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, token-efficient skill body that assumes Claude's competence and routes detail to verified one-level-deep references. It pairs a sequenced workflow with explicit failure modes and validation checkpoints, with only minor inline-command gaps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and sectioned into terse bullet lists with no padding or explanation of concepts Claude already knows; nearly every line is decision-relevant guidance. | 5 / 5 |
Actionability | Gives concrete, executable direction (resolve by id/name/prompt/TOML, prefer heartbeats for short delays, use suggested create/update for worktree automations) but lacks literal tool-call command shapes inline, deferring those to references. | 4 / 5 |
Workflow Clarity | The Workflow section sequences resolve-existing, map-kind, preflight, validate steps, with a dedicated Failure Mode section and explicit 'fail fast / stop at first failed gate' validation checkpoints for destructive automation operations. | 5 / 5 |
Progressive Disclosure | SKILL.md is an overview with a dedicated Progressive Disclosure section pointing one level deep to real bundle files (contract.yaml, tool-examples.md, evals.yaml, task-profile.json), all verified present, plus a clearly signaled legacy path. | 5 / 5 |
Total | 19 / 20 Passed |