docs
Get official Claude Code documentation. Use when the user asks about Claude Code features OR when you need to create/implement plugins, skills, hooks, subagents, slash commands, or MCP servers. Always retrieve documentation BEFORE implementing any Claude Code feature. Topics include configuration, settings, deployment, and troubleshooting.
What this skill does
# Claude Code Documentation This Skill provides access to official Claude Code documentation through the `claude-docs` CLI tool. ## Available Documentation The plugin's session hook installs the `claude-docs` CLI globally, making it available as a command. ## When to Use This Skill **User asks questions:** - "How do I..." (create plugins, use hooks, configure settings, etc.) - "Can Claude Code..." (feature capability questions) - "What are..." (subagents, MCP servers, skills, etc.) - "Tell me about..." (any Claude Code feature or concept) - Questions about configuration, setup, deployment - Troubleshooting Claude Code issues **User requests implementation:** - "Create/make a skill that..." - Get skill documentation first - "Write a plugin for..." - Get plugin documentation first - "Add a hook that..." - Get hook documentation first - "Set up a slash command..." - Get command documentation first - "Build a subagent..." - Get subagent documentation first - ANY task involving Claude Code features - retrieve docs BEFORE implementing **You recognize you need domain knowledge:** - Before creating plugins, skills, hooks, subagents, or commands - Before modifying Claude Code configuration - Before answering questions about Claude Code capabilities - When you're unsure about the correct way to implement a Claude Code feature ## How to Use the CLI Tool ### Step 1: Identify what documentation is needed Determine the topic from the user's question: - plugins, hooks, skills, mcp, agents, slash commands, settings, etc. ### Step 2: Load ALL related documentation **Common topics and their related slugs (load ALL):** - **plugins** → `plugins`, `plugin-marketplaces`, `plugins-reference` - **hooks** → `hooks-guide`, `hooks` - **skills** → `skills` - **mcp** → `mcp` - **agents/subagents** → `sub-agents` - **slash commands** → `slash-commands` - **settings** → `settings` - **security/iam** → `security`, `iam` - **monitoring** → `monitoring-usage`, `analytics`, `costs` ### Step 3: Use the CLI tool with Bash **Load full documents (default approach):** ```bash claude-docs get plugins claude-docs get plugin-marketplaces claude-docs get plugins-reference ``` **Browse document structure (if needed):** ```bash # See list of all available docs claude-docs list # See table of contents for a specific document claude-docs list plugins ``` **Search for specific topics:** ```bash claude-docs search 'oauth' claude-docs search 'environment variables' ``` **Get specific section (only if specifically requested):** ```bash claude-docs get 'plugins#quickstart' ``` ## Key Principles 1. **Load full documents first** - `get <slug>` loads the entire document including all sections 2. **Load ALL related docs** - Don't load just one if multiple exist for a topic 3. **Avoid anchors unless needed** - Full documents are usually better than subsections 4. **Be comprehensive** - When in doubt, load more documentation rather than less ## What NOT to Do - ❌ Don't answer from training data without checking current docs - ❌ Don't use anchors (`get <slug>#<anchor>`) unless user specifically requests a section - ❌ Don't load just one doc when multiple related ones exist - ❌ Don't search the web before checking official documentation ## Example Workflows **User asks:** "How do I create a plugin with hooks?" 1. Identify topics: plugins + hooks 2. Load all related documentation: ```bash claude-docs get plugins claude-docs get plugin-marketplaces claude-docs get plugins-reference claude-docs get hooks-guide claude-docs get hooks ``` 3. Provide comprehensive answer from loaded docs **User asks:** "What are Skills?" 1. Identify topic: skills 2. Load documentation: ```bash claude-docs get skills ``` 3. Explain Skills concept from documentation **User asks:** "Can you help me set up MCP servers?" 1. Identify topic: mcp 2. Load documentation: ```bash claude-docs get mcp ``` 3. Provide setup instructions from docs ## Remember - The `claude-docs` CLI is installed globally (managed by the plugin's session hook) - Always load documentation BEFORE implementing Claude Code features - Documentation is locally cached and fast to retrieve - Full documents are comprehensive - you usually don't need subsections - After loading docs, provide answers based on official information This Skill ensures you always have accurate, up-to-date Claude Code documentation when needed.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.