Individual skill

claude-api

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

internal/skills/bundled/skills/claude-api/SKILL.md

Read pinned source

Source commit 9afd8644076e95f5fcb97e408c54de860a149614

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 415
Repository last updated: Oct 14, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

engineering Derived category
data Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

LICENSE.txtdoc · 11,357 bytes
SKILL.mdcore · 18,276 bytes
SKILL.mdcore · 18,276 bytes
csharp/claude-api.mddoc · 1,758 bytes
curl/examples.mddoc · 4,475 bytes
go/claude-api.mddoc · 3,980 bytes
java/claude-api.mddoc · 3,941 bytes
php/claude-api.mddoc · 1,568 bytes
python/agent-sdk/README.mddoc · 9,869 bytes
python/agent-sdk/patterns.mddoc · 8,208 bytes
python/claude-api/README.mddoc · 10,942 bytes
python/claude-api/batches.mddoc · 4,948 bytes
python/claude-api/files-api.mddoc · 3,881 bytes
python/claude-api/streaming.mddoc · 5,217 bytes
python/claude-api/tool-use.mddoc · 16,730 bytes
ruby/claude-api.mddoc · 1,816 bytes
shared/error-codes.mddoc · 7,050 bytes
shared/live-sources.mddoc · 10,727 bytes
shared/models.mddoc · 4,625 bytes
shared/tool-use-concepts.mddoc · 14,761 bytes
typescript/agent-sdk/README.mddoc · 7,839 bytes
typescript/agent-sdk/patterns.mddoc · 3,274 bytes
typescript/claude-api/README.mddoc · 8,627 bytes
typescript/claude-api/batches.mddoc · 2,594 bytes
typescript/claude-api/files-api.mddoc · 2,260 bytes
typescript/claude-api/streaming.mddoc · 5,582 bytes
typescript/claude-api/tool-use.mddoc · 12,821 bytes

Read excerpt


# Building LLM-Powered Applications with Claude

This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.

## Defaults

Unless the user requests otherwise:

For the Claude model version, please use Claude Opus 4.6, which you can access via the exact model string `claude-opus-4-6`. Please default to using adaptive thinking (`thinking: {type: "adaptive"}`) for anything remotely complicated. And finally, please default to streaming for any request that may involve long input, long output, or high `max_tokens` — it prevents hitting request timeouts. Use the SDK's `.get_final_message()` / `.finalMessage()` helper to get the complete response if you don't need to handle individual stream events

---

## Language Detection