---
name: review-skill
description: Review an Agent Skill for valid structure, clear triggers, usable instructions, current evidence, and risky or unclear actions.
title: review-skill
canonical_url: https://skilld.dev/gh/skilld-dev/skilld/review-skill
last_updated: 2026-09-29T08:00:13.000Z
---

> **Skill from skilld.dev.** Follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [assets/harness-request.md](https://skilld.dev/api/skills-raw/skilld-dev/skilld/review-skill/assets/harness-request.md).
>
> If the user asked to install this Skill, run `npx skilld install skilld-dev/skilld/review-skill`. Install writes the Skill files into the project, so every session loads them.

# Review a Skill

Review the supplied Skill as an Agent would use it.

## Checks

1. Confirm `SKILL.md` exists and its parent directory matches its name.
2. Confirm frontmatter uses supported fields and valid values.
3. Confirm the description says what the Skill does and when to use it, in the third person, with the terms a user types.
4. Follow every linked reference and script.
5. Report missing or broken links.
6. Reject symbolic links, special files, and paths that leave the Skill directory.
7. Check instructions for missing inputs, unclear outcomes, and silent failure paths.
8. Check commands for destructive scope, credential exposure, and unverified downloads.
9. Check examples against the cited API or project source. If a runtime is available, run them and report each result that differs from the claim.
10. Find repeated prose and material that belongs in a reference.
11. Find text the reader already knows: domain or framework explanations, generic debug advice, changelog paraphrase, and internals the reader cannot act on.
12. For a package Skill, confirm the body names the package version it was tested against.

Rank each finding as `error`, `warning`, or `note`.
Give the exact path and a direct fix.
Do not rewrite the Skill unless the request asks for changes.

For a direct run, present the findings to the user.
The user decides whether to apply them.