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
Use when creating, reviewing, or editing a CLAUDE.md (or nested CLAUDE.md) file. Defines what belongs in project memory versus what is derivable bloat — high-value build/test…
Persistent memory compression system for Claude Code enabling context preservation across sessions with automatic observations, semantic search, and privacy controls
Audit, review, clean up, and prune Claude Code durable context. Use when the user asks about CLAUDE.md, CLAUDE.local.md, .claude/rules, user Claude rules, Claude Code auto memory,…
Use when implementing Claude API cost tracking, monitoring token usage, displaying cost metrics in Settings, or user asks about costs - calculates exact costs using $0.003/1k…
Auto-select the optimal Claude model tier (Haiku 4.5, Sonnet 4.6, or Opus 4.8) for each task based on complexity signals, latency requirements, and budget constraints — minimizes…
Monitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema. — from renat
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Office document automation -- PPTX presentations, DOCX documents, XLSX spreadsheets, PDF reports. "office", "pptx", "docx", "xlsx", "pdf", "프레젠테이션", "presentation", "보고서",…
Use when you need practical office/business skills for Claude - contracts, HR, finance, PDF, documents, presentations, workflows, CRM, marketing, e-commerce, project management,…
PROMETHEUS NEXUS v6.0 - Constitutional multi-agent framework with director domains, mutual accountability, and Teammate coordination.
Guide for writing and optimizing CLAUDE.md files for maximum Claude Code performance. Use when creating new CLAUDE.md, reviewing existing ones, or when user asks about CLAUDE.md…
Maximizing Claude Code capabilities and efficiency. Use when helping users discover features, optimize workflows, or improve their Claude Code experience.
18-step Claude optimization, custom instructions, projects, style cloning. Use when user mentions 'optimisation Claude', '18 étapes', 'custom instructions'.
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus — from…
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus — from…
將提示詞和程式碼從 Claude Sonnet 4.0、Sonnet 4.5 或 Opus 4.1 遷移至 Opus 4.5。當使用者想要更新其程式碼庫、提示詞或 API 呼叫以使用 Opus 4.5 時使用。處理模型字串更新和針對已知 Opus 4.5 行為差異的提示詞調整。不會遷移 Haiku 4.5。 — from bg-szy/TOP-SKILLS
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus — from…
將提示詞和程式碼從 Claude Sonnet 4.0、Sonnet 4.5 或 Opus 4.1 遷移至 Opus 4.5。當使用者想要更新其程式碼庫、提示詞或 API 呼叫以使用 Opus 4.5 時使用。處理模型字串更新和針對已知 Opus 4.5 行為差異的提示詞調整。不會遷移 Haiku 4.5。 — from…
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus — from…
Automatic tool discovery across 19 sources — INVOKE before planning, before adding dependencies, or when looking for tools to discover relevant skills, plugins, and MCP servers
Prompt rhetoric coach — deterministic scoring and restructuring using Anthropic best practices
Delegate a coding task to Claude Code CLI via print mode (oai -p). Use for one-shot, non-interactive tasks: fix a bug, add a feature, review code, extract structured data.
Optimize Claude Code permissions by finding safe Bash commands from session history and auto-applying them to settings.json.
Sync auto-approved permissions from all community-patterns directories (including community-patterns-2, -3, etc.) to the shared project settings.
Author reference for claude-pilot components. Skills, commands, agents, rules documentation patterns. VIBE coding compliance.
Read and list planning documents from the ~/.claude/plans directory. Use when the user references a plan file located in the Claude plans directory or asks to see available plans.
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…
ACTIVATE when creating a Claude Code plugin, writing plugin.json, marketplace.json, hooks.json, or structuring plugin directories.
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
Run a non-interactive Claude Code print-mode call from Codex. Use when the user asks to \"claude print\", \"ask claude\", \"run claude\", \"consult claude\", or when a Codex Turbo…
Generate concise CLAUDE.md files and agent documentation following best practices. Use when setting up a new project for Claude Code, auditing existing CLAUDE.md, or creating…
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations.
Generate production-grade prompts following patterns extracted from Claude Code source. Use when writing system prompts, tool descriptions, agent instructions, compression…
Anthropic official XML tag patterns and prompt engineering best practices. Document behavior control tags, system prompt internals, and the 10-Component Framework for effective…
Persistent memory for Claude across conversations. Use when starting any task, before writing or editing code, before making decisions, when user mentions preferences or…
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.
Self-improvement and learning skill that helps Claude learn from user interactions, corrections, and preferences
Per-channel remote sessions for Claude Code via Discord and Telegram — each channel, thread, or chat gets its own isolated Claude Code session via tmux, with per-channel access…