CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply…
Audit CLAUDE.md and the memory store (MEMORY.md + fact files) for drift — stale path citations, cross-file contradictions, duplicated facts, and bloat.
Audit CLAUDE.md files in repository against 6-criteria quality rubric. Auto-activates when: user mentions CLAUDE.md / project memory quality / audit memory.
Creating and maintaining CLAUDE.md project memory files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural…
Use when the user wants to create or bootstrap a project-local CLAUDE.md - the auto-loading project context file for the agent.
Use when creating CLAUDE.md files, updating existing CLAUDE.md, validating CLAUDE.md structure, or auto-fixing CLAUDE.md issues.
Manage CLAUDE.md documentation when updating the seed system documentation or project overview. Not for creating specific skills or commands.
Produces a CLAUDE.md health report listing conflicts, redundancies, and stale rules across the global, project, and subdirectory hierarchy — and optionally installs a PreToolUse…
How to maintain a project's claude.md file -- the project's working memory loaded into every agent session.
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files.
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files.
Validate/update/create CLAUDE.md memory files with progressive disclosure and context-optimized structure — from general/ai-tooling
How Claude writes rules for itself, when to update CLAUDE.md, keeping it lean and effective
Optimize CLAUDE.md files using progressive disclosure. Goal: Maximize information efficiency, readability, and maintainability.
審查並精簡 CLAUDE.md 文件：把累積的 gotcha / 規則段落路由到對應的 .claude/rules/ 子檔， 刪除過期內容，維持 CLAUDE.md 在 Anthropic 建議的 200 行軟上限內。 觸發關鍵字：CLAUDE.md 太大、精簡 CLAUDE.md、CLAUDE.md 太多規則、migrate gotcha to…
Reviews, creates, and optimizes CLAUDE.md and .claude/ folder structures against Anthropic's official best practices.
Set up or review the project's CLAUDE.md through an interactive interview with the developer
PROMETHEUS NEXUS v6.0 - Constitutional multi-agent framework with director domains, mutual accountability, and Teammate coordination.
Authoritative reference and authoring guide for the Claude platform — both the Claude Code `.claude/` config layer (skills, subagents, output styles, hooks, plugins, settings) and…
**Use MCP repo-map tools when:** - Searching for symbols by name pattern (faster than Grep) - Getting all symbols in a file (faster than Read + parsing)
Scaffold complete Claude Code plugins with MCP servers, commands, agents, and skills
Basics of authoring a Claude Code plugin — the plugin.json manifest, the .claude-plugin/ directory layout, the component types (skills, agents, commands, hooks, MCP), and the…
Claude Code plugin creation guide. Use when creating new plugins, adding commands/skills/hooks/MCP servers to plugins, or setting up marketplace distribution.
Use for diagnosing and fixing Claude Code / Claude Desktop plugin staleness, stuck updates, and cache drift.
Use when managing Claude Code plugins, plugin marketplaces, plugin validation/details/token cost/tag/install/update/remove/prune, session-only plugin-dir or plugin-url, MCP…
Claude Code plugin development reference for this monorepo (evonest, distill, solera, flutter-cask, pencil_m3_flutter).
Comprehensive validation system for Claude Code plugins to ensure compliance with official plugin development guidelines and prevent installation failures
Bit CLI command reference. Use before running bit commands to get correct syntax and flags.
Guides creation and improvement of Claude Code skills using Anthropic's official
Guide for creating effective Claude skills. Use when users want to create, update, package, or refine a Claude skill that extends Claude with focused knowledge, workflows, or tool…
[claude-plugins/skill-creator] Create new skills, modify and improve existing skills, and measure skill performance.
Use when user asks to leverage claude or claude code to do something (e.g. implement a feature design or review codes, etc).
Legge e interroga la knowledge base Logseq personale dell'utente (appunti, note, journal, task). Il percorso del graph si configura con la variabile d'ambiente LOGSEQ_GRAPH_PATH…
Copy or sync Claude skills from ~/.claude/skills into ~/.codex/skills so they are available in Codex.
エージェントライフサイクル管理を専門とするスキル。 起動、実行、状態管理、終了、バージョニング、メンテナンスにより、 エージェントの継続的な品質を保証します。 📖 参照書籍: - 『The Pragmatic Programmer』（Andrew Hunt, David Thomas）: 手順設計 📚 リソース参照: -…
スクラム・カンバンの実践知識とアジャイルプロジェクト管理の体系的手法。 ジェフ・サザーランドのスクラムフレームワークを基盤として、 イテレーティブ開発とチームの自己組織化を実現します。 📖 参照書籍: - 『Agile Estimating and Planning』（Mike Cohn）: 見積もり 📚 リソース参照: -…
Evaluate and benchmark Agent Skills quality using static analysis and evaluation methodology. Use when discussing skill quality, benchmarking skills, measuring activation rates,…
Composite Actionsのスキル。 📖 参照書籍: - 『The Pragmatic Programmer』（Andrew Hunt, David Thomas）: 実践的改善 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド -…
データベース接続管理の専門スキル。 サーバーレス環境での接続管理、Tursoの接続管理とEmbedded Replicas、 高負荷時の接続最適化を専門とします。 専門分野: - 接続管理設計: 環境に応じた最適な接続設定 - サーバーレス対応: TursoでのlibSQL接続管理とEmbedded Replicas - Drizzle ORM統合:…
Ryan Dahlのイベント駆動・非同期I/O思想に基づくファイルシステム監視の専門知識。 Chokidarライブラリを中心に、Observer Patternによる効率的なファイル変更検知、 クロスプラットフォーム対応、EventEmitterによる疎結合な通知システムを提供。 使用タイミング: -…
Few-Shot Learning（少数例示学習）のパターンとベストプラクティスを提供するスキル。 効果的な例示の設計、構造化、配置により、AIの出力品質を大幅に向上させます。 専門分野: - 例示設計: 効果的な入出力ペアの作成 - パターン構造: 例示の形式と配置最適化 - ドメイン適応: 領域特化した例示戦略 - 品質制御:…
SOLID原則のインターフェース分離原則（ISP）を専門とするスキル。 Robert C. Martinの『アジャイルソフトウェア開発の奥義』に基づき、 クライアントが使用しないメソッドへの依存を強制しない、 📖 参照書籍: - 『The Pragmatic Programmer』（Andrew Hunt, David Thomas）: 実践的改善 📚…
ippoan/claude-skills (この repo 自身。Claude Code 共有 skill 集) の構造ナビゲーション。skill ディレクトリ群を「種別 (per-repo map / PR・CI 運用 / 構造把握メタ / secret・MCP / テスト・カバレッジ / freee・egov ドメイン /…
Reference guide for Claude Code skills system (January 2026). Use when creating, modifying, or understanding skills, SKILL.md format, frontmatter fields, hooks, context fork, or…
PM2エコシステム設定の設計と最適化を専門とするスキル。 Alexandre Strzelewiczの思想に基づき、ecosystem.config.js の 構成、実行モード選択、環境設定、監視設定を体系的に設計します。 📖 参照書籍: - 『The Pragmatic Programmer』（Andrew Hunt, David Thomas）:…
Author, validate, and install custom Claude Code subagents as .claude/agents Markdown files. Use when the user asks to create a subagent, custom agent, or .claude/agents role;…
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Eliza runtime context.
Use when spawning a Claude Code, Codex, Gemini, Aider, or other CLI task agent whose work needs parent Milady runtime context.
Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents.
Your Claude Code wingman - dispatch coding tasks via tmux for free/work-paid coding while keeping Clawdbot API costs minimal
Compiles web documentation into agent-native memory context using the Moltext Compiler. — from general/ai-tooling
Stop your AI from making the same mistake twice. Pre-Action Gates that block repeat hallucinations, retry loops, and known-bad tool calls before they reach the model — zero tokens…
Canonical joelclaw mail coordination protocol for all agents. Use when announcing work, checking inboxes, reserving files, releasing locks, handling task handoffs, triaging stale…
Run ClickHouse queries for analytics, metrics analysis, and event data exploration. Use when you need to query ClickHouse directly, analyze metrics, check event tracking — from…
Cloud Monitoring Alert - Auto-activating skill for GCP Skills. Triggers on: cloud monitoring alert, cloud monitoring alert Part of the GCP Skills skill category.
AI swarm orchestration and management in Flow Nexus cloud. Use for deploying, coordinating, and scaling multi-agent swarms for complex task execution.
Use when executing implementation plans — choose mode: batch execution with checkpoints, subagent-per-task, or parallel dispatch for independent problems.
Use when you need to interact with the MCP engineering bridge tools (cm_plan, cm_review, cm_qa, cm_deploy, cm_search).
Run the validation suite and report results against acceptance criteria Bound to ADRs: adr.skill-register-and-adr-binding-policy.draft.md,…
Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases.