1---2name: anthropic-platform-features3description: Router skill for Anthropic platform-side features that sit above the raw Messages API: Agent Skills format (the spec for `.skill` packages used by platform-managed agents), MCP connectors hosted by Anthropic, tool use (computer use, code execution, bash tool, define-your-own tools), build-with-claude features (extended thinking, message batches, citations, Amazon Bedrock, Google Vertex, embeddings, fast mode, context editing), manage-claude operations (workload identity federation, billing, identity), and the Managed Agents product. Use when the user asks about: writing an Agent Skill `.skill` package, Anthropic's hosted MCP connector, MCP Tunnels (connecting private-network MCP servers without opening inbound ports), the computer-use tool, the code_execution tool, bash tool, extended thinking, message batches, prompt caching strategy at the platform level, citations, deploying via Bedrock or Vertex, embeddings models, fast-mode behavior, context editing strategies, WIF setup, billing / cost reports, identity4---56# Anthropic Platform Features — Router78| Field | Value |9|---|---|10| **Source docs** | [platform.claude.com/docs](https://platform.claude.com/docs) |1112> **This skill is auto-updated daily.** A pipeline reads the upstream13> docs and rewrites the per-surface files below. Section structure is14> stable; content drifts to track upstream.1516## Dispatch table1718| Surface file | Read when the user asks about… |19|---|---|20| [`SKILL-agents-and-tools.md`](SKILL-agents-and-tools.md) | Agent Skills format spec, MCP connector, MCP Tunnels (private-network MCP servers), remote MCP servers, tool use (computer use, code execution, bash, define-your-own tools), tool_choice |21| [`SKILL-build-with-claude.md`](SKILL-build-with-claude.md) | extended thinking, message batches, prompt caching, citations, Amazon Bedrock, Google Vertex, embeddings, fast mode, context editing, vision; also platform foundation (`intro`, `get-started`) and guardrails / streaming-refusals from `test-and-evaluate/` |22| [`SKILL-manage-claude.md`](SKILL-manage-claude.md) | workload identity federation (WIF), billing & usage, organizations & workspaces operations, identity & SSO, customer-managed encryption keys (CMEK) |23| [`SKILL-managed-agents.md`](SKILL-managed-agents.md) | Managed Agents product — agent definitions, deployment, lifecycle, monitoring, self-hosted sandboxes |2425---2627*This skill is auto-updated daily by a maintainer-run pipeline. File28issues at [xiaolai/anthropic-docs](https://github.com/xiaolai/anthropic-docs).*
xiaolai