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 highly actionable, well-structured instruction skill with executable gh commands and concrete output templates. The chief gaps are the absence of an explicit error-recovery feedback loop in the workflow and some inlined material that could be split into reference files.
Suggestions
Add an explicit validate-fix-retry loop (e.g., on a failed gh query or auth warning, diagnose and retry once before skipping) to raise workflow_clarity.
Move the detailed gh command catalog and/or the three output-shape templates into reference files referenced one level deep from SKILL.md to improve progressive_disclosure.
Tighten the brag-candidate criteria and guardrails lists to remove phrasing that restates earlier instructions, improving conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes Claude's competence (no 'what is GitHub/Slack' padding), using compact templates and a YAML block, though the brag-candidate criteria and guardrails could be tightened slightly. | 4 / 5 |
Actionability | Provides fully executable, copy-paste-ready gh commands with complete --json field lists, concrete tools.yaml defaults, exact cross-reference rules, and precise output-shape templates covering the common cases. | 5 / 5 |
Workflow Clarity | An 8-step sequenced workflow with real checkpoints (auth/CLI check, warn-and-skip, stop-when-no-evidence, mark 'claimed, not found'), but it lacks an explicit validate-fix-retry feedback loop for the batch collection. | 4 / 5 |
Progressive Disclosure | Well-organized into clearly headed sections with no nested references, but at ~180 lines with the full gh-command catalog and all output templates inlined, some material could be externalized into one-level-deep reference files. | 4 / 5 |
Total | 17 / 20 Passed |