How do I install the Anthropic API skill?

Run npx skillmds@latest add xiaolai/anthropic-api in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Anthropic API safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Anthropic API?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Anthropic API free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Anthropic API?

xiaolai (@xiaolai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Anthropic API by xiaolai — Agent Skill

Name: Anthropic API
Author: xiaolai

Anthropic API

Router skill for the Anthropic Messages API and adjacent surfaces (admin endpoints, compliance, beta features, models catalog) hosted under platform.claude.com/docs/en/api/. Use when the user asks about: POST /v1/messages, tool_use / tool_result blocks, count_tokens, message batches, streaming responses, prompt caching, prompt cache TTL / breakpoints, system prompts, anthropic-beta headers, the admin API (organizations / workspaces / API keys / invites), compliance endpoints (data residency, audit logs, retention), beta-only features behind a beta header, or the models catalog (model IDs, deprecation dates, context window sizes). Skip: questions about Claude Code (use claude-code skill), the Claude Agent SDK (use claude-agent-sdk), platform features beyond the raw API such as Agent Skills format or tool-use guides (use anthropic-platform-features), MCP connector docs (claude-connectors), or per-language auto-generated SDK reference (use anthropic-sdk's TypeScript / Python types directly via your IDE).

xiaolai a240223 29 files · 193.6 KB Updated Sep 17, 2026

File contents

Anthropic API Reference — Router

Field	Value
API base	`https://api.anthropic.com/v1/`
Source docs	platform.claude.com/docs/en/api
TypeScript SDK	`@anthropic-ai/sdk`
Python SDK	`anthropic`

This skill is auto-updated daily. A pipeline reads the upstream docs and rewrites the per-surface files below. Section structure is stable; content drifts to track upstream.

Dispatch table

Surface file	Read when the user asks about…
`SKILL-messages.md`	`POST /v1/messages`, request/response shape, `tool_use` / `tool_result` content blocks, streaming (`stream: true`), system prompts, `count_tokens`, message batches; also legacy `/v1/complete` (text completions)
`SKILL-admin.md`	admin API — organizations, workspaces, API keys, invites, usage reports, cost reports
`SKILL-compliance.md`	data residency, audit logs, retention policies, compliance API endpoints
`SKILL-beta.md`	features gated behind `anthropic-beta` header, beta endpoints, opt-in feature flags
`SKILL-models.md`	model IDs (`claude-opus-4-7`, `claude-sonnet-4-6`, `claude-haiku-4-5-20251001`, …), context window sizes, deprecation dates, model card / capabilities

Out of scope for this skill (intentionally excluded by docsPathFilter): the auto-generated per-language SDK reference under platform.claude.com/docs/en/api/{cli,csharp,go,java,php,python,ruby,terraform,typescript}/ (~1100 pages). Use your IDE's type-defs from @anthropic-ai/sdk (npm) or anthropic (PyPI) for those — they ship the authoritative signatures and stay in sync with the SDK release you're using.

Auto-correction rules

Rule file	Triggers on edits to
`rules/messages-api.md`	code calling `client.messages.create`, `POST /v1/messages`, or constructing `tool_use` / `tool_result` content blocks

This skill is auto-updated daily by a maintainer-run pipeline. File issues at xiaolai/anthropic-docs — SKILL fixes flow through the next research run, not via PRs.

---name: anthropic-apidescription: Router skill for the Anthropic Messages API and adjacent surfaces (admin endpoints, compliance, beta features, models catalog) hosted under platform.claude.com/docs/en/api/. Use when the user asks about: POST /v1/messages, tool_use / tool_result blocks, count_tokens, message batches, streaming responses, prompt caching, prompt cache TTL / breakpoints, system prompts, anthropic-beta headers, the admin API (organizations / workspaces / API keys / invites), compliance endpoints (data residency, audit logs, retention), beta-only features behind a beta header, or the models catalog (model IDs, deprecation dates, context window sizes). Skip: questions about Claude Code (use claude-code skill), the Claude Agent SDK (use claude-agent-sdk), platform features beyond the raw API such as Agent Skills format or tool-use guides (use anthropic-platform-features), MCP connector docs (claude-connectors), or per-language auto-generated SDK reference (use anthropic-sdk's TypeScript / Python types directly via your IDE).---# Anthropic API Reference — Router| Field | Value ||---|---|| **API base** | `https://api.anthropic.com/v1/` || **Source docs** | [platform.claude.com/docs/en/api](https://platform.claude.com/docs/en/api) || **TypeScript SDK** | [`@anthropic-ai/sdk`](https://www.npmjs.com/package/@anthropic-ai/sdk) || **Python SDK** | [`anthropic`](https://pypi.org/project/anthropic/) |> **This skill is auto-updated daily.** A pipeline reads the upstream> docs and rewrites the per-surface files below. Section structure is> stable; content drifts to track upstream.## Dispatch table| Surface file | Read when the user asks about… ||---|---|| [`SKILL-messages.md`](SKILL-messages.md) | `POST /v1/messages`, request/response shape, `tool_use` / `tool_result` content blocks, streaming (`stream: true`), system prompts, `count_tokens`, message batches; also legacy `/v1/complete` (text completions) || [`SKILL-admin.md`](SKILL-admin.md) | admin API — organizations, workspaces, API keys, invites, usage reports, cost reports || [`SKILL-compliance.md`](SKILL-compliance.md) | data residency, audit logs, retention policies, compliance API endpoints || [`SKILL-beta.md`](SKILL-beta.md) | features gated behind `anthropic-beta` header, beta endpoints, opt-in feature flags || [`SKILL-models.md`](SKILL-models.md) | model IDs (`claude-opus-4-7`, `claude-sonnet-4-6`, `claude-haiku-4-5-20251001`, …), context window sizes, deprecation dates, model card / capabilities |> **Out of scope for this skill** (intentionally excluded by `docsPathFilter`):> the auto-generated per-language SDK reference under> `platform.claude.com/docs/en/api/{cli,csharp,go,java,php,python,ruby,terraform,typescript}/`> (~1100 pages). Use your IDE's type-defs from `@anthropic-ai/sdk`> (npm) or `anthropic` (PyPI) for those — they ship the authoritative> signatures and stay in sync with the SDK release you're using.## Auto-correction rules| Rule file | Triggers on edits to ||---|---|| `rules/messages-api.md` | code calling `client.messages.create`, `POST /v1/messages`, or constructing `tool_use` / `tool_result` content blocks |---*This skill is auto-updated daily by a maintainer-run pipeline. Fileissues at [xiaolai/anthropic-docs](https://github.com/xiaolai/anthropic-docs) —SKILL fixes flow through the next research run, not via PRs.*

Frequently asked questions