Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a lean, well-structured orchestration skill: it sequences a multi-step PR workflow with explicit validation and a Codex/CI feedback loop, keeps deprecation guidance in its own section, and gives concrete actionable instructions throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~40-line body assumes Claude's knowledge (no explanation of what a PR or CI is) and confines deprecation detail to a dedicated "Compatibility" section, so every token earns its place per the score-3 anchor. | 3 / 3 |
Actionability | Specific, actionable instructions dominate: "Confirm commits are signed off", "title follows the repository's semantic PR-title format", "Do not enable auto-merge", and named tools (`pull-request`, `pr-description`, `fix-pr-issues`); per the scoring notes, instruction-only skills are not penalized for lacking code when guidance is this concrete. | 3 / 3 |
Workflow Clarity | Six numbered steps give a clear sequence, step 3 is an explicit validation checkpoint, and step 6 defines a feedback loop ("If Codex or CI reports a blocker, use `fix-pr-issues`, push the fix, and restart `pr-review-loop`"), matching the score-3 anchor of clear sequence with validation and error recovery. | 3 / 3 |
Progressive Disclosure | Under 50 lines with no bundle references needed (only assets/icon.svg exists), the content is organized into clearly signaled Compatibility/Workflow/Report sections and points one level deep to peer skills, meeting the score-3 simple-skill allowance for well-organized sections. | 3 / 3 |
Total | 12 / 12 Passed |