Content
63%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is actionable with a clear, validated workflow and real commands, but it is longer than necessary and duplicates template material that already lives in the references file. Progressive disclosure is weakened by inlining templates instead of pointing to the existing reference.
Suggestions
Move the inlined Bug Fix and New Feature templates out of SKILL.md and link to references/pr-templates.md instead, since that file already contains them and more.
Tighten the Tag Safety and PETE sections to remove repeated phrasing and cut overall length.
Add explicit links to the bundle files (e.g. 'See references/pr-templates.md for all PR-type templates') so the reference is clearly signaled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and concrete, but the ~230 lines include redundant template material that also appears in references/pr-templates.md and verbose prose in the Tag Safety and PETE sections that could be tightened. | 3 / 5 |
Actionability | It provides concrete commands (gh issue view, gh pr edit, pbcopy), a documented script invocation with format flags, and executable example PR bodies with real tags; minor gaps remain in placeholder templates like #[issue]. | 4 / 5 |
Workflow Clarity | A clear five-step sequence is present with validation checkpoints (PETE Insufficient feedback before finalizing, and a self-scan for @: outside Validation Steps), but the steps are prose-heavy rather than crisp checklists, keeping it just below a 5. | 4 / 5 |
Progressive Disclosure | Bundle files exist (references/pr-templates.md, scripts/fetch-test-tags.sh), but PR templates are inlined in the body and largely duplicated in the reference file, and the body never links to references/pr-templates.md, so references are present but not clearly signaled and content that should be separate is inline. | 3 / 5 |
Total | 14 / 20 Passed |