Content
92%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 well-structured, highly actionable triage skill with explicit sequencing and validation checkpoints for destructive/batch operations, and appropriately split one-level references. Minor rationale prose is the only thing keeping conciseness from full marks.
Suggestions
Tighten the justifying prose in Stage 2 and Stage 5 (e.g. 'Insufficient issues are the main reason contributor time is wasted, so act on it') to instruction-only phrasing that earns fewer tokens.
Consider moving the 'Run scope' parameter table and slice-sizing detail into a reference file to keep SKILL.md a leaner overview of the seven stages.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Largely efficient and assumes Claude's competence — it never explains concepts Claude already knows — but includes some rationale prose ('Insufficient issues are the main reason contributor time is wasted', 'costs tokens, adds public noise, and helps no one') that could be trimmed. | 4 / 5 |
Actionability | Provides copy-paste-ready commands (`gh issue list` with full jq filters, `gh issue view`, `gh issue comment --body-file`) plus findings→action tables and exact label names, covering the common cases concretely. | 5 / 5 |
Workflow Clarity | A 7-stage process is laid out in a sequencing table with explicit validation checkpoints — re-read before editing, one issue at a time, evidence-or-silence, the regression 'Cannot tell → compute then judge' row — and feedback loops for the destructive/batch label-removal operations. | 5 / 5 |
Progressive Disclosure | SKILL.md holds the core workflow while the policy and formatting recipe are split into one-level-deep, clearly signaled references ([references/good-student-issue.md], [references/body-formatting.md]), both of which exist on disk, making navigation easy. | 5 / 5 |
Total | 19 / 20 Passed |