Follow Discord
Sweep 30 Oct 2026 · 21:36Z Build v2.1.315 533 read Stable v2.1.308 Latest v2.1.314 Next v2.1.315 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

PDF Processing changedagents-and-tools/agent-skills/overview

Recorded here
Lines+77added
Lines−7removed
From line 2 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits14to this page, all time

## Availability ### API support #### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) ### Data handling

The whole hunk

from line 2, old and new numbered
/
lines
from line 2
22title: Agent Skills
33url: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
44description: Agent Skills are modular capabilities that extend Claude's functionality. Each Skill packages instructions, metadata, and optional resources (scripts, templates) that Claude uses automatically when relevant.
5featureMetadata:
6 status: ga
7 zdr:
8 eligibility: not-eligible
9 note: Skill data retained according to standard policy.
10 supportedModels:
11 - claude-fable-5-1
12 - claude-mythos-5-1
13 - claude-fable-5
14 - claude-mythos-5
15 - claude-mythos-preview
16 - claude-opus-5-5
17 - claude-opus-5
18 - claude-sonnet-5-5
19 - claude-sonnet-5
20 - claude-haiku-5-5
21 - claude-haiku-4-5-20251001
22 - claude-opus-4-8
23 - claude-opus-4-7
24 - claude-opus-4-6
25 - claude-sonnet-4-6
26 - claude-opus-4-5-20251101
27 - claude-sonnet-4-5-20250929
28 supportedPlatforms:
29 Claude API: ga
30 Claude Platform on AWS: ga
31 Claude Models on Google Cloud (Anthropic managed): ga
32 Microsoft Foundry (hosted on Anthropic):
33 availability: ga
34 note: Hosted on Anthropic deployments only; the skill version download endpoint (`GET /v1/skills/{skill_id}/versions/{version}/content`) is not supported on Foundry.
535---
636 
7<Note>
8 To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
9</Note>
37**API support**: Usage differs by product.
1038 
39* **Messages API**: List `skill_ids` in the `container` parameter and include the code execution tool, whose container the skills run in.
40* **Managed Agents**: Attach skills in the agent’s `skills` array, or load them from a GitHub repository mounted on the session.
41 
1142## Why use Skills
1243 
1344Skills are reusable, filesystem-based resources that give Claude domain-specific expertise: workflows, context, and best practices that turn a general-purpose agent into a specialist. Unlike prompts (conversation-level instructions for one-off tasks), Skills load on demand, so you don’t have to repeat the same guidance across conversations.
from line 300
269300 
270301Agent Skills is not covered by ZDR arrangements. Skill definitions and execution data are retained according to Anthropic’s standard data retention policy.
271302 
272For ZDR eligibility across all features, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
273 
274303For audit logging of Skills API operations, see [Audit logging](https://platform.claude.com/docs/en/build-with-claude/skills-guide#audit-logging) in Using Agent Skills with the API.
275304 
276305## Limitations and constraints
from line 365
336365 Learn how to write effective Skills that Claude can discover and use successfully.
337366 </Card>
338367</CardGroup>
368 
369## Availability
370 
371Agent Skills are available on every model.
372 
373### API support
374 
375#### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages)
376 
377* Availability: Available
378* Usage: List `skill_ids` in the `container` parameter and include the code execution tool, whose container the skills run in.
379 
380| Status | Cloud platforms |
381| --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
382| Available | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed) |
383| Available<sup>1</sup> | [Microsoft Foundry (hosted on Anthropic)](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
384 
3851. Hosted on Anthropic deployments only; the skill version download endpoint (`GET /v1/skills/{skill_id}/versions/{version}/content`) is not supported on Foundry.
386 
387#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
388 
389* Availability: Available
390* Usage: Attach skills in the agent’s `skills` array, or load them from a GitHub repository mounted on the session.
391 
392| Status | Cloud platforms |
393| --------- | ----------------------- |
394| Available | All supported platforms |
395 
396### Data handling
397 
398[Data handling overview](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility)
399 
400| Item | Zero data retention | HIPAA |
401| ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------ |
402| Status | Not eligible | Not eligible |
403| Details | Skill data retained according to standard policy. [Learn more](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview#data-retention) | — |
404 
405Applicable endpoints:
406 
407* `/v1/skills`
408* `/v1/messages` with `skills`
339409 
Feedback