score-quality

SkillDev tools

Score code migration quality based on coverage and correctness. Evaluates how well target code represents source functionality.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the score-quality skill

What this skill tells your AI

The instructions your AI receives, as published by openhands/extensions in plugins/migration-scoring/skills/score-quality/SKILL.md and read by ahel’s review.

Evaluate migration quality by scoring coverage and correctness for each source-target file pair.

Prerequisite: A migration mapping file must exist (see migration-mapping skill).

See references/scoring-criteria.md for the 1-5 scoring scales.

Output Format

Save scores as a JSON file:

{
  "source_file_1.cbl": {
    "coverage": 4,
    "correctness": 5,
    "justification": "All calculation logic migrated. Tax rounding matches COBOL behavior."
  }
}

Evaluation Process

For each source file and its mapped target files:

  1. Identify key functionality in the source

    • Business logic, data operations, control flow, error handling
  2. Check coverage in the target

    • Is each function/paragraph represented?
    • Are all data fields and code paths covered?
  3. Verify correctness

    • Do calculations produce the same results?
    • Are edge cases handled the same way?
  4. Document justification

    • Specific functionality present/missing
    • Known discrepancies

Incremental Scoring

If a score file already exists, update it with new scores rather than replacing it entirely.

Signals

GitHub stars
143
Forks
83
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
score-quality
Source
github.com/openhands/extensions