Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
aitask-pick
Select the next AI task for implementation from the `aitasks/` directory.
majiayu000/claude-skill-registry 163
-
windows-discovery
Windows local privilege escalation enumeration and attack surface mapping.
majiayu000/claude-skill-registry 163
-
review-quality
Analyze code for cross-file quality issues: duplicated logic, architectural inconsistencies, and abstraction opportunities. Returns structured findings without applying fixes. Use when the user asks to "review quality", "check for duplication across files", "find architectural inconsistencies", "cross-file quality review", or "review code quality".
majiayu000/claude-skill-registry 163
-
deployment
Kubernetes Deployment 管理
majiayu000/claude-skill-registry 163
-
gh-fix-ci
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.
majiayu000/claude-skill-registry 163
-
discord-aresbit-matebot
majiayu000/claude-skill-registry 163
-
seo-expert
Эксперт SEO. Используй для поисковой оптимизации, keyword research, technical SEO и link building.
majiayu000/claude-skill-registry 163
-
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
majiayu000/claude-skill-registry 163
-
check-prod
Query the production Vercel database via the public API to investigate data issues
majiayu000/claude-skill-registry 163
-
openskills-plugin-separation
Enforce clean separation between core openskills-runtime and optional WASM build plugins so plugin compilation does not break runtime consumers or language bindings.
majiayu000/claude-skill-registry 163
-
sure
Get report from Sure personal financial board
majiayu000/claude-skill-registry 163
-
run-benchmark
Run an MCP evaluation using mcpbr on SWE-bench or other datasets.
majiayu000/claude-skill-registry 163
-
better-all
Use the better-all library for Promise.all with automatic DAG-based dependency optimization and full type inference. Use when parallelizing async operations with complex dependencies.
majiayu000/claude-skill-registry 163
-
sr
Conduct comprehensive code review before PR merge. Use when asked to 'review code', 'start code review', 'review PR', 'check before merge', or 'pre-merge review'. NOT for addressing review comments (use /prc), NOT for code exploration (use /code-analysis).
majiayu000/claude-skill-registry 163
-
plugin-creator
This skill should be used when the user asks to 'create a plugin', 'scaffold a plugin', 'set up plugin structure', 'new plugin', 'add plugin components', or needs to substantially edit an existing plugin.
majiayu000/claude-skill-registry 163
-
workflow-lite-plan
Explore-first wave pipeline. Decomposes requirement into exploration angles, runs wave exploration via spawn_agents_on_csv, synthesizes findings into execution tasks with cross-phase context linking (E*→T*), then wave-executes via spawn_agents_on_csv.
majiayu000/claude-skill-registry 163
-
nuxt-ui
Use when implementing or debugging UI features with Nuxt UI components, designing forms, tables, modals, or any user interface work - fetches current documentation to ensure accurate component APIs
majiayu000/claude-skill-registry 163
-
bmad-bmm-retrospective
bmad-bmm-retrospective skill
majiayu000/claude-skill-registry 163
-
documentation-writer
生成全面的文档，包括README文件、API文档、代码注释（JSDoc、docstrings、XML）和架构文档。
majiayu000/claude-skill-registry 163
-
shadcn-ui
Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.
majiayu000/claude-skill-registry 163
-
tdd-workflows-tdd-cycle
Use when working with tdd workflows tdd cycle
majiayu000/claude-skill-registry 163
-
incubator
majiayu000/claude-skill-registry 163
-
multi-agent-composition
This skill should be used when the user asks to "choose between skill and agent", "compose multi-agent system", "orchestrate agents", "manage agent context", "design component architecture", "should I use a skill or agent", "when to use hooks vs MCP", "build orchestrator workflow", needs decision frameworks for Claude Code components (skills, sub-agents, hooks, MCP servers, slash commands), context management patterns, or wants to build effective multi-component agentic systems with proper orchestration and anti-patterns guidance.
majiayu000/claude-skill-registry 163
-
write-blog
End-to-end blog creation pipeline from topic to publish-ready draft. Orchestrates research, planning, diagram generation, and writing in sequence with approval checkpoints. Use when user wants to create a complete blog post from scratch on a given topic.
majiayu000/claude-skill-registry 163