The main file of a Claude Agent Skill. It starts with YAML frontmatter holding a name and a description, followed by Markdown instructions. The skill folder can also hold scripts and reference files that SKILL.md points to. Claude Code, the Claude apps, and the Claude API can all load skills.

Why isn't my Claude skill triggering?

Usually the description. Claude sees only the name and description until it decides to load the skill, so a description like "Helps with data" gives it nothing to match. Say what the skill does and when to use it, with the phrases and file types users actually mention. The reviewer rewrites the description line for you.

How long should a SKILL.md be?

Keep the body under about 500 lines. Move API references, schemas, and long examples into separate files in the skill folder and link them by relative path, so Claude reads them only when a task needs them.

Does it check the scripts in my skill folder?

No. It reviews the SKILL.md text you paste. It checks that scripts are referenced by path with instructions for running them, not pasted inline, but it does not read or run the scripts.

SKILL.md Reviewer

A Claude Agent Skill is a folder with a SKILL.md file. Claude loads only the name and description from its YAML frontmatter until the skill triggers, so a vague description means the skill never runs, and a bloated body wastes context when it does. Paste your SKILL.md and get a numbered audit: a valid kebab-case name, a description that says what the skill does and when to use it with concrete trigger phrases, imperative steps instead of narration, long reference material moved into separate files referenced by path, concrete examples, scripts referenced by path, and a body under about 500 lines. The review ends with a rewritten description: line and 1-2 rewritten sections. For always-loaded project instructions, use the CLAUDE.md Reviewer. For the cross-agent instruction file, use the AGENTS.md Reviewer.

AI-powered. Paste a Claude Agent Skill's SKILL.md and get a numbered audit of the frontmatter, the trigger description, and the body, plus a rewritten description line. No login. Daily-capped to stay free.

Try an example SKILL.md

Paste your SKILL.md

0 / 20,000 chars

Review & suggestions

Numbered, specific suggestions will appear here after you click Review.

Review a CLAUDE.mdAlways-loaded project instructions Review an AGENTS.mdCodex, Cursor, Copilot, Jules Optimize a promptSystem prompts and task prompts

What gets reviewed

• Frontmatter: kebab-case name and a description
• Description says what it does and when to trigger
• Imperative instructions, not narration
• Long reference moved to separate files
• Concrete steps, commands, and examples
• Scripts referenced by path; body under ~500 lines

Inputs to AI tools may be used to improve MarkdownMe. Data controls

Was this rewrite usable?

Get new tools by email

We add tools most weeks. Give an email address and we send you the new ones, plus short notes on how to use them. No more than one email a week. Unsubscribe with one click.

Example Input and Output

A skill whose description never triggers

SKILL.md

---
name: Data Helper
description: Helps with data.
---

# Data Helper

This skill makes working with data easier. Be helpful and accurate.

Audit

1. Invalid name. `Data Helper` has a space and capitals. Use kebab-case: `name: data-helper`.
2. Description gives Claude nothing to match. It is the only text loaded before the skill triggers, and it says neither what the skill does nor when to use it.
3. Narration, not instructions. "This skill makes working with data easier" tells the agent nothing to do. Replace it with numbered steps.
4. Vague rule. "Be helpful and accurate" changes no behavior. Delete it.

Rewrite Suggestions:
description: Cleans and summarizes CSV and Excel files. Use when the user uploads a .csv or .xlsx, asks to clean a spreadsheet, or wants summary statistics.

The rewritten description line comes first because it decides whether the skill runs at all.

How to Use SKILL.md Reviewer

Open the SKILL.md Reviewer
Paste your SKILL.md, frontmatter included, or pick an example
Run the AI review
Replace your description: line with the rewritten one
Apply the numbered fixes and move long reference material into separate files

Frequently Asked Questions

What is a SKILL.md?: The main file of a Claude Agent Skill. It starts with YAML frontmatter holding a name and a description, followed by Markdown instructions. The skill folder can also hold scripts and reference files that SKILL.md points to. Claude Code, the Claude apps, and the Claude API can all load skills.
Why isn't my Claude skill triggering?: Usually the description. Claude sees only the name and description until it decides to load the skill, so a description like "Helps with data" gives it nothing to match. Say what the skill does and when to use it, with the phrases and file types users actually mention. The reviewer rewrites the description line for you.
How long should a SKILL.md be?: Keep the body under about 500 lines. Move API references, schemas, and long examples into separate files in the skill folder and link them by relative path, so Claude reads them only when a task needs them.
Does it check the scripts in my skill folder?: No. It reviews the SKILL.md text you paste. It checks that scripts are referenced by path with instructions for running them, not pasted inline, but it does not read or run the scripts.

Claude Code tools

One CLAUDE.md, reviewed, generated, converted, and costed. Start at the hub for the guides.

CLAUDE.md reviewer — A numbered audit of an existing CLAUDE.md: vague rules, missing commands, token waste.
CLAUDE.md generator — Create a CLAUDE.md from your stack, commands, and conventions.
CLAUDE.md to AGENTS.md converter — The same instructions for Codex, Cursor, Copilot, and Windsurf.
AGENTS.md reviewer — The same audit for the AGENTS.md that Codex, Cursor, and Copilot read.
All Claude Code tools — The hub: every CLAUDE.md tool and guide on one page.

Related Tools

CLAUDE.md Reviewer

Paste your existing CLAUDE.md and get specific, numbered suggestions for vague rules, missing commands, repo boundaries, and token waste.

AGENTS.md Reviewer

Paste your AGENTS.md and get numbered fixes for missing commands, monorepo scoping, PR rules, agent boundaries, vague rules, and token bloat.

AI Prompt Optimizer (Rewrites Your Prompt)

Paste a rough prompt and get a structured, production-grade rewrite — Role, Context, Task, Constraints, Output Format, and Examples — tuned to best practices from Anthropic, OpenAI, and Google. AI-powered.

CLAUDE.md Converter

Convert agent configs between CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md, and .windsurfrules. One file, every format.

About SKILL.md Reviewer

Paste a Claude Agent Skill's SKILL.md and get numbered fixes for the frontmatter, the trigger description, the instructions, and the file layout. This AI-backed tool sends your input to MarkdownMe's capped AI endpoint to generate the result. You choose whether we keep it to improve the tools. See the privacy page. No account is required. MarkdownMe provides free, fast, and reliable Markdown tools for developers, writers, and anyone who works with Markdown.