All skills & plugins / Anthropic Agent Skills

claude-api

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.ant

Type: Skill by Anthropic
Catalog: Anthropic Agent Skills
Source: anthropics/skills/skills/claude-api (96 files scanned)
Install and details: Agent Skills Index entry
License: Apache-2.0 (LICENSE file)
Signals: Bundled scriptsNetwork calls in codeReads credentials

Pre-approved tools

No allowed-tools or tools list in its SKILL.md, command or agent files, so the agent asks before using tools as usual.

Hooks

No hooks.

MCP servers and apps

None.

Bundled code

4 code files (JavaScript, Python):

Network calls

1 file with a network call pattern. First match per file:

skills/claude-api/shared/preserved-thinking-migration/drop_block_probe.py:96
```
import http.client
```

Starts other programs

No subprocess, exec or eval pattern found.

Credentials referenced

ANTHROPIC_API_KEYANTHROPIC_AUTH_TOKEN

Static scan of commit dbd4588 on 2026-10-27. Signals are patterns found in the files, not a verdict: a network call can be the whole point of a skill. Read the linked lines before you decide. How the scan works.