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.
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)
Claude Code plugin creation guide. Use when creating new plugins, adding commands/skills/hooks/MCP servers to plugins, or setting up marketplace distribution.
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
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: -…
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 📚…
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）:…
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.
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…
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).
Portable Codebase Argus agent playbook for evidence-first multi-agent review of GitHub pull requests, CI failures, GitHub Actions logs, GitHub App webhook review, /argus PR…
Create, manage, and optimize GitHub Codespaces cloud development environments. Configure devcontainers, manage resources, and streamline cloud-based development.
Delegate coding tasks to Codex AI for implementation, analysis, and alternative solutions. Use when you need a second AI perspective, want to explore different approaches, or need…
Use when creating, installing, validating, folding, or troubleshooting Codex custom subagent role TOML and discoverability config.
OpenAI Codex CLI(`codex exec`)의 내장 `image_generation` 툴로 이미지를 생성하는 스킬. 단일/배치/병렬 생성 지원. 핵심 강점은 **최대 5장 동시 병렬 생성** (실측 직렬 대비 2.4~2.85배 속도).
Use OpenAI Codex from inside Claude Code — code reviews, adversarial reviews, and delegating tasks to Codex.
Use when the user wants to set up or sync Codex MCP servers for Polaris workflows. Trigger: 'codex mcp', '同步 mcp', '設定 codex mcp', '讓 codex 接 mcp', 'codex mcp setup'.
マルチエージェントでタスク分解・委譲・並列実行・結果統合を行うための共通運用スキル。Use when: 「マルチエージェントで進めたい」「並列で進めたい」「サブエージェントに任せたい」「複数 agent で調査/実装/レビューしたい」。Claude Code / Codex のどちらでも使える共通原則を定義し、末尾にツール別の読み替えを置く。
Construction d'agents de coding autonomes capables de lire, écrire et modifier du code. Se déclenche avec "coding agent", "agent de code", "agent développeur", "Devin", " — from…
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. — from user/repo.git
コーディング用プロンプトを最適化・添削するスキル。 以下の状況で使用: (1) ユーザーが「このプロンプトを改善して」「プロンプトを最適化して」と依頼した時 (2) ユーザーが明示的に「/coding-prompt-optimizer」を実行した時 (3) AI向けプロンプトの品質改善を求められた時
Enable multi-agent brainstorming and collaborative problem-solving using pub/sub messaging. Use for complex decisions requiring multiple perspectives.
Minds multiply, not add. Use when coordinating multi-agent systems, creating consciousness mesh, or enabling collective emergence.
Use when creating or editing a slash command in .agent-src.uncompressed/commands/ — frontmatter, numbered steps, safety gates — even when the user just says 'add a /command for X'.
Create or edit a Claude Skill with guided assistance and best practices
Sistema multi-agente especializado en materias primas globales. ACTÍVALO ante cualquier mención de: oro, plata, petróleo, gas natural, cobre, trigo, soja, maíz, commodities,…
Shared utilities for Gemini-based skills including API key management, Vertex AI configuration, and client helpers. Use as dependency for skills requiring Gemini API access.
Review pull requests that change Compose UI by rendering @Preview composables on base and head and diffing them.
Connect LLMs to MCP servers through composable patterns like router, evaluator-optimizer, and orchestrator flows without hand-managing server lifecycles.
Automate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas. — from phamlongh230-lgtm/yamtam-engine
Automate Appdrag tasks via Rube MCP (Composio). Always search tools first for current schemas. — from phamlongh230-lgtm/yamtam-engine
Automate Gemini tasks via Rube MCP (Composio). Always search tools first for current schemas. — from phamlongh230-lgtm/yamtam-engine
Automate OpenAI API operations -- generate responses with multimodal and structured output support, create embeddings, generate images, and list models via the Composio M — from…
Use when superpowers:brainstorming has produced a spec, OR when superpowers:writing-plans has produced a plan, OR when about to invoke superpowers:subagent-driven-development or…
\"Compress context to fit within token limits while preserving signal. 壓縮語境以適應令牌限制同時保留關鍵信號。 Use when: context approaching window limit, compressing conversation history or RAG…
Reduces token burn by compressing command output and deduplicating repeated file reads before they are sent to Claude Code, Codex, Cursor, and related coding-agent tools.
Applies personalized Claude Code settings. Use when setting up Claude Code preferences on a new machine.
Den putior-MCP-Server konfigurieren, um 16 Workflow-Visualisierungswerkzeuge fuer KI-Assistenten bereitzustellen.
Set up Craft Agents workspaces with connected sources, imported skills, MCP servers, permission modes, and session workflow states for supervised agent work.
Connect Claude to any app. Send emails, create issues, post messages, update databases - take real actions across Gmail, Slack, GitHub, Notion, and 1000+ services.
Expose Zendesk tickets, comments, and Help Center context to MCP-capable agents for supervised support workflow preparation.