Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
service-mesh-observability
Implement comprehensive observability for service meshes including distributed tracing, metrics, and visualization. Use when setting up mesh monitoring, debugging latency issues, or implementing SLOs for service communication.
majiayu000/claude-skill-registry 163
-
eir-summary
Produces legally focused summaries of Environmental Impact Reports (EIRs) and Environmental Impact Statements (EISs), extracting impacts, mitigation, alternatives, and compliance vulnerabilities. Triggers on requests for EIR/EIS summary, CEQA/NEPA review, mitigation analysis, alternatives analysis, cumulative impacts review, permit challenge prep, or administrative record review.
majiayu000/claude-skill-registry 163
-
OWASP 資安模式庫
基於 OWASP Top 10 2025 的可重用安全程式碼模式，供跨專案參考
majiayu000/claude-skill-registry 163
-
ecosystem-mapping
Reading a habitat — identifying biome, plant community, food web structure, successional stage, and the keystone species that hold the system together. Covers the elevational and latitudinal gradients that Humboldt first mapped, the structural vocabulary for describing a habitat, the core concepts of food-web and trophic analysis, and the practice of diagnosing habitat health from indicator species. Use when the task is to understand a place rather than a species.
majiayu000/claude-skill-registry 163
-
vvvv-spreads
Helps write code using vvvv gamma's Spread<T> immutable collection type and SpreadBuilder<T>. Use when working with Spreads, collections, arrays, iteration, mapping, filtering, zipping, or converting between Span and Spread.
majiayu000/claude-skill-registry 163
-
openspec-ff-change
Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.
majiayu000/claude-skill-registry 163
-
Agent Design Architecture
Design effective AI agent systems with clear architecture, capability planning, and tool integration. Use when building agent systems, designing agent workflows, planning tool ecosystems, defining agent roles and boundaries, or architecting multi-agent systems. Covers agent patterns, agentic loops, capability design, and system composition.
majiayu000/claude-skill-registry 163
-
cook
[Implementation] Implement a feature [step by step]
majiayu000/claude-skill-registry 163
-
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
majiayu000/claude-skill-registry 163
-
code-quality
Provides code quality principles including SOLID, DRY, testing strategies, and best practices for implementation review. Use when reviewing code or applying quality standards.
majiayu000/claude-skill-registry 163
-
docs-seeker
Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.
majiayu000/claude-skill-registry 163
-
design-polish
Use when a frontend has placeholder assets (data-asset attributes, empty image slots) and needs real generated visuals. Triggers: post-implementation polish, preparing for demo/launch, replacing placeholder images with AI-generated assets matching a design system.
majiayu000/claude-skill-registry 163
-
angular
Modern Angular (v20+) expert with deep knowledge of Signals, Standalone Components, Zoneless applications, SSR/Hydration, and reactive patterns. Use PROACTIVELY for Angular development, component architecture, state management, performance optimization, and migration to modern patterns.
majiayu000/claude-skill-registry 163
-
smart-sourcing
Select optimal information sources for tool calls and file reads, balancing accuracy with token efficiency.
majiayu000/claude-skill-registry 163
-
deepagents-cli
Deep Agents CLI reference and usage guide. Use when the user wants to:
(1) Launch or configure the deepagents terminal coding assistant,
(2) Set up interactive or non-interactive (automation/CI) agent sessions,
(3) Manage agent memory, skills, or AGENTS.md context files,
(4) Configure LLM providers, models, or sandbox execution environments,
(5) Build scripted workflows or subagent patterns with deepagents.
majiayu000/claude-skill-registry 163
-
convert-elm-roc
Bidirectional conversion between Elm and Roc. Use when migrating projects between these languages in either direction. Extends meta-convert-dev with Elm↔Roc specific patterns. Use when migrating Elm frontend code to Roc applications, translating browser-based Elm to platform-agnostic Roc, or refactoring Elm web applications to Roc CLI/native tools. Extends meta-convert-dev with Elm-to-Roc specific patterns.
majiayu000/claude-skill-registry 163
-
mcp-efficiency
Token-efficient codebase exploration using MCP servers (Serena, Context7, JetBrains, Claude-mem). Reduces token usage by 80-90% through structured queries. Use ALWAYS before reading files to minimize context window usage.
majiayu000/claude-skill-registry 163
-
ask-ai
Use external AI assistants (ChatGPT, Claude, Gemini, DeepSeek) when agent encounters difficult problems. Trigger when: (1) User explicitly asks to consult AI, (2) Agent cannot solve the problem independently, (3) Knowledge gaps or needing deeper explanations, (4) Complex problems requiring multi-round reasoning. Provides two modes: Ask Mode (ask user first) and Trust Mode (auto ask).
majiayu000/claude-skill-registry 163
-
eywa
Multi-agent coordination, spatial memory, and swarm navigation. Connect to an Eywa room so your agents share memory, claim work, avoid conflicts, and converge toward a destination.
majiayu000/claude-skill-registry 163
-
Generating New Skills
Meta-skill that creates other skills from detected patterns. Use when user repeatedly explains workflow (2+ times), says 'remember this', or you notice repetitive pattern.
majiayu000/claude-skill-registry 163
-
onboarding-cro
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence.
majiayu000/claude-skill-registry 163
-
unsafe-checker
CRITICAL: Use for unsafe Rust code review and FFI. Triggers on: unsafe, raw pointer, FFI, extern, transmute, *mut, *const, union, #[repr(C)], libc, std::ffi, MaybeUninit, NonNull, SAFETY comment, soundness, undefined behavior, UB, safe wrapper, memory layout, bindgen, cbindgen, CString, CStr, 安全抽象, 裸指针, 外部函数接口, 内存布局, 不安全代码, FFI 绑定, 未定义行为
majiayu000/claude-skill-registry 163
-
restart-test-containers
Restarts WitchCityRope Docker TEST containers using the CORRECT procedure. Handles shutdown, rebuild with test compose overlay (--no-cache by default), health checks, and verification. Ensures environment is ready for testing. SINGLE SOURCE OF TRUTH for test container restart process. Uses -p witchcityrope-test for isolation from dev containers.
majiayu000/claude-skill-registry 163
-
vercel-shipper
Vercel release specialist. Use for Next.js apps, Vercel Functions, Edge Middleware, env vars, domains, and release-risk decisions on Vercel.
majiayu000/claude-skill-registry 163