Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
edit-page-content
Edit and refine Dutch copy for existing pages, limited to content updates only. Use when updating text in content/behandelingen/*.md or app/features/**/*.vue without changing layout, structure, or creating new components/files.
majiayu000/claude-skill-registry 163
-
vercel-upgrade-migration
Execute analyze, plan, and execute Vercel SDK upgrades with breaking change detection.
Use when upgrading Vercel SDK versions, detecting deprecations,
or migrating to new API versions.
Trigger with phrases like "upgrade vercel", "vercel migration",
"vercel breaking changes", "update vercel SDK", "analyze vercel version".
majiayu000/claude-skill-registry 163
-
vexor-cli
Semantic file discovery via `vexor`. Use whenever locating where something is implemented/loaded/defined in a medium or large repo, or when the file location is unclear. Prefer this over manual browsing.
majiayu000/claude-skill-registry 163
-
oe-hil-and-billing-triage
Debug common manager/HIL + billing/deposit regressions: tasks not appearing in the panel, approve/reject button failures, billing capture loops, and “deposit paid but workflow stuck”. Produces a targeted repro + test run and points to the likely faulty layer (frontend vs backend).
majiayu000/claude-skill-registry 163
-
file-exclusion-patterns
ファイル監視システムにおける効率的な除外パターン設計の専門知識。.gitignore互換のglob pattern、プラットフォーム固有の一時ファイル除外、パフォーマンス最適化のための早期除外戦略を提供。
Anchors:
• The Pragmatic Programmer / 適用: ファイル監視・パターン設計 / 目的: 実用的な除外戦略とglob構文の習得
• Software Engineering at Google / 適用: パフォーマンス最適化・クロスプラットフォーム対応 / 目的: 早期除外戦略とOS間の統一設定
• Refactoring / 適用: パターンの保守性 / 目的: 重複を排除し明確な意図を持つ設計
Trigger:
Use when designing file exclusion patterns, optimizing .gitignore files, improving file watching performance, or implementing cross-platform exclusion rules.
Keywords: gitignore, glob pattern, file watching, chokidar, build optimization, node_modules, platform-specific, .DS_Store, Thumbs.db, performance tuning
majiayu000/claude-skill-registry 163
-
validate-story
Pre-implementation story validation with 10-step comprehensive assessment including template compliance, anti-hallucination verification, and implementation readiness scoring. This skill should be used before handing story to development agent.
majiayu000/claude-skill-registry 163
-
home-assistant-api
Orchestrates access to the Home Assistant REST API for programmatic control of smart home devices. Routes requests to specialized resource files based on task type - authentication, state management, service calls, entity types, or advanced queries. Provides intelligent decision tables for selecting appropriate endpoints and managing integrations.
majiayu000/claude-skill-registry 163
-
klingai-pricing-basics
Manage understand Kling AI pricing, credits, and cost optimization. Use when budgeting or optimizing
costs for video generation. Trigger with phrases like 'kling ai pricing', 'klingai credits',
'kling ai cost', 'klingai budget'.
majiayu000/claude-skill-registry 163
-
state-management-patterns
State persistence patterns for autonomous-dev including JSON persistence, atomic writes, file locking, crash recovery, and state versioning. Use when implementing stateful libraries or features requiring persistent state.
majiayu000/claude-skill-registry 163
-
codebuddy-deploy
部署与运维专家,负责把通过 Reviewer 与 QA 门禁的构建安全、可回滚、可观测地部署到服务器(PM2 三进程 + Nginx 反代 + 宝塔)。遵循零停机部署、健康检查、回滚≤3分钟、发布后冒烟的工程基线。处理部署编排、配置管理、流量管理、监控告警。适用于收到 Deploy 部门任务卡或需要发布上线时使用。
majiayu000/claude-skill-registry 163
-
irb-protocol
Develop IRB/ethics protocols for human subjects research. Use when: (1) Planning studies involving humans, (2) Preparing IRB applications, (3) Ensuring ethical compliance, (4) Addressing informed consent.
majiayu000/claude-skill-registry 163
-
concurrency
majiayu000/claude-skill-registry 163
-
provider-integration-templates
OpenRouter framework integration templates for Vercel AI SDK, LangChain, and OpenAI SDK. Use when integrating OpenRouter with frameworks, setting up AI providers, building chat applications, implementing streaming responses, or when user mentions Vercel AI SDK, LangChain, OpenAI SDK, framework integration, or provider setup.
majiayu000/claude-skill-registry 163
-
functional-programming
Use when writing functional code - covers FP best practices (Lea differs from traditional FP languages)
majiayu000/claude-skill-registry 163
-
code-search-selector
⚡ AUTO-INVOKE when user asks: 'audit', 'investigate', 'how does X work', 'find all', 'where is', 'trace', 'understand', 'map the codebase', 'comprehensive'. MUST run BEFORE Read/Glob when planning to read 3+ files. Prevents tool familiarity bias toward native tools.
majiayu000/claude-skill-registry 163
-
cobol-modernization
Guidance for converting COBOL programs to modern languages (Python, Java, etc.) while preserving exact behavior and data format compatibility. This skill should be used when modernizing legacy COBOL applications, converting COBOL business logic to modern languages, or ensuring byte-for-byte output compatibility between COBOL and its replacement.
majiayu000/claude-skill-registry 163
-
git-code-review
Get git records for specified users and days, perform code review for each commit, and generate detailed code review reports
majiayu000/claude-skill-registry 163
-
at-dispatch-v2
Convert PyTorch AT_DISPATCH macros to AT_DISPATCH_V2 format in ATen C++ code. Use when porting AT_DISPATCH_ALL_TYPES_AND*, AT_DISPATCH_FLOATING_TYPES*, or other dispatch macros to the new v2 API. For ATen kernel files, CUDA kernels, and native operator implementations.
majiayu000/claude-skill-registry 163
-
pydantic-ai-common-pitfalls
Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.
majiayu000/claude-skill-registry 163
-
simo-multiomics-integration-agent
AI-powered spatial integration of multi-omics datasets using probabilistic alignment for comprehensive tissue atlas construction and cellular state mapping.
majiayu000/claude-skill-registry 163
-
dropdown-menu
Creates dropdown menus with proper click-outside detection and z-index stacking for list contexts. Use when building action menus, context menus, or any dropdown that appears in cards/list items.
majiayu000/claude-skill-registry 163
-
deliverable-tracking-mariuswilsch-clarity-workflow-plu
majiayu000/claude-skill-registry 163
-
evaluation
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
majiayu000/claude-skill-registry 163
-
test-sync
Detect orphaned tests, obsolete assertions, and test-code misalignment. Use for test suite maintenance, cleanup, and traceability validation.
majiayu000/claude-skill-registry 163