[agents](https://carteblanche.com/index.md?kind=agent) / [code](https://carteblanche.com/index.md?category=code) # skill-reviewer what it does 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. Trigger proactively after skill creation. Examples: \ Context: User just created a new skill user: "I've created a PDF processing skill" assistant: "Great! Let me review the skill quality." \ Skill created, proactively trigger skill-reviewer to ensure it follows best practices. \ assistant: "I'll use the skill-reviewer agent to review the skill." \ \ Context: User requests skill review user: "Review my skill and tell me how to improve it" assistant: "I'll use the skill-reviewer agent to analyze the skill quality." \ Explicit skill review request triggers the agent. \ \ \ Context: User modified skill description user: "I updated the skill description, does it look good?" assistant: "I'll use the skill-reviewer agent to review the changes." \ Skill description modified, review for triggering effectiveness. \ \ tools it asks for Reads files by anthropics · version 1 · license Apache-2.0 We imported this agent from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/skill-reviewer) Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/anthropics/claude-plugins-official/blob/0412be76f50ab4f4f8abff3753efa9269fbbca5b/plugins/plugin-dev/agents/skill-reviewer.md) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/skill-reviewer/download) ## Compare the answers Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1 Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself. [Compare the answers](https://carteblanche.com/skills/skill-reviewer/compare) ## The models 2 models Claude Sonnet 5.5 made by Anthropic claude-sonnet-5-5 · revision not reported by the provider 1 try per case · tested 7 Nov 2026 GPT-6.1 Sol made by OpenAI gpt-6.1-sol · revision not reported by the provider 1 try per case · tested 7 Nov 2026 ## The tasks written by Carte Blanche **example-1** “Can you review my skill? Here's the SKILL.md frontmatter and start of the body: --- name: csv-cleaner description: Helps with CSV files. --- # CSV Cleaner You should use this when working with CSVs. I am going to show you how to clean them. First, you load the file with pandas, then you drop duplicates, then you fix the date columns. Use pandas for everything. The description feels vague to me. How can I improve it so it triggers properly?” **example-2** “I just updated the description of my PDF processing skill and want to know if it looks good for triggering. New description: 'Use this skill when the user wants to extract text, merge, split, or fill forms in PDF files. Triggers on phrases like "extract text from PDF", "merge these PDFs", "split PDF pages", "fill out this PDF form".' The body is about 400 lines in one SKILL.md with no references folder. Please check quality and tell me what to fix.” ## Install Download the .zip and unzip it. Put `skill-reviewer.md` here: Claude Code · `~/.claude/agents/` · Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others. Cursor · `~/.cursor/agents/` · Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for. Codex · Codex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there. Keep its license file beside it, as `skill-reviewer.LICENSE`: a name that doesn’t end in .md, since every .md file there is read as an agent. Then start a new session and ask for it by name. Folders checked 6 November 2026. Or [install from your agent](https://carteblanche.com/connect.md): ask it to install `skill-reviewer` from Carte Blanche. ## Badge for your README Carte Blanche: Verified Paste this into the agent’s README. It links to this page, and shows how the listing stands whenever it’s loaded. ``` [![Carte Blanche](https://carteblanche.com/badge/skill-reviewer.svg)](https://carteblanche.com/skills/skill-reviewer) ``` ## About this test - **tested**: 7 Nov 2026 - **version tested**: v1 - **cases**: 2 - **tries per case**: 1 try per case - **run without the agent**: yes - **cases written by**: Carte Blanche - **size**: 4819 characters What this shows, and what it doesn’t How 2 models answered these 2 requests, with and without the agent. It says nothing about other models, and it doesn’t limit what your own agent can do. The answers were written without tools: the agent’s instructions were the system prompt, and it read no file and ran nothing. [How we test](https://carteblanche.com/how-it-works.md)