rules-optimizer
Optimize and create Claude Rules (.claude/rules/*.md) following best practices. Use when asked to "create a rule", "optimize my rules", or "review my .claude/rules files".
Découvrez les skills research llm ai, comparez leurs dépôts et consultez leurs instructions.
Optimize and create Claude Rules (.claude/rules/*.md) following best practices. Use when asked to "create a rule", "optimize my rules", or "review my .claude/rules files".
Search and retrieve information from the vector knowledge base (RAG)
Gerencia memoria persistente do usuario. Use para salvar/recuperar preferencias, fatos aprendidos e contexto entre sessoes. Exemplos: 'lembre que prefiro respostas diretas', 'o que voce sabe sobre mim?', 'esque...
Create aesthetically pleasing, visually distinctive frontend UIs using research-backed prompting strategies from Anthropic's frontend aesthetics cookbook
Help with creating and managing Claude Code skills. Use when the user asks about creating skills, skill structure, or customizing Claude Code behavior.
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
string (required, when to use this agent)
OpenAI Codex (GPT-5) を使用して特定のファイルをレビュー。「ファイルレビュー」「このファイルをレビュー」などの依頼で起動。
OpenAI Codex (GPT-5) を使用したブランチ変更のセキュリティレビュー。「セキュリティレビュー」「脆弱性チェック」などの依頼で起動。
GraphRAG implementation patterns for hybrid search, Text2Cypher, and agentic retrieval. Use when implementing RAG workflows with Neo4j.
指示の最初でコンテキストが不足している場合に自動的に呼び出す必要があるスキルです
Use this skill when integrating with OpenCode CLI for task execution. This skill covers CLI commands, session management, output parsing, and best practices for OpenCode integration.
Generate comprehensive learning documents by combining information from tickets, memories, GitHub PRs, and proposals. Use after completing significant work to capture lessons learned.
Versatile Codex MCP integration for code review, technical research, documentation generation, and custom technical queries. Automatically constructs optimized prompts and gathers project context.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective cont...
Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-...
Review CLAUDE.md files for quality, efficiency, and structure. Use when auditing LLM context files, checking documentation organization, preparing for context optimization, or ensuring lean imperative instructi...
Comprehensive quality audit for CLAUDE.md context files. Use when performing thorough quality checks, preparing for releases, ensuring context efficiency, or verifying token optimization.
Track tasks and subtasks in .claude/tasks/ for context preservation. Use when planning multi-step work, tracking progress, or resuming interrupted sessions.
Meta-skill for creating and managing Claude Code skills. Activated when creating skills, modifying skill rules, or working with the skill system.
Apply Adam's voice and style when drafting articles, posts, or documentation. Auto-triggers on content creation.
This skill provides expert guidance for creating, writing, building, and refining Claude Code Skills. It should be used when working with SKILL.md files, authoring new skills, improving existing skills, or unde...
Create new Claude Code rules with proper structure and best practices. Use this skill when developing custom rules for coding standards, conventions, or guidelines that Claude should follow.
Perform comprehensive research using the diffusion research loop - parallel worker agents, iterative gap detection, and structured synthesis. Use when you need thorough, multi-perspective research with citation...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.