Content
100%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.
An exemplar operational skill body: concise, fully actionable, with a clearly sequenced workflow that embeds validation/readback checkpoints and routes detail to one-level-deep reference files. It balances safety guidance with token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean, directive operational prose that assumes Claude's competence — it never explains concepts Claude already knows (no 'what is a PR/GitHub') and every line (operating contract, readback table, reporting states) earns its place. | 5 / 5 |
Actionability | Copy-paste-ready commands throughout — `gh auth status --hostname HOST`, `gh repo view ... --json ...`, the quick-reference block, and a concrete readback evidence table mapping each mutation to required acceptance proof. | 5 / 5 |
Workflow Clarity | A clear 7-step universal operating contract (Classify → Bind → Preview → Choose interface → Mutate once → Verify readback → Report) with explicit validation checkpoints, bounded polling, feedback loops, and a four-state honest reporting checklist for destructive/batch operations. | 5 / 5 |
Progressive Disclosure | SKILL.md is a well-signaled overview with a task→reference routing table linking one level deep to 7 real reference files (all present in ./references/); bulk detail is split out and navigation is easy. | 5 / 5 |
Total | 20 / 20 Passed |