Build a dependency graph of skills based on cross-reference extraction. Outputs JSON, Mermaid diagram, or stats. Identifies orphan skills and most-referenced skills.
SKILL.md description style — conceptual conciseness then caveman/wenyan compression. Retriever is LLM semantic match, not keyword index, so terse-but-complete beats verbose prose.
Detect workflow patterns, draft new skills, and improve existing ones. Active triggers: "analyze my skills" / "what skills should I make?".
Comprehensive guide for creating and managing skills in Claude Code with auto-activation system, following Anthropic's official best practices including the 500-line rule and…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing sk — from…
開發新 Agent Skills 的標準化工作流程。當使用者要求建立新技能、轉化工作流程為技能、或詢問 SKILL.md 格式時自動啟用。包含技能結構設計、YAML frontmatter 規範、觸發關鍵字最佳實踐、資源檔案組織。A meta-skill for creating new Agent Skills with standardized…
Search for reusable skills across OpenSpace's local registry and cloud community. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond…
Enforces Law 7 (Learn From Every Session) of the 7 Laws of AI Agent Discipline. Distills repeated successful tool sequences into reusable draft instincts, so a pattern that worked…
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements.
Spawn and manage E2B sandbox instances for parallel Claude Code task execution. Use when you need to run multiple tasks in parallel across isolated environments, distribute work…
Выполняет перевод, проверку и исправление текста между русским и татарским языками с учетом контекста локализации ПО и игр.
Naval Ravikant的思维操作系统。基于著作、播客、推文、决策记录和外部批评的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 激活后沉浸式扮演Naval，直接以「我」的视角回应问题。 当用户提到「用Naval的视角」「Naval会怎么看」「纳瓦尔模式」「Naval perspective」「切换到Naval」 — from…
Signals that this message was dictated by voice, so technical terms may be mis-transcribed. Use when the user prefixes a dictated message with /v. — from wkentaro/dotfiles
Выполняет художественный перевод английских текстов на русский язык, сохраняя литературный стиль, тональность и повествовательный поток оригинала.
Comprehensive diagnostic of the skill ecosystem — 21 categories across 5 domains with composite health scoring, trend tracking, patch suggestions, and interactive…
Выполняет команды по перефразированию названий, созданию описаний и придумыванию названий для дизайнов ногтей на английском или русском языках. — from ECNU-ICALK/AutoSkill
Как редактировать навыки фреймворка, работая из каталога проекта 1С. Используй когда пользователь просит изменить, дополнить или исправить навык/правило фреймворка, находясь не в…
Редактирование, перефразирование и составление процессуальных и следственных документов на русском языке в строгом соответствии с нормами УПК РФ и официально-деловым стил — from…
AI-powered enhancement of skill SKILL.md files. Use to transform basic templates into comprehensive, high-quality skill documentation.
Improves Agent Skills via validate → rule-based eval cases → plugin-eval → prompt evals → bounded edits with held-out gates.
Evaluate, forward-test, and improve Codex skills. Use when Codex is asked to test a skill, compare performance with and without a skill, improve a skillset, make skills stronger,…
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality.
Self-improving skill system that auto-extracts patterns from sessions into reusable skills with confidence scoring, skill versioning, import/export, and continuous improvement…
Skill 进化管理器，记录 skill 运行中的错误和经验，自动迭代优化。当 skill 运行出错或有改进空间时，记录经验到 evolution.json，然后缝合到 SKILL.md 中，让 skill 越来越牛逼。适用于：skill 运行出错后想避免再犯、发现 skill 可以优化的地方、想让 skill 在使用中不断进化。
技能自进化工作流 —— 对已有 skill 进行反思分类、双结构维护、Auditor 检查的标准化流程。 适用于：遇到一个 skill 执行失败后，判断是 skill 本身的问题还是执行失误，然后针对性地修改。 Triggers: skill 改进, skill 进化, 优化 skill, skill 自进化, 技能改进, 修改 skill, 技能有缺陷,…
Skill Self-Verification & Auto-Evolution Framework. 实现 EvoSkills/EvoSkill 论文核心思路：Surrogate Verifier 隔离验证、Pareto 前沿多版本进化、失败驱动的 Skill 发现、跨模型迁移测试。触发词：/evolve, /verify, 进化技能, 技能自验证,…
Utiliser ce skill quand il faut transformer une demande vague en un bref Markdown concis avec objectif, entrees, hypotheses, livrable attendu et points de vigilance.
Create and optimize Claude Code skills. Expertise in skill design, SKILL.md structuring, guide/template creation, and best practices for .claude/skills/ system.
プロジェクトのコード・設定・ドキュメントを精査し、Skillとして切り出すべきドメイン知識を発見・リストアップするスキル。 コードに埋もれた規約・パターン・手順をSkill候補として抽出し、Skill名・description案・初期内容の骨子を提示する。 使用タイミング: (1) 「Skill化すべき知識を探して」「プロジェクトからSkillを抽出して」…
Переводит текст с английского на русский язык, делая его максимально естественным. Используется для получения точного перевода без добавлений, комментариев или кратких из — from…
Выполняет фонетическую транскрипцию корейского текста, используя русский алфавит (кириллицу) для передачи произношения.
Questa skill permette di creare altre skills nel workspace in lingua italiana, seguendo gli standard di Google Antigravity.
Route skill lifecycle requests to a Skill Factory lane. Use when users ask to create, harden, install, audit, or skillify skills.
Capture a completed Codex workflow as a reusable SKILL.md package by analyzing session context plus optional session-collector evidence, interviewing the user with structured…
Gemini(리서치) + Codex(설계 검토) + Claude(작성) 3자 협업 워크플로우를 시작합니다
Local-first self-assessment for Claude Code skills. After you use any skill (your own or someone else's), call `skill-feedback log --rating N --outcome ...
Comprehensive Feishu (飞书) management toolkit for documents, knowledge bases, bitables, and cloud storage.
Паттерн организации файлов скилла: SKILL.md + подпапки для скриптов/ресурсов. Никогда не держать инлайн-код в SKILL.md — выносить в scripts/.
Discover external skills from the skills.sh registry. Search by keyword and/or GitHub owner, present ranked options with install counts, and recommend.
Skill 查找器 | Skill Finder. 帮助发现和安装 ClawHub Skills | Discover and install ClawHub Skills. 回答'有什么技能可以X'、'找一个技能' | Answers 'what skill can X', 'find a skill'.
skill-creator出力フィクスチャの自動検証スキル。 ディレクトリ構造・SKILL.mdフォーマット・エージェント仕様書・JSONスキーマ・EVALS.json を6スクリプトで決定論的に検証する。
Use when the user asks Codex to inspect, import, enable, disable, deploy, update, repair, migrate, or uninstall Skill Flow skill groups through the skill-flow CLI or bridge…
Scaffold and build Claude Code skills from plans or descriptions. Generates SKILL.md files, sub-skills, scripts, references, agents, and templates following the Agent Skills…
Arquitecto y generador de Skills. Define, estructura y registra nuevas capacidades para el agente Antigravity. — from general/agents-skills-meta
Arquitecto y generador de Skills. Define, estructura y registra nuevas capacidades para el agente Antigravity. — from general/agents-skills-meta
Forjador de habilidades. Detecta patrones repetidos en AUMFORMBRING y crea nuevas skills automáticamente (auto-evolución).
Enhanced SKILL.md format inspired by Claude Code. Use when creating or upgrading skills to include rich metadata, conditional activation, tool restrictions, and multi-agent…
Functional verification audit of all registered onex skills — classifies by risk tier, invokes read-only skills, greps write skills for stub markers, produces structured per-skill…
Audit workforce skill gap identification systems and labor market alignment. Use when you need to evaluate skill taxonomy quality, individual and aggregate gap analysis accuracy,…
When no skill covers a needed capability, draft a local skill proposal and log it in SKILL_REQUESTS.md.
Gerencia os skill gates do Otto. Use quando precisar: - Entender por que uma tool carrega uma skill automaticamente - Listar regras default e overrides de skill gates - Criar…
Auto-generate Claude skills from documentation URLs using Firecrawl agent. Use when user wants to create a skill from docs, API references, or tool homepages.
Use for selecting and enforcing the right process level across skills via deterministic risk scoring, mode-based gates, critical overrides, break-glass controls, ownership, and…
HelmForge skill 开发/升级流程管家 + 质量门控。用于新增 skill、修改现有 skill、废弃 skill 时的规范流程与五镜像同步 checklist，含 frontmatter 校验、references 组织、入口文档同步（CLAUDE/AGENTS/GEMINI/OPENCLAW.md）、路由表更新、ETHICS 合规…
Map Skill() refs across plugins; detect hubs, isolates, and dangling targets. Use when auditing skill composition or hunting broken refs.
Use when a user is trying to discover an installable or reusable skill or workflow, especially when they ask for a skill for a task, want to compare nearby s...
Guidelines for authoring SKILL.md files with progressive disclosure. Apply when editing files under `.claude/skills/` or creating new skills.
Structural lint for skill files: validates YAML frontmatter has required fields, checks line count limits, and enforces coordination metadata (group, order, internal) as errors.
Registers skills for next-session activation by injecting them into CLAUDE.md. Claude cannot hot-reload mid-session — this prepares skills for the NEXT session.
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs.