Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
accessibility-engineer
セマンティックHTML/JSXとWAI-ARIAを「最小で正しく」適用し、キーボード操作・スクリーンリーダ・コントラスト等を満たす実装を作るための判断軸。ネイティブ要素優先、ARIAの過剰使用を避ける。
majiayu000/claude-skill-registry 163
-
octave-literacy
Fundamental reading and writing capability for the OCTAVE format. Basic structural competence without full architectural specifications
majiayu000/claude-skill-registry 163
-
dotnet-testing-advanced-tunit-fundamentals
TUnit 新世代測試框架入門完整指南。
涵蓋 Source Generator 驅動測試發現、AOT 編譯支援、流暢式非同步斷言。
包含專案建立、[Test] 屬性、生命週期管理、並行控制與 xUnit 語法對照。
majiayu000/claude-skill-registry 163
-
pytorch-model-cli
Guidance for implementing CLI tools that perform inference using PyTorch models in native languages (C/C++/Rust). This skill should be used when tasks involve extracting weights from PyTorch .pth files, implementing neural network forward passes in C/C++, or creating standalone inference tools without Python dependencies.
majiayu000/claude-skill-registry 163
-
json-validation
Centralized JSON validation for AGENT_SUCCESS_CRITERIA with defensive parsing and injection attack prevention (CVSS 8.2)
majiayu000/claude-skill-registry 163
-
falcon-deep-research
Execute deep research protocols using the Falcon specialized research framework.
majiayu000/claude-skill-registry 163
-
using-superpowers
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
majiayu000/claude-skill-registry 163
-
crane-deployment
This skill should be used when the user asks about "create3", "deploy", "diamond factory", "package", "deterministic deployment", "cross-chain", "DiamondPackageCallBackFactory", "FactoryService", or needs guidance on deploying Diamond proxies and facets using Crane's factory system.
majiayu000/claude-skill-registry 163
-
claude-memory
Create and optimize CLAUDE.md memory files or .claude/rules/ modular rules for Claude Code projects. Comprehensive guidance on file hierarchy, content structure, path-scoped rules, best practices, and anti-patterns. Use when working with CLAUDE.md files, .claude/rules directories, setting up new projects, or improving Claude Code's context awareness.
majiayu000/claude-skill-registry 163
-
requirements-gathering
Guides comprehensive requirements gathering and analysis including stakeholder interviews, user story creation, use case documentation, acceptance criteria, requirements prioritization, and traceability. Produces requirements documents, user stories, use cases, and development roadmaps. Use when gathering requirements, writing user stories, creating acceptance criteria, analyzing stakeholder needs, prioritizing features, or when users mention requirements analysis, business analysis, user stories, use cases, or requirements documentation.
majiayu000/claude-skill-registry 163
-
spec-tests
Intent-based specification tests evaluated by LLM-as-judge. Use when the user asks to "create spec tests", "write intent tests", "TDD with intent", "natural language tests", or wants tests that capture WHY, not just WHAT. NOT pytest/jest/unittest - natural language specs Claude evaluates.
majiayu000/claude-skill-registry 163
-
validate-tenant-isolation
Verifies tenant isolation is enforced at all layers (gateway, service, database) following .cursorrules Security Requirements and ModuleImplementationGuide.md Section 11. Checks X-Tenant-ID header validation in routes, verifies tenantId in all database queries, validates tenant enforcement middleware, checks service-to-service tenant propagation, verifies audit logging includes tenantId, and ensures tenantId is in partition key for all Cosmos DB queries. Use when performing security audits, pre-deployment checks, or ensuring multi-tenancy compliance.
majiayu000/claude-skill-registry 163
-
python-expert
Expert-level Python development with Python 3.12+ features, async/await, type hints, and modern best practices
majiayu000/claude-skill-registry 163
-
env-patterns
Environment/config conventions (env vars, defaults, validation, CI/local differences). Use when adding config or diagnosing env-related failures.
majiayu000/claude-skill-registry 163
-
frontend-component
Create React/Vue component with TypeScript, tests, and styles. Auto-invoke when user says "create component", "add component", "new component", or "build component".
majiayu000/claude-skill-registry 163
-
Deployment Strategies
This skill should be used when the user asks about "deployment", "CI/CD", "continuous integration", "GitHub Actions", "GitLab CI", "environments", "staging", "production", "rollback", "versioning", "gradual rollout", "canary deployment", "blue-green deployment", or discusses deploying Workers, managing multiple environments, or setting up automated deployment pipelines.
majiayu000/claude-skill-registry 163
-
dexie-cache-sync
Dexie IndexedDB caching layer with Convex sync for local-first architecture. Covers sync hooks, optimistic updates (React state only), cascade deletes, orphan detection, SSR safety. Triggers on "cache", "dexie", "useCacheSync", "optimistic", "offline", "IndexedDB".
majiayu000/claude-skill-registry 163
-
swiftlint-autofix
Run SwiftFormat and fix all auto-correctable SwiftLint issues
majiayu000/claude-skill-registry 163
-
styling-patterns
DaisyUI v5 design system. Use for backgrounds, borders, text sizes, opacity, semantic colors, and spacing.
majiayu000/claude-skill-registry 163
-
scientific-slides
Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.
majiayu000/claude-skill-registry 163
-
skill-logger
Logs and scores skill usage quality, tracking output effectiveness, user satisfaction signals, and improvement opportunities. Expert in skill analytics, quality metrics, feedback loops, and continuous improvement. Activate on "skill logging", "skill quality", "skill analytics", "skill scoring", "skill performance", "skill metrics", "track skill usage", "skill improvement". NOT for creating skills (use agent-creator), skill documentation (use skill-coach), or runtime debugging (use debugger skills).
majiayu000/claude-skill-registry 163
-
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
majiayu000/claude-skill-registry 163
-
rewrite-history
Rewrite branch into clean, narrative-quality commits. Creates backup, reimplements on fresh branch, verifies byte-identical, then replaces original branch history.
majiayu000/claude-skill-registry 163
-
use-plan-create
Use when you have a spec or requirements for a multi-step task, before touching code
majiayu000/claude-skill-registry 163