agentleFS
Sign inStart free
mrinalwadhwamrinalwadhwa/fluent/skills/review-skills/SKILL.md

review-skills

Skill125 starsChanged 13 days agoApache-2.0View on GitHub

Reviews Agent Skills. Use when auditing skills in a codebase, checking a new or edited SKILL.md, or verifying that a skill follows the Agent Skills spec.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. base44/skills★ 92same name
    2. g-bastianelli/nuthouse★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When an agent picks among skills based on their descriptions, an overlap can cause it to pick the wrong one.

    line 16
  2. Very specific:

    Read references/skills.md for skill-writing standards and references/documentation.md for writing quality.

    line 20
  3. Very specific:

    Read the SKILL.md and files under references/, scripts/, and assets/.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Purpose

Decide whether each skill under review is fit to ship. Identify improvements that would make a skill more discoverable, more efficient, or more likely to succeed at its purpose.

Scope

The invoking layer decides which skills to review: the changed skills for a diff-scoped review, or all skills for a full-codebase audit.

For each skill in scope, assess it as a whole: the SKILL.md, its supporting files under references/, scripts/, and assets/, and how the skill is invoked in its codebase. Skills can be invoked by name from a prompt template, through a hook, or by agent auto-activation.

When an agent picks among skills based on their descriptions, an overlap can cause it to pick the wrong one. Compare each in-scope skill's description against sibling skills invoked the same way, including siblings that aren't part of this review.

Method

  1. Read references/skills.md for skill-writing standards and references/documentation.md for writing quality.
  2. For each skill under review:
    • Read the SKILL.md and files under references/, scripts/, and assets/.
    • Understand how the skill is invoked in its codebase — by name from a prompt template, through a hook, or by agent auto-activation.
    • Compare descriptions against siblings invoked the same way.
    • Identify improvements using the standards in references/skills.md (skill-writing) and references/documentation.md (writing quality).
  3. For each improvement, decide if it blocks shipping. Missing or invalid frontmatter, broken references, or instructions that contradict the invoking layer's specifications (output format, error handling) typically block. Lighter versions — a vague but present description, load triggers that could be sharper, duplication that's aligned rather than conflicting — and style issues typically don't.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free