Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
writing-product-specs
Use when asked to design a new feature or project
majiayu000/claude-skill-registry 163
-
api-boilerplate
生成 REST API 样板代码，支持 Express、FastAPI、Next.js 等框架
majiayu000/claude-skill-registry 163
-
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
majiayu000/claude-skill-registry 163
-
tofu
OpenTofu infrastructure-as-code reference for HCL syntax, state management,
module design, and provider configuration. Use when working with OpenTofu
configurations (.tf files), running tofu commands, troubleshooting state
issues, or designing modules. Includes Proxmox provider patterns.
Triggers: tofu, opentofu, tfstate, .tf files, HCL, modules, providers.
majiayu000/claude-skill-registry 163
-
job-fit-analysis
Analyze fit between job requirements and background using lexicons - identifies gaps, develops reframing strategies, creates cover letter plan
majiayu000/claude-skill-registry 163
-
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
majiayu000/claude-skill-registry 163
-
helper-reference
Tum helper fonksiyonlari referansi. Use for quick lookup of available functions.
majiayu000/claude-skill-registry 163
-
debate-persona-generator
Generates three distinct expert challenger personas for multi-perspective debate. Each persona critiques from a different angle.
majiayu000/claude-skill-registry 163
-
skill-sync
Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running ./skills/skill-sync/assets/sync.sh (including --dry-run/--scope).
majiayu000/claude-skill-registry 163
-
mlops-patterns
Follow these patterns when implementing MLOps features in OptAIC. Use for ML model definitions (5-component structure), model instances, training/inference pipelines, model registry, and monitoring. Covers signal models, macro regime models, relevance models, and signal combining/filtering models.
majiayu000/claude-skill-registry 163
-
deepwork_jobs.implement
Generates step instruction files and syncs slash commands from the job.yml specification. Use after job spec review passes.
majiayu000/claude-skill-registry 163
-
social-graphics
Generate platform-optimized social media graphics and posts. Use when creating content for Instagram, Twitter, LinkedIn, TikTok, or other social platforms.
majiayu000/claude-skill-registry 163
-
nixtla-demo-generator
Generate production-ready Jupyter notebooks showcasing Nixtla forecasting workflows for statsforecast, mlforecast, and TimeGPT. Use when creating demos, building examples, or showcasing forecasting capabilities. Trigger with 'generate demo notebook', 'create Jupyter demo', or 'build forecasting example'.
majiayu000/claude-skill-registry 163
-
discord-kavia-common-moltbot-311196
majiayu000/claude-skill-registry 163
-
healthcare-expert
Expert-level healthcare systems, medical informatics, HIPAA compliance, and health data standards
majiayu000/claude-skill-registry 163
-
curriculum-grade-assist
Assist with grading by applying rubrics to student work, generating criterion-level feedback, and maintaining consistency across submissions. Use when grading assignments, applying rubrics, or providing feedback. Activates on "grade this", "apply rubric", "provide feedback", or "score student work".
majiayu000/claude-skill-registry 163
-
neon-async-db
This skill should be used when setting up and managing reliable, high-performance asynchronous database connections for Neon Serverless PostgreSQL using SQLModel and SQLAlchemy's async capabilities.
majiayu000/claude-skill-registry 163
-
dag-isolation-manager
Manages agent isolation levels and resource boundaries. Configures strict, moderate, and permissive isolation profiles. Activate on 'isolation level', 'agent isolation', 'resource boundaries', 'sandboxing', 'agent containment'. NOT for permission validation (use dag-permission-validator) or runtime enforcement (use dag-scope-enforcer).
majiayu000/claude-skill-registry 163
-
juicebox-sdk-patterns
Apply production-ready Juicebox SDK patterns.
Use when implementing robust error handling, retry logic,
or enterprise-grade Juicebox integrations.
Trigger with phrases like "juicebox best practices", "juicebox patterns",
"production juicebox", "juicebox SDK architecture".
majiayu000/claude-skill-registry 163
-
engine-superpower-profiling
Profile AI engine superpowers and capability boundaries.
majiayu000/claude-skill-registry 163
-
nextjs-boilerplate
Bootstrap a new Next.js development environment with Tailwind CSS, shadcn/ui components, and assistant-ui for AI chat interfaces. Use when the user asks to "create a new Next.js project", "bootstrap Next.js with shadcn", "set up a Next.js app", "create an AI chat app", "start a new React project with Tailwind", or mentions creating a fresh frontend project with modern tooling.
majiayu000/claude-skill-registry 163
-
end-to-end-orchestrator
Complete development workflow orchestrator coordinating all multi-ai skills (research → planning → implementation → testing → verification) with quality gates, failure recovery, and state management. Single-command complete workflows from objective to production-ready code. Use when implementing complete features requiring full pipeline, coordinating multiple skills automatically, or executing production-grade development cycles end-to-end.
majiayu000/claude-skill-registry 163
-
intent-analyzer
Advanced intent interpretation system that analyzes user requests using cognitive science principles and extrapolates logical volition. Use when user requests are ambiguous, when deeper understanding would improve response quality, or when helping users clarify what they truly need. Applies probabilistic intent mapping, first principles decomposition, and Socratic clarification to transform vague requests into well-understood goals.
majiayu000/claude-skill-registry 163
-
fastapi-integration-testing
Provides a comprehensive guide and templates for creating integration tests for FastAPI applications. Use this skill when you need to set up or write integration tests involving a database, authentication, file uploads, or error handling. It includes patterns for pytest fixtures, test client usage, and test data factories.
majiayu000/claude-skill-registry 163