Example Skill
Template example showing the SKILL.md structure — replace this description with one that names YOUR skill's concrete trigger condition ("Triggers when the user asks how to X, Y, Z"). Keep it ≤200 characters for best intent-matching.
Install
$ agentstack add skill-xiaolai-anthropic-docs-example ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-xiaolai-anthropic-docs-example) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Example Skill
This is a minimal SKILL.md showing the required structure.
What every skill needs
- YAML frontmatter with
nameanddescription.descriptionis what Claude reads at intent-match time, so make it specific and name the trigger condition. - A short body that Claude reads on activation. Keep it ≤2,000 tokens for the single-file case.
When the skill is bigger than 2,000 tokens
Split into a router + per-surface deep references, and load them on demand:
---
name: my-skill
description: Router for my-skill. Use when the user asks about X, Y, or Z.
---
# My Skill — Router
| Surface | Read when… |
|---|---|
| [`SKILL-foo.md`](SKILL-foo.md) | User asks about Foo |
| [`SKILL-bar.md`](SKILL-bar.md) | User asks about Bar |The router stays small (≤100 lines), and Claude reads the surface files only when the dispatch table maps to them. This repo's own SKILL.md is an example of the pattern.
Cross-reference
If a fact lives in another skill (e.g., a sibling deep reference), link to it with a markdown link rather than duplicating.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: xiaolai
- Source: xiaolai/anthropic-docs
- License: MIT
- Homepage: https://github.com/xiaolai/autoupdated-anthropic-documentation-knowledge
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.