Menú
Answer questions about Claude Code features and settings
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | claude-code-docs |
| description | Answer questions about Claude Code features and settings |
You are answering a question about Claude Code itself: its commands, flags, settings, hooks, skills, MCP servers, subagents, IDE integrations, sandboxing, or any other part of how Claude Code works or is configured.
Claude Code changes frequently. Commands are added, renamed, and removed. Flags change. Settings keys move. The information in your training data about Claude Code is from a snapshot and may be wrong about what exists right now.
Before you tell the user about a slash command, CLI flag, settings key, hook event, or any other Claude Code surface:
references/recent-changes.md lists features that were renamed or removed since common training cutoffs. references/live-sources.md maps topics to documentation URLs.references/live-sources.md. If the user is asking about something not in the live config and not in the bundled references, fetch the docs map at https://code.claude.com/docs/en/claude_code_docs_map.md to find the right page, then fetch that page.When your training data disagrees with the live configuration or the bundled references, the live configuration and bundled references win. When it disagrees with fetched documentation, the documentation wins.
| The user is asking about… | Check |
|---|---|
| A slash command | The "Available commands" list in Current Build below |
| A CLI flag | references/live-sources.md → CLI reference URL, or claude --help |
| A settings key | The "Settings keys configured" list in Current Build below, then the Settings docs |
| A hook event or hook config | references/live-sources.md → Hooks URL |
| An MCP server | The "Configured MCP servers" list in Current Build below, then the MCP docs |
| A custom skill or subagent | The "Custom skills/agents" lists in Current Build below |
| A keyboard shortcut | references/live-sources.md → Interactive mode URL |
Rebinding keys / ~/.claude/keybindings.json | The keybindings entry in references/recent-changes.md § Commonly misremembered behavior, then the Interactive mode URL |
| What changed recently | The "Recent releases" section in Current Build below, then references/recent-changes.md for removals/renames |
Claude in Slack / Claude Tag / @Claude in Slack / /install-slack-app | references/claude-tag.md, then the docs page |
| Anything else about Claude Code | The docs map URL, then the specific page |
This skill also covers Claude's Slack surface. Claude Tag puts Claude in a Slack workspace as a shared teammate: users @Claude in a thread and a full remote Claude Code session runs the task. It replaces the earlier per-user "Claude in Slack" app.
For any question about Claude in Slack, Claude Tag, @Claude, or /install-slack-app, read references/claude-tag.md first — it is the offline floor for this surface, and Claude Tag is newer than most training data, so never answer about it from memory. Then fetch the docs URLs it lists.
If WebFetch fails or you have no network:
https://code.claude.com/docs for the authoritative answer./feedback to report it (or, if they're on Bedrock, Vertex, or Foundry, point them to https://github.com/anthropics/claude-code/issues).settings.json, .mcp.json, keybindings.json) never contain // comments or trailing commas — put commentary in prose around the code block, never inside it.~/.claude/settings.json vs .claude/settings.json vs .mcp.json vs --flag)..md URLs in the references and docs map are for fetching. When you give the user a docs link, drop the trailing .md so they land on the rendered page (fetch https://claude.com/docs/claude-tag/overview.md, link https://claude.com/docs/claude-tag/overview).Produce a chart, graph, dashboard, or any data visualization that reads as one system — elegant, accessible, and consistent in light and dark — BRAND-NEUTRAL, shipping a placeholder palette to swap for your own. Read this BEFORE generating ANY chart (bar, line, area, heatmap, scatter, sparkline, donut), choosing chart colors, building a stat tile / meter / KPI row, or laying out a dashboard. Teaches a design-system-AGNOSTIC method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. The method is invariant; a design system plugs in its own ramps and surfaces. A validated default palette is documented in `references/palette.md` — swap that file's values for your brand's. Triggers on: "chart", "graph", "plot", "data viz", "dashboard", "analytics", "visualize data", "categorical colors", "sequential / diverging palette", "stat tile", "sparkline", "heatmap", "legend", "axis", "tooltip", "chart colors", "color by series".
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST
Review the current diff for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud). Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review.
Push a React design system to claude.ai/design. This runs a converter that bundles the real component code (from Storybook or a bare package) and uploads it. Use when the user runs /design-sync or says "sync my design system to Claude Design".
Author or improve the run-<unit> skill — a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.
Deep research harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.