Content
82%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.
A lean, highly actionable skill body with concrete gh commands, a clearly sequenced workflow, and built-in validation/dry-run safeguards for a batch GitHub-labeling operation. Minor room to tighten prose and make error-recovery loops explicit.
Suggestions
Tighten the explanatory prose around stale-claim detection to reduce token load while keeping the rule.
Add an explicit error-recovery feedback loop for step 5 (e.g., what to do if `gh issue edit` fails or the verification shows the label was not applied).
Consider moving the long include/exclude ownership lists into a reference file to keep the core workflow scannable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and largely purposeful with copy-paste gh commands and no concept padding, but a few explanatory sentences (e.g. the stale-claim reasoning) could be trimmed, fitting the efficient-but-minor-over-explanation score-4 anchor rather than the fully-lean score-5. | 4 / 5 |
Actionability | It provides fully executable, copy-paste-ready `gh` commands for every operation (auth, label list/create, issue view, issue edit, verification) covering the common cases, matching the score-5 anchor. | 5 / 5 |
Workflow Clarity | A clear numbered 1-5 sequence with explicit validation checkpoints (verify label exists, dry-run must not mutate, verify the label was applied), but the error-recovery feedback loop is only lightly sketched, so it fits score 4 rather than 5; the destructive/batch cap does not apply because verification steps are present. | 4 / 5 |
Progressive Disclosure | No bundle files exist and the skill is a single self-contained document with well-organized sections (Inputs, Classification, Workflow, Output) and no nested references, giving good structure that fits score 4; at ~60 lines it slightly exceeds the under-50-line simple-skill exception that would justify a 5. | 4 / 5 |
Total | 17 / 20 Passed |