Ship skill changes to PRs when Codex skills need source edits, rooted sync, strict audit, reviewer evidence, commit, push, and PR status.
在 Skill（SKILL.md）与 Prompt（聊天框指令）两种格式之间相互转换。支持 Skill→Prompt 与 Prompt→Skill 双向转换，保持核心信息零丢失。当用户提到 Skill 转 Prompt、Prompt 转 Skill、格式互转、SKILL.md 转换时使用。
Analyseskill auf Meta-Ebene, der LeanDeep-Marker (ATO→SEM→CLU→MEMA) mit Emotion Dynamics vereint und eine psychoanalytische Linse (Konflikte, Abwehr, Übertragung) appliziert;…
Create and push reusable skills to SkillNote when repeated instructions are detected or user says "create a skill", "save this pattern", "push a skill".
Skills kanzleiweit unter QA-Kontrolle halten: zentrale Skill-Bibliothek, Versionsverwaltung, Aenderungsfreigaben, Validatoren, Tests.
Automatically recognizes and recommends suitable skills for user requests. Discovers helpful installed skills even without explicit skill requests.
Redirect-Skill fuer weitergehts.online Escape-Game-Infrastruktur. Laedt die kanonische Projektanleitung aus dem Repo.
· Improve skill collections or a named skill with iterative scoring, lint checks, behavioral tests, peer review.
Use when the user provides a Skill, SKILL.md, prompt workflow, agent instructions, marketplace page, or skill directory and asks to analyze, reverse-engineer, compare, improve,…
Run dial-gated Seven Sweeps + auxiliary gates against a brief or copy draft. Returns synthesized findings to the operator.
Reviews and improves Claude Code skills against official best practices. Supports three modes - self-review (validate your own skills), external review (evaluate others' skills),…
Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their…
Audyt i synchronizacja skill-rules.json z istniejącymi skillami. Wykrywa brakujące wpisy, martwe referencje, problemy z keywords. Uruchamiaj po dodaniu/usunięciu skilli.
Suggest the narrowest permission scope by mapping a file path to its enclosing skill directory before prompting the user.
Search existing local, marketplace, GitHub, and web skill sources before creating a new skill. Use when the user wants to create, build, fork, or find a skill for a workflow.
-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.
Seleciona quais skills devem ser utilizadas para resolver a tarefa, orquestrando comportamento do agente de forma estratégica e eficiente.
Meta-skill for picking project skills via APM. Invoke ONLY when the user explicitly asks to set up apm.yml, choose which skills a project needs, or evaluate a catalog match — do…
Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e relatorios de saude.
SKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functionality lost.
Use when 需要创建新的 AI Agent 技能、改进已有 SKILL.md 文件、设计技能工作流或不确定技能该如何组织时。触发场景：创建技能、新建技能、写技能、技能开发、skill-smith、设计技能、编写SKILL.md、制作技能、开发skill、如何写一个好技能、技能质量不好怎么改进。
Audit SKILL.md and skill directories for Agent Skills spec, Cursor extensions, and npx skills compatibility.
Standardize and validate SKILL.md files against the Agent Skills specification (agentskills.io). Use when creating new skills, auditing existing skills for spec compliance,…
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
Safe surgical updates to existing AI skill files. Use when updating, modifying, or editing an existing skill file — ensures only intended changes are made and unintended rewrites…
Synchronization across model directories. Trigger: After creating or modifying skills, agents, or prompts to sync across directories.
Technical writing and documentation skill — specs, runbooks, changelogs, meeting notes, ADRs
Skill-Templating fuer kanzleieigene Vorlagen: vom Schriftsatz-Bauplan zum eigenen Skill mit Platzhaltern, Pruefraster, Quellenregel.
Test a skill's quality before publishing — validate SKILL.md frontmatter schema, check instruction structure for phases and guardrails, score against the marketplace rubric out of…
Use when verifying that a skill actually changes Claude's behaviour — runs TDD pressure scenarios against a skill before and after writing it.
Automated QA system for Claude Code skills. Discovers skills from GitHub/SkillsMP, installs them, generates tests, executes with screenshot capture, evaluates quality with A-F…
Enable, disable, and manage Claude Code skills. Use when the user asks to enable/disable/toggle/manage skills, check skill status, list skills, manage skill collections, or clean…
Universal skill diagnosis and optimization tool. Detect and fix skill execution issues including context explosion, long-tail forgetting, data flow disruption, and agent…
Agent-ready toolkit for Twenty CRM. 396 bash scripts covering every REST endpoint — CRUD, batch operations, filters, merges, and duplicate detection across 30+ objects (Companies,…
Sử dụng khi tạo mới hoặc sửa đổi React Components trong thư mục frontend/src/components/ hoặc frontend/src/pages/.
Audit installed Claude skills: flag unused, spot duplicates, generate deactivation checklist. Reduces context noise from skill overload.
Referenz-Skill für die Deinstallation, Deaktivierung und Reaktivierung von Community-Skills, die über den Kanzlei-Builder-Hub installiert wurden.
Use when deciding 'should this be a skill or a rule?', creating/improving/reviewing agent skills, SKILL.md frontmatter, or procedure sections — even without saying 'skill-writing'.
Autonomously improve an MCP skill via the skillit audit→draft→review loop (build or runtime mode) Also: skillit, refine, mcp, skill-generation, cli, audit, overlay.
Use when users ask to discover, install, list, check, update, remove, back up, restore, sync, or initialize Agent Skills, mention `bunx skills`, `npx skills`, `skills.sh`, or…
Omit skill-listing attachments for agents that do not expose the Skill tool, so discoverability context is only sent where it can be acted on.
Derive a slash-command skill surface from a broader prompt-command registry by requiring descriptive metadata, excluding builtins, and admitting only a controlled set of origins…
Run Socratic Duel through two participant subagents while the launcher only coordinates and reports.
Master-Routing-Skill der sozialrechtlichen Kanzlei. Nimmt einen frischen Fall an und entscheidet in drei Schritten welche weiteren Skills wann gezogen werden.
Pattern for spawning parallel subagents efficiently. Use when you need multiple independent tasks done concurrently.
User-gated promotion of a supervisor-written SKILL.patch.md sidecar into a real SKILL.md. Scans the current project and harness skills dir for pending sidecars, lets the user pick…
Scan a transferable SKILL.md (or a draft transferable proposal) for proprietary leakage using LLM judgment, not regex.
Meta-skill for creating new stitch-kit skills. Enforces naming conventions, SKILL.md structure, examples format, and the Design-First SOP.
Use subagents to throw more compute at hard problems, keep the main context window clean, and auto-approve safe permissions via hooks.
Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
Submit a pull request with skill fixes. Validates skill structure, bumps versions, and creates a PR with a proper description.
Bounded subagent delegation and synthesis. Use for explicit subagent, delegation, fan-out, spawn policy, custom agent routing, wait behavior, and evidence-first synthesis.
Use when you have a chunk of QA work (a story, a PR, a strategy phase) that needs to be turned into a written plan of bite-sized, independently-executable tasks before any test…
Use when: Mau execute implementation plan dengan parallel subagents dalam current session
[PROTOCOL] Generic system-optimization (skill-evolution) methodology shared by the three domain director-optimizers (dev / design / marketing).
Zerlege jede gegebene Aufgabe zwingend in parallele Subagents und verteile die Arbeit. Verwende diesen Skill IMMER wenn der Nutzer "/subagent" schreibt, "mit Subagents", "parallel…
Record SkillTool usage with sanitized telemetry fields so built-in, bundled, and custom skills are distinguished while avoiding PII leakage.
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Skill-Modul für 5-Achsen-Heuristik-Check (read-only, kein Text-Edit). Eingabe: Text + Ziel-Niveau; Ausgabe: Score je Achse + Pass/Fail-Ampel.
Run an observed live dev session — Claude drives an interactive REPL in a named tmux session, the human spectates read-only via `tmux attach -r`.