards for Oh My Brand! theme. Semantic elements, accessibility requirements, ARIA attributes, and attribute best practices. Use when writing HTML templates or render output.
majiayu000/claude-skill-registry 163
-
context-monitor
Monitors context token usage and warns when approaching limits.
Automatically activates when context usage exceeds thresholds (30k, 50k, 70k tokens).
Provides recommendations for context management and /clear usage.
Auto-activates based on token usage, no specific keywords needed.
majiayu000/claude-skill-registry 163
-
nielsen-user-control
Proporciona a usuarios control total sobre sus acciones con opciones de deshacer y salir. Use cuando diseñe flujos de navegación, acciones destructivas, o cualquier operación que el usuario pueda querer revertir.
majiayu000/claude-skill-registry 163
-
lindy-common-errors
Troubleshoot common Lindy AI errors and issues.
Use when encountering errors, debugging agent failures,
or resolving integration problems.
Trigger with phrases like "lindy error", "lindy not working",
"debug lindy", "lindy troubleshoot".
majiayu000/claude-skill-registry 163
-
cloudflare-sandbox-secondsky-claude-skills
majiayu000/claude-skill-registry 163
-
llm-icon-finder
Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.
majiayu000/claude-skill-registry 163
-
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
majiayu000/claude-skill-registry 163
-
skill-researcher
Conduct general research using web search, documentation, and codebase exploration. Invoke for non-Lean research tasks.
majiayu000/claude-skill-registry 163
-
status-report-template
Эксперт по статус-отчётам. Используй для создания шаблонов отчётов, executive summaries и project dashboards.
majiayu000/claude-skill-registry 163
-
exa-search
Use when searching for concepts, ideas, or similar content without exact keywords; when user asks "find similar to...", needs semantic discovery, research across perspectives, or explicitly mentions exa
majiayu000/claude-skill-registry 163
-
AI Inference & Model Serving
AI model inference and serving. Activate when: (1) Setting up LocalAI or vLLM, (2) Configuring model serving, (3) Working with GGUF/GGML models, (4) Implementing inference pipelines, or (5) Optimizing model performance.
majiayu000/claude-skill-registry 163
-
supabase-python
FastAPI with Supabase and SQLAlchemy/SQLModel
majiayu000/claude-skill-registry 163
-
codex-exec
Execute development tasks using OpenAI Codex CLI for code generation, refactoring, feature implementation, and bug fixes. Use when the user asks to create code, add features, refactor, fix bugs, or generate tests. Requires Codex CLI installed.
majiayu000/claude-skill-registry 163
-
arch-patterns
majiayu000/claude-skill-registry 163
-
clavix-prd
Create comprehensive Product Requirements Documents through strategic questioning. Use when planning a new feature or project that needs clear requirements.
majiayu000/claude-skill-registry 163
-
fixed-appetite-product-cycles
Replace open-ended time estimates with fixed "appetites" to prevent scope creep. Use this when projects consistently miss deadlines, teams feel burnt out by endless sprints, or product development feels bloated and slow.
majiayu000/claude-skill-registry 163
-
sy3-stocks-and-flows
Apply SY3 Stocks & Flows to distinguish accumulations from rates of change affecting them.
majiayu000/claude-skill-registry 163
-
add-database-table
majiayu000/claude-skill-registry 163
-
supabase-integration
Unified database operations for BidDeed.AI and Life OS ecosystems. Use when: (1) logging insights, activities, or learning sessions, (2) querying historical data from any table, (3) user says "log this" or "save to database", (4) storing auction results, task states, swim times, or health metrics. Database: mocerqjnksmhcjzxrewo.supabase.co
majiayu000/claude-skill-registry 163