审核/审查 Skill 代码质量的专业工具。当用户说"检查 skill"、"审核 skill"、"review {名称} skill"、"skill 写得怎么样"、"帮我看看这个 skill 有什么问题"时使用。依据 Anthropic 官方指南进行结构验证、YAML 前置信息检查、描述质量评估、指令完整性审查，...
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…
中文 skills 总控路由技能：用于在 C:\Users\zbh\.agents\skills 中按任务领域、阶段、风险和交付物选择最少必要 skill 组合，避免一次性加载全量技能。Use when:…
Audyt i synchronizacja skill-rules.json z istniejącymi skillami. Wykrywa brakujące wpisy, martwe referencje, problemy z keywords. Uruchamiaj po dodaniu/usunięciu skilli.
Safely slim a local Skill runtime without deleting source. Use for usage audits, duplicate consolidation, implicit-to-explicit policy changes, AGENTS cleanup, on-demand packs,…
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.
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other know — from…
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other know — from…
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other know — from…
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…
Self-improvement for MoltBot skills. Create, review, and improve own skills with quality control. Git-managed like Claude Code.
Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e relatorios de saude.
Partage et synchronisation de skills entre différents environnements d'IA (Antigravity, Cursor, Windsurf, GitHub Copilot, Claude Desktop, ChatGPT).
Package and finalize completed work for delivery — use when a feature is done and ready to ship
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。
Autonomous skill generation agent that picks up community ideas, uses evolved builder tools to produce Agent Skills, and publishes them back to the Skill Soup ecosystem.
Audit SKILL.md and skill directories for Agent Skills spec, Cursor extensions, and npx skills compatibility.
Splits an over-loaded SKILL.md into always-loaded (SKILL.md) + on-demand (SKILL_detail.md) layers using a governance-semantic criterion — not length, but when the content is…
Review code in two passes: spec compliance then quality — use for thorough PR or feature reviews
Standardize and validate SKILL.md files against the Agent Skills specification (agentskills.io). Use when creating new skills, auditing existing skills for spec compliance,…
훅으로 기록된 스킬별 사용 통계(호출 횟수·소요 시간)를 CLI 표로 보여준다. 사용자가 "스킬 통계", "skill stat", "스킬 사용량 보여줘", "어떤 스킬 많이 썼어?" 같이 요청할 때 사용한다.
查看本机 skill 使用频率统计：哪些 skill 高频、哪些近期常用、哪些长期没碰过（可考虑清理）。数据由本插件的采集 hook 持续记录，区分 AI 自动调用 与 用户手输 /命令 两种来源。触发：用户说『/skill-stats、skill 使用频率、哪些 skill 常用、哪些 skill 没用过、skill 使用统计、skill 排行、我的…
Weekly external skill delta scan → SOIL triage queue → Grove #upstream. Phase 3 of skill surface strategy. Never auto-installs.
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
Use when auditing one specific worldloom skill directory (target = SKILL.md + references/*.md + templates/*) for content that is redundant, contradictory, stale, or detrimental to…
调用链编排技能 — 既是调用链编辑器，也是粗粒度规划器。理解用户意图 → 规划 Skill 参与顺序 → 更新/保存/推荐调用链 → 拼接为调用链（支持循环/分支编排、子步骤拓扑排序、准确步骤计数）。
Scan prompt history for recurring patterns and unmet needs, then propose new skills or command templates
Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and…
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.
Combines multiple skills into synergistic pipelines. Use for: combine skills, skill pipeline, chain skills, skill synergy.
Combine, chain, specialize, or adapt existing Nexus skills into new ones. Use when the user wants to "combine skills", "merge skills", "chain skills into a workflow", "specialize…
Agente-ciclo: interlocutore fisso dell'utente. A monte (dice «prepara»/«prepara prompt») trasforma il flusso grezzo in un prompt ottimizzato e sicuro; a valle revisiona se leggero…
Build features with tests-before-code rigor — use for new features needing test coverage
Orchestrate multi-agent implementation with parallel phase execution. Spawns teammates for independent phases and coordinates dependent phases.
Technical writing and documentation skill — specs, runbooks, changelogs, meeting notes, ADRs
Recursively checkout `` on root + every nested git submodule, including detached HEADs. Use when the user types `/rcheckout ` or asks to switch recursively.
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…
Generates audio feedback from text using OpenAI TTS. Fulfills the "Conversational" requirement.
Анализирует Telegram-канал или список постов, извлекает живой стиль автора и выдаёт TG_STYLE_GUIDE.md — операционный файл для автономного написания постов от лица персоны.
Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
Archive completed and abandoned tasks with CHANGE_LOG.md updates and memory harvest suggestions
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…
Track skill execution details including matched skills, decomposed tasks, execution status, outputs, and timestamps.
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/.
Safely update skills with preview, migration support, and user validation. Never lose data or break workflows.
Use when the user wants to know which OpenClaw skills are used most, compare usage across periods, or understand how counts are shared across installations, agents, and channel…
Audit installed Claude skills: flag unused, spot duplicates, generate deactivation checklist. Reduces context noise from skill overload.
Use for periodically reviewing which skills are overused, underused, missing, or creating friction by examining recent governance artifacts, handoffs, instruction trackers, and…
Install and set up the OpenClaw Skill Usage plugin.\n\n Use when users say:\n - \"install skill usage\"\n - \"setup skill usage\"\n - \"add skill usage analytics\"\n - \"install…
Evidence before claims — run verification commands before declaring work complete, fixed, or passing