Content
86%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 body is an exemplary lean, instruction-only skill: a clear three-phase workflow with concrete commands, explicit stop conditions, and well-signaled one-level-deep references. The only meaningful gap is that verification and error-recovery specifics live in external documents rather than inline, which slightly limits standalone actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~28-line body is lean and dense: every sentence is operative instruction or policy, with no explanation of concepts Claude already knows and no padded sections. It consistently assumes the model's competence. | 5 / 5 |
Actionability | Provides a copy-paste-ready command ('gh issue view <id> --json number,title,body,state,labels,comments,assignees'), exact comment markers ('> **🏗️ build-plan**'), 'Closes #<id>' convention, and signed-off Conventional Commit guidance. Not 5 because several steps defer concrete specifics to external docs (CONTRIBUTING.md sections, sibling skills) rather than stating them inline. | 4 / 5 |
Workflow Clarity | Clear Inspect → Plan → Implement sequence with explicit checkpoints and stop conditions ('ask the operator before proceeding', 'If blocked, preserve local work and report the reason', 'stop after the plan is available for review'). Below 5 because error-recovery loops when verification or checks fail are deferred to CONTRIBUTING.md rather than stated inline. | 4 / 5 |
Progressive Disclosure | Under 50 lines with well-organized sections and no bundle files to split; external references (CONTRIBUTING.md sections, sibling skills, CRYPTO.md) are clearly signaled by name and only one level deep. Meets the simple-skill exception for a full score. | 5 / 5 |
Total | 18 / 20 Passed |