platform-docs
Anthropic Platform Docs
Local search over the official Anthropic platform documentation. All ~488 English doc pages from platform.claude.com/docs are stored as individual markdown files with directory structure preserved.
How to search
The docs live in a local directory. Find it by checking common locations:
ls ~/github/*/claude-docs/platform/docs/**/*.md 2>/dev/null
Search strategy
The platform docs are larger (~488 pages) than Claude Code docs, organized into category directories. Narrow by category first, then search within.
- Identify the category from the table below. Most questions map to one or two directories.
- Grep within that directory using 2-3 keywords. This quickly narrows to the right doc.
- Read the most relevant doc in full using Read. Grep snippets alone lack context — the full doc has examples, edge cases, and related parameters.
- Check related docs when the question spans features. For example, tool use touches both
agents-and-tools/andapi/(for the request schema). A second grep often surfaces the complementary doc. - Stop searching once you have the answer. Two or three doc reads should be enough. Don't keep searching for confirmation.
Category directory mapping
| Category | Directory | Pages | What's inside |
|---|---|---|---|
| API Reference | api/ |
314 | REST endpoints, request/response schemas, all parameters |
| Build with Claude | build-with-claude/ |
40 | Features: vision, caching, streaming, thinking, structured output, etc. |
| Resources | resources/ |
65 | Guides, cookbooks, migration guides, examples |
| Agent SDK | agent-sdk/ |
25 | Agent SDK for Python and TypeScript |
| Agents & Tools | agents-and-tools/ |
18 | Tool use, MCP, computer use, prompt chaining |
| About Claude | about-claude/ |
12 | Models overview, pricing, deprecations, what's new |
| Test & Evaluate | test-and-evaluate/ |
10 | Evals, benchmarks, testing strategies |
| Release Notes | release-notes/ |
2 | API changelog |
Two root-level docs: get-started.md and intro.md.
Common lookups
| Looking for... | Start here |
|---|---|
| API request/response format | api/messages/ |
| Model names, context windows, pricing | about-claude/models/ and about-claude/pricing.md |
| Tool use (function calling) | agents-and-tools/tool-use/ |
| Prompt caching | build-with-claude/prompt-caching.md |
| Extended thinking | build-with-claude/extended-thinking.md |
| Vision / image input | build-with-claude/vision.md |
| Streaming | build-with-claude/streaming.md |
| Structured output (JSON) | build-with-claude/structured-outputs.md |
| Batch API | build-with-claude/batch-processing.md |
| Agent SDK | agent-sdk/ |
| Computer use | agents-and-tools/tool-use/computer-use/ |
| MCP (Model Context Protocol) | agents-and-tools/mcp/ |
| Prompt engineering tips | build-with-claude/prompt-engineering/ |
| Error codes and rate limits | api/errors/ or grep for "rate limit" |
| SDK setup (Python/TypeScript) | resources/quickstarts/ |
Tips
- Directory names match the platform.claude.com URL structure, so if you know the URL slug you know the file path
- API reference pages (
api/) are very granular — one page per endpoint or schema component - Use Glob with
**/*.mdto list all docs or browse a category - The
resources/directory has practical cookbooks and migration guides — check there for "how do I..." questions
More from s0up4200/skills
mobile-adapt
Use when a user wants a site, app, screen, flow, dashboard, or full project adapted for phones or mobile web, or mentions responsive/mobile-first/iPhone/iOS Safari/touch/safe-area/landscape/keyboard issues. Also use for mobile audits, mobile regressions, small-screen layout fixes, bottom navigation redesigns, form/table/chart adaptation, or iPhone-specific usability work.
12claude-code-docs
Search and reference official Claude Code documentation locally. Use whenever the user asks about Claude Code features, configuration, hooks, MCP, settings, permissions, CLI flags, IDE integrations, plugins, skills, agent teams, scheduled tasks, sub-agents, custom agents, worktrees, session management, Desktop app features, or any other Claude Code capability. Also use when you need to look something up yourself mid-task — checking hook schemas, CLI flags, environment variables, settings format, etc. Prefer this over web fetching for Claude Code docs. Claude Code evolves fast — features like custom agents (.claude/agents/), session forking (/branch), /batch, live app preview, and worktree support are newer and not reliably in model training data, so always check the docs rather than guessing.
7release-tag
Create and push a signed git release tag. Use this skill when the user says "tag a release", "new release", "cut a release", "bump version", "release tag", "tag version", "push a tag", or any variation of wanting to create a new version tag. Also use when the user types "/release-tag" or "/release".
6retro
>-
3libtorrent
Answer questions about the libtorrent C++ BitTorrent library using a local scraped mirror of libtorrent.org docs and blog posts. Use this skill whenever the user asks about libtorrent settings, APIs, performance tuning, building libtorrent, the piece picker, DHT, BitTorrent v2, alerts, torrent_handle, session configuration, or any other libtorrent-specific topic. Also trigger when the user mentions libtorrent by name, references libtorrent classes like session, torrent_handle, settings_pack, or asks about BitTorrent implementation details that libtorrent covers. Invoke via /libtorrent or automatically when the context matches.
1emotional-awareness
>-
1