claude-code-guide
Provides interactive access to Claude Code documentation and configuration.
Install
mkdir -p .claude/skills/claude-code-guide-matteocervelli && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13016" && unzip -o skill.zip -d .claude/skills/claude-code-guide-matteocervelli && rm skill.zipInstalls to .claude/skills/claude-code-guide-matteocervelli
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Fetch Claude Code documentation and help update configuration. Use /claude-code-guide <topic> where topic is: memory, skills, hooks, agents, settings, mcp, plugins, cli, overview, allKey capabilities
- →Fetch Claude Code documentation for a specified topic
- →Read current configuration files related to the topic
- →Identify differences from documentation best practices
- →Suggest improvements for configuration files
- →Highlight missing recommended configurations
- →Apply updates to configuration files with user approval
How it works
The skill fetches documentation from code.claude.com for a given topic, reads local configuration files, compares them, and suggests updates. It applies changes after user approval.
Inputs & outputs
When to use claude-code-guide
- →Looking up Claude Code CLI commands
- →Updating memory configuration
- →Setting up MCP servers
- →Learning about skill authoring
About this skill
Purpose
Fetch the latest Claude Code documentation from code.claude.com and help update your configuration files based on current best practices.
Usage
/claude-code-guide <topic>
Topics
| Topic | Description | Doc URLs | Config Files |
|---|---|---|---|
memory | CLAUDE.md configuration | /memory, /best-practices | CLAUDE.md, CLAUDE.local.md |
skills | Skills system | /skills | .claude/skills/*.md |
hooks | Hooks configuration | /hooks, /hooks-guide | .claude/hooks/, settings.json |
agents | Custom subagents | /sub-agents | .claude/agents/*.md |
settings | Settings.json config | /settings | settings.json, settings.local.json |
mcp | MCP servers | /mcp | settings.json mcpServers |
plugins | Plugin system | /plugins, /plugin-marketplaces | plugins/ |
cli | CLI reference | /cli-reference | N/A (reference) |
overview | Features overview | /features-overview | N/A (reference) |
all | Full documentation | All above | All config files |
Embedded Best Practices
Memory (CLAUDE.md)
File Locations & Precedence (highest to lowest):
- Managed policy:
/Library/Application Support/ClaudeCode/CLAUDE.md(macOS) - org-wide - Project memory:
./CLAUDE.mdor./.claude/CLAUDE.md- team-shared - Project rules:
./.claude/rules/*.md- modular topic-specific rules - User memory:
~/.claude/CLAUDE.md- personal across all projects - Project local:
./CLAUDE.local.md- personal project-specific (gitignored)
Best Practices:
- Be specific: "Use 2-space indentation" beats "Format code properly"
- Use structure: Format memories as bullet points under descriptive markdown headings
- Review periodically: Update as project evolves
- Use imports:
@path/to/filesyntax to include other files - Path-specific rules: Use YAML frontmatter with
pathsfield for conditional rules
Example CLAUDE.md:
# Project Standards
- Use TypeScript strict mode
- Follow ESLint airbnb config
- Write tests for all new functions
# Commands
- Build: `npm run build`
- Test: `npm test`
- Lint: `npm run lint`
# Architecture
- React components in src/components/
- API routes in src/api/
- Shared utilities in src/utils/
Modular Rules (.claude/rules/):
---
paths:
- "src/api/**/*.ts"
---
# API Development Rules
- All endpoints must include input validation
- Use standard error response format
- Include OpenAPI documentation comments
Skills
Location: .claude/skills/<skill-name>/SKILL.md
Frontmatter Fields:
| Field | Required | Description |
|---|---|---|
name | No | Display name (defaults to directory name) |
description | Recommended | When to use this skill |
argument-hint | No | Hint for arguments, e.g., [filename] |
disable-model-invocation | No | true = only user can invoke |
user-invocable | No | false = only Claude can invoke |
allowed-tools | No | Restrict tools available |
model | No | Model override |
context | No | fork = run in subagent |
agent | No | Subagent type when context: fork |
Example Skill:
---
name: code-review
description: Reviews code for quality and best practices. Use after code changes.
allowed-tools: Read, Grep, Glob
---
When reviewing code:
1. Check for code clarity and readability
2. Look for potential bugs
3. Verify error handling
4. Check test coverage
5. Note security concerns
Provide feedback organized by priority:
- Critical (must fix)
- Warnings (should fix)
- Suggestions (consider)
Supporting Files: Skills can include additional files (templates, scripts, examples) referenced from SKILL.md.
String Substitutions:
$ARGUMENTS- User-provided arguments${CLAUDE_SESSION_ID}- Current session ID
Hooks
Configuration Location: settings.json under hooks key
Available Hook Events:
| Event | When | Matcher |
|---|---|---|
SessionStart | Session begins | startup, resume, clear, compact |
UserPromptSubmit | User submits prompt | - |
PreToolUse | Before tool execution | Tool name |
PermissionRequest | Permission dialog | Tool name |
PostToolUse | After tool succeeds | Tool name |
PostToolUseFailure | After tool fails | Tool name |
SubagentStart | Subagent spawns | Agent type |
SubagentStop | Subagent finishes | Agent type |
Stop | Claude finishes | - |
PreCompact | Before compaction | manual, auto |
SessionEnd | Session terminates | - |
Hook Configuration Structure:
{
"hooks": {
"PostToolUse": [
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/format.sh",
"timeout": 30
}
]
}
]
}
}
Exit Codes:
0: Success (stdout shown in verbose mode)2: Blocking error (stderr fed back to Claude)- Other: Non-blocking error
Environment Variables:
CLAUDE_PROJECT_DIR: Project root pathCLAUDE_ENV_FILE: (SessionStart only) File for persisting env vars
Agents (Subagents)
Location: .claude/agents/<agent-name>.md or ~/.claude/agents/
Built-in Agents:
Explore: Fast, read-only, uses HaikuPlan: Research for plan mode, inherits modelgeneral-purpose: Full tools, complex tasks
Frontmatter Fields:
| Field | Required | Description |
|---|---|---|
name | Yes | Unique identifier |
description | Yes | When to delegate |
tools | No | Allowed tools (inherits all if omitted) |
disallowedTools | No | Tools to deny |
model | No | sonnet, opus, haiku, or inherit |
permissionMode | No | default, acceptEdits, dontAsk, bypassPermissions, plan |
skills | No | Skills to preload |
hooks | No | Lifecycle hooks |
Example Agent:
---
name: code-reviewer
description: Expert code review. Use proactively after code changes.
tools: Read, Grep, Glob, Bash
model: sonnet
---
You are a senior code reviewer ensuring high standards.
When invoked:
1. Run git diff to see changes
2. Focus on modified files
3. Review for quality, security, performance
Provide feedback by priority:
- Critical (must fix)
- Warnings (should fix)
- Suggestions (consider)
Settings
File Locations (precedence highest to lowest):
- Managed: System-level
managed-settings.json - CLI arguments: Session overrides
- Local project:
.claude/settings.local.json - Project:
.claude/settings.json - User:
~/.claude/settings.json
Key Settings:
| Key | Description |
|---|---|
permissions | Allow/deny/ask rules for tools |
hooks | Hook configurations |
env | Environment variables |
model | Default model override |
attribution | Git commit/PR attribution |
mcpServers | MCP server configurations |
enabledPlugins | Plugin enable/disable |
Permissions Example:
{
"permissions": {
"allow": ["Bash(npm run lint)", "Bash(npm run test:*)"],
"deny": ["Bash(curl:*)", "Read(./.env)"],
"additionalDirectories": ["../docs/"]
}
}
MCP Servers
Adding Servers:
# HTTP transport (recommended for remote)
claude mcp add --transport http <name> <url>
# SSE transport (deprecated)
claude mcp add --transport sse <name> <url>
# Stdio transport (local)
claude mcp add --transport stdio <name> -- <command> [args...]
Scopes:
local(default): Current project, privateproject: Shared via.mcp.jsonuser: All your projects
Example .mcp.json:
{
"mcpServers": {
"github": {
"type": "http",
"url": "https://api.githubcopilot.com/mcp/"
},
"db": {
"command": "npx",
"args": ["-y", "@bytebase/dbhub", "--dsn", "${DB_URL}"]
}
}
}
Commands:
claude mcp list- List serversclaude mcp get <name>- Get detailsclaude mcp remove <name>- Remove server/mcp- Check status (in Claude Code)
Plugins
Plugin Structure:
my-plugin/
├── .claude-plugin/
│ └── plugin.json # Required manifest
├── skills/ # Skills with SKILL.md
├── agents/ # Agent definitions
├── hooks/
│ └── hooks.json # Hook configs
└── .mcp.json # MCP servers
plugin.json Manifest:
{
"name": "my-plugin",
"description": "Plugin description",
"version": "1.0.0",
"author": { "name": "Your Name" }
}
Testing Plugins:
claude --plugin-dir ./my-plugin
Installing from Marketplace:
/plugin install <plugin-name>@<marketplace>
Workflow
Step 1: Fetch Fresh Documentation
For the requested topic, fetch from https://code.claude.com/docs/en/<topic>:
For memory:
- WebFetch https://code.claude.com/docs/en/memory
- WebFetch https://code.claude.com/docs/en/best-practices
For skills:
For hooks:
For agents:
For settings:
For mcp:
- WebFetch https://code.claude.com/docs/en/mcp
For plugins:
- WebFetch https://code.claude.com/docs/en/plugins
- WebFet
Content truncated.
When not to use it
- →When documentation is not available on code.claude.com
- →When configuration files are not in the specified locations
- →When user approval for updates cannot be provided
Limitations
- →Documentation is fetched from code.claude.com only
- →Configuration file locations are predefined
- →Updates require user approval
How it compares
This workflow automates the process of comparing local configurations with official documentation and applying updates, which is more efficient than manually checking and editing files.
Compared to similar skills
claude-code-guide side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| claude-code-guide (this skill) | 0 | 2mo | Caution | Beginner |
| notion-knowledge-capture | 10 | 9mo | No flags | Intermediate |
| feishu-doc | 14 | 5mo | No flags | Intermediate |
| openspec-continue-change | 4 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by matteocervelli
View all by matteocervelli →You might also like
notion-knowledge-capture
makenotion
Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.
feishu-doc
openclaw
Feishu document read/write operations. Activate when user mentions Feishu docs, cloud docs, or docx links.
openspec-continue-change
studyzy
通过创建下一个产出物继续处理 OpenSpec 变更。当用户想要推进其变更、创建下一个产出物或继续其工作流程时使用。
kimi-cli-help
MoonshotAI
Answer Kimi Code CLI usage, configuration, and troubleshooting questions. Use when user asks about Kimi Code CLI installation, setup, configuration, slash commands, keyboard shortcuts, MCP integration, providers, environment variables, how something works internally, or any questions about Kimi Code CLI itself.
openspec-archive-change
studyzy
归档实验性工作流中已完成的变更。当用户想要在实现完成后最终确定并归档变更时使用。
feishu-perm
m1heng
Feishu permission management for documents and files. Activate when user mentions sharing, permissions, collaborators.