Content
96%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 tightly written, highly actionable procedural skill with a clear validated workflow and strong command coverage. The only minor gap is progressive disclosure, where a couple of reference blocks (table format, signature examples) could optionally be externalized.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and command-driven throughout; it assumes Claude's competence (no explanation of gh or CI basics) and every section earns its tokens with domain-specific rules rather than filler. | 5 / 5 |
Actionability | Fully executable, copy-paste-ready `gh` commands cover every common entry path (PR given, run/job URL given, no context, rerun, tracker update) with appropriate placeholders. | 5 / 5 |
Workflow Clarity | Clear sequenced phases (Find → Classify → Signature → Update → Rerun → Report) with explicit validation ("Verify after editing") and error-recovery feedback loops (handle non-zero `gh run watch` after cancel). | 5 / 5 |
Progressive Disclosure | Well-organized with clear section headers and no nested references, and all content is appropriately inline for a procedural skill; sits just over the simple-skill 50-line threshold so does not quite reach the structure-only 5. | 4 / 5 |
Total | 19 / 20 Passed |