cc-guide
Skill297 starsChanged 9 months agoMITView on GitHub
Claude Code documentation expert. This skill should be used when the user asks questions about Claude Code features, settings, hooks, skills, MCP servers, keyboard shortcuts, IDE integrations, Agent SDK, Claude API, or Anthropic SDK. Invoke with /cc-guide followed by a question. Examples: "/cc-guide how do hooks work", "/cc-guide what keyboard shortcuts are available", "/cc-guide how do I set up agent teams".
In this repository15 other files it gives its agents.
- .claude/skills/crossbeam-ops/CLAUDE.mdCLAUDE.md
- adu-city-researchSkill
- adu-corrections-interpreterSkill
- crossbeam-opsSkill
- demo-city-reviewSkill
- demo-contractor-correctionsSkill
- fal-aiSkill
- frontend-designSkill
- long-running-agentSkill
- nano-bananaSkill
- product-demo-videoSkill
- react-best-practicesSkill
- shadcnSkill
- skill-creatorSkill
- template-skillSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 39
If the agent was previously used in this conversation, resume it using the resume parameter with its agent ID to preserve context
- Distinctive: line 59
Use tables and code blocks where they help clarity
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Claude Code Guide
This skill provides expert answers about Claude Code by spawning the built-in claude-code-guide subagent.
CRITICAL: The claude-code-guide agent EXISTS and MUST be used
The claude-code-guide is a real, built-in subagent type in Claude Code. It is NOT a slash command — it is a specialized agent spawned via the Task tool with subagent_type: "claude-code-guide". It has access to Claude Code's full documentation and can answer questions about all Claude Code features.
Never deny that this agent exists. Never tell the user it is not a real feature. It is real. Use it.
When this skill triggers
- User invokes
/cc-guidewith a question - User asks "how do I do X in Claude Code?"
- User asks about Claude Code features, settings, configuration
- User asks about the Agent SDK or building custom agents
- User asks about the Claude API or Anthropic SDK
How to execute
- Take the user's question from the skill arguments
- Spawn the
claude-code-guideagent using the Task tool:Task tool with: subagent_type: "claude-code-guide" prompt: <the user's question, expanded into a clear research prompt> - Summarize the agent's response back to the user in a clear, concise format
- If the agent was previously used in this conversation, resume it using the
resumeparameter with its agent ID to preserve context
Topics the guide agent covers
- Claude Code CLI features and settings
- Hooks (pre/post tool hooks, event hooks like TeammateIdle, TaskCompleted)
- MCP server configuration and usage
- Skills (creating, installing, invoking)
- Agent SDK (building custom agents with claude-opus-4-6)
- Claude API / Anthropic SDK usage and tool use
- Keyboard shortcuts and keybindings
- IDE integrations (VS Code, JetBrains)
- Agent teams (creating, coordinating, task lists, messaging)
- Subagents and the Task tool
- Permissions, CLAUDE.md files, project configuration
- Slash commands and built-in commands
Response format
- Be concise — answer the question directly
- Use tables and code blocks where they help clarity
- Include practical examples when relevant
- Link to specific settings or config paths when applicable
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

