Content
78%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 appropriately minimal body for a simple router-style skill, with excellent conciseness and a clean one-level reference. Actionability and workflow clarity are slightly capped because the body delegates all execution and validation detail to the referenced file.
Suggestions
Add a one-line validation reminder in the body (e.g. 'Run `pnpm validate:agent-skills` after any skill-tree change') so destructive/batch operations have an explicit checkpoint before completion.
Surface one or two concrete next actions inline (such as the canonical tree path or the symlink rule) rather than routing all actionable detail to references/skill-format.md.
Clarify the trigger phrasing in the body to echo the description's 'Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work' so routing and scope stay aligned.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Three lean lines with zero padding; it assumes Claude's competence and every token earns its place, consistent with the simple-skill exception. | 5 / 5 |
Actionability | The body gives one concrete directive ('Read `references/skill-format.md` before changing skill folders, validation, or compatibility mirrors') but defers essentially all executable detail to the reference, leaving the body itself incomplete. | 3 / 5 |
Workflow Clarity | The single action is unambiguous (qualifying for the simple-skill exception), but because skill-tree reorganization can be a batch/destructive operation the body surfaces no validation checkpoint, leaving a minor gap. | 4 / 5 |
Progressive Disclosure | A clear overview points to one well-signaled, one-level-deep reference (references/skill-format.md, verified to exist) with no nested reference-chasing and easy navigation. | 5 / 5 |
Total | 17 / 20 Passed |