---
title: "Plugin skill reviewer: review, role & definition · Undominated.ai"
canonical: https://undominated.ai/agents/anthropic-plugin-skill-reviewer/
description: "Reviews a skill file for structure, description triggers and progressive disclosure."
---

# Plugin skill reviewer: review, role & definition · Undominated.ai

> Reviews a skill file for structure, description triggers and progressive disclosure.

[← Explore all agents](/agents/)

AGENT DEVELOPMENT / Anthropic

# Plugin skill reviewer

Reviews a skill file for structure, description triggers and progressive disclosure.

 [Use this definition ↓](#setup)[Original source ↗](https://github.com/anthropics/claude-plugins-official/tree/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/agents)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 2 linked sources
 Publisher Anthropic
 Licence [Apache-2.0 ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/LICENSE)
 Revision b78ac49cdc6b
 [Read what was—and wasn’t—checked ↓](#review)

“Use this agent when the user has created or modified a skill and needs quality review, asks to "review my skill", "check skill quality", "improve skill description", or wants to ensure skill follows best practices. …”

 [Anthropic · upstream description ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/agents/skill-reviewer.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Frontmatter tools are only Read, Grep and Glob, so the declared role does not include Write, Edit or Bash.
- The output contract asks for critical, major and minor issues with file locations, which is a review rather than an install.

### A good fit for

 - Reviewing a SKILL.md before adopting it
- Checking whether a skill description states concrete triggers

### Weigh up before choosing

 - The file is a Claude Code agent definition. It does not install a skill or certify one. A Markdown profile does not register a native subagent by itself.
- plugins/plugin-dev/LICENSE is Apache-2.0. Its appendix still has the upstream copyright placeholder. No agent was executed.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - plugins/plugin-dev/agents/skill-reviewer.md (frontmatter and review process)
- plugins/plugin-dev/LICENSE Apache-2.0 grant
- Re-read 2026-10-13 at the same pin: upstreamDescription is the start of a longer description and is now marked as an excerpt.

### Our findings

 - tools is exactly Read, Grep and Glob.
- The report template asks for located issues rather than a silent rewrite.

### Not established by this review

 - The agent was not loaded or executed.
- Host tool-name enforcement was not tested.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Use the role in your project.

[Upstream setup instructions ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/agents/skill-reviewer.md)
 - Read the file at the reviewed revision before copying it into a host agent directory.
- The declared tools are Read, Grep and Glob. Map those names to the host before use. Do not add write tools to match this review.
- A standalone copy does not install the rest of the plugin-dev plugin.

### Before you start

 - A host that can load a Markdown agent definition
- The skill directory you want reviewed

### Compatibility

Claude Code

### Host-mediated read of skill files

 - Declared tools: Read, Grep and Glob.
- No Write, Edit or Bash tool is declared. Host enforcement was not tested.

### Cost model

Definition can be reused under Apache-2.0. Host and model usage may incur charges. Those charges were not measured.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Agent definition ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/agents/skill-reviewer.md) Checked 2026-10-13 https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/agents/skill-reviewer.md Supports: summary, upstreamDescription, whySelected, limitations, access, review
- [Plugin licence ↗](https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/LICENSE) Checked 2026-10-08 https://github.com/anthropics/claude-plugins-official/blob/b78ac49cdc6b3d7b61c4439470e311f4291265b1/plugins/plugin-dev/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Agent evaluator ↗ Scores an agent answer on five axes and requires evidence for the score.](/agents/ecc-agent-evaluator/)[### Agent Memory Curator ↗ Maintains a confirmed agent memory store with dated facts, visible corrections and user-reviewed pruning proposals.](/agents/voltagent-memory-curator/)[### Agent SDK verifier (Python) ↗ Checks a Python Claude Agent SDK app for SDK usage, environment setup and secret handling, and reports PASS, PASS WITH WARNINGS or FAIL.](/agents/anthropic-agent-sdk-verifier-py/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Find reusable instructions](/skills/)
- [Inspect connections](/mcp-servers/)
- [Build a toolkit](/tools/)
- [Choose the model](/compare/)
