agentleFS
Sign inStart free
peopleforresterpeopleforrester/claude-dotfiles/skills/workflow/eval/SKILL.md

eval

Skill3 starsChanged 7 months agoMITView on GitHub

Evaluate code or implementation against specific criteria

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run tests and capture results

    line 29
  2. Distinctive:

    Run linters and type checkers

    line 30
  3. Very specific:

    When $ARGUMENTS specifies custom criteria, use those instead of defaults.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “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

/eval

Evaluate the current implementation against defined criteria, standards, or a rubric. Produces a structured assessment with scores.

Arguments

  • $ARGUMENTS — Criteria to evaluate against, or "default" for standard quality gate

Default Criteria

CategoryWeightChecks
Correctness30%Tests pass, edge cases handled, no regressions
Security20%OWASP checks, input validation, secrets management
Performance15%No N+1 queries, efficient algorithms, caching
Maintainability15%Readability, modularity, naming clarity
Testing10%Coverage ≥80%, edge cases, test quality
Documentation10%API docs current, README accurate, comments useful

Process

1. Gather Evidence

For each category, collect evidence:

  • Run tests and capture results
  • Run linters and type checkers
  • Review code changes
  • Check documentation accuracy

2. Score Each Category

Rate each category: 1 (Poor) to 5 (Excellent)

3. Generate Report

## Evaluation Report

### Overall Score: X.X / 5.0

| Category | Score | Weight | Weighted |
|----------|-------|--------|----------|
| Correctness | 4/5 | 30% | 1.20 |
| Security | 3/5 | 20% | 0.60 |
| Performance | 4/5 | 15% | 0.60 |
| Maintainability | 5/5 | 15% | 0.75 |
| Testing | 3/5 | 10% | 0.30 |
| Documentation | 4/5 | 10% | 0.40 |
| **Total** | | | **3.85** |

### Detailed Findings
[Per-category evidence and recommendations]

### Verdict
**SHIP IT** (≥4.0) | **IMPROVE** (3.0-3.9) | **REWORK** (<3.0)

Custom Criteria

When $ARGUMENTS specifies custom criteria, use those instead of defaults. Format each criterion as: name: description (weight%).

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.

Reviews can't be read right now.

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