Measure

Name: Measure
Author: benmarte

ASecurity

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.

5 stars
0 votes
0 copies
4 views
Added May 26, 2026

code-quality

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add benmarte/autoimprove --skill measure --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Measure?

Add the live security badge to your README. It updates with every re-scan.

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/benmarte-measure/badge)](https://www.skillsdirectory.com/skills/benmarte-measure)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
description: 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.
---

# 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]
```

6. If any command fails unexpectedly (not just returns errors but actually crashes), report the raw output so the user can debug their tooling.