Loading...
Loading...
Found 10,136 Skills
End-to-end application deployment orchestration for the Kubernetes homelab. Use when: (1) Deploying a new application to the cluster, (2) Adding a new Helm release to the platform, (3) Setting up monitoring, alerting, and health checks for a new service, (4) Research before deploying, (5) Testing deployment on dev cluster before GitOps promotion. Triggers: "deploy app", "add new application", "deploy to kubernetes", "install helm chart", "/deploy-app", "set up new service", "add monitoring for", "deploy with monitoring"
Documents the blooming-blockery (block) CLI contract and provides correct command patterns for block store operations.
Create versioned OpenSCAD (.scad) files for 3D printing, render previews, and compare iterations. Use this when designing or iterating on 3D models.
从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
Update documentation after code changes. Use when adding features, changing keybindings, modifying config options, or updating TUI behavior. Automatically finds and updates relevant documentation files (README, recipes, help text).
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
Optimizes Claude Code memory files in 4 interactive steps: removes duplicates, migrates rules to CLAUDE.md/rules files, compresses remaining entries, validates with cleanup. Typical reduction: 30-50% on token count.
Generate Git branch names from staged or branch changes
Use when starting a new project, adding a major feature to an existing system, or when unsure which skills to run and in what order. Supports macOS, iOS, web, full-stack, voice agent, and edge/IoT+ML projects.
Surfaces relevant instincts during work. Use when starting a task to check if any learned behaviors apply.
Git 설정부터 PR까지의 전체 진행 상황을 체크리스트로 보여주고 현재 단계를 안내합니다. "어디까지 했지?", "진행 상황", "다음 단계" 같은 질문에 사용됩니다.
Inline adversarial plan review — 3 sequential checks (Feasibility, Completeness, Scope & Alignment) performed by the calling LLM in its own context. No subagents spawned. Call after saving a plan. Returns GATE_PASS or GATE_FAIL with blocking issues.