agentsclimarketplace
Sign in

Measure

Skill benmarte/autoimprove/skills/measure

Run the full measurement suite defined in .claude/autoimprove/config.md and report the current codebase quality score (0-100). Use this to check your baseline before running the improve loop, or to spot-check at any time.From its SKILL.md

Install
npx -y skills add benmarte/autoimprove --skill measure

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.2 KB, 244 tokens by cl100k_base, as published. Nobody here has run it

Measure Skill

Run the project's quality measurement suite and report the composite score.

Steps

  1. Read .claude/autoimprove/config.md. If it doesn't exist, say: "Run /autoimprove:setup first."

  2. Run each command defined in the config's measurement sections, in order:

    • Type check / compile
    • Build
    • Tests
    • Lint

  3. Parse results using the error patterns and success patterns defined in the config.

  4. Calculate composite score using the weights in the config.

  5. Report:

📊 Codebase Quality Score: XX/100

  [Type check label]:  X errors  → XX/40 pts
  [Build label]:       ✅/❌      → XX/20 pts
  [Test label]:        X/X pass  → XX/30 pts
  [Lint label]:        X errors  → XX/10 pts

💡 Lowest area: [label] — [one specific actionable suggestion]
  1. If any command fails unexpectedly (not just returns errors but actually crashes), report the raw output so the user can debug their tooling.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.