Content
75%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 content is well-structured, actionable, and concise, with a clear workflow and appropriate externalization of terminology detail. Minor redundancy between the rules and mistakes sections and the absence of an explicit retry loop keep it just below top marks.
Suggestions
Fold the 'Common mistakes' items that merely restate 'Rules and conventions' into the rules, or keep only the forward-looking guidance to remove redundancy.
Add an explicit feedback loop in the Verify step, e.g. 'If the build fails, fix the reported links/errors and re-run the build before proceeding.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence with no concept-explanation padding, though the 'Common mistakes' section partially restates the 'Rules and conventions' section. | 4 / 5 |
Actionability | Provides concrete commands (git diff, pnpm build) and specific typography/terminology rules, with minor gaps where guidance defers to the external docs/AGENTS.md. | 4 / 5 |
Workflow Clarity | A clear four-step sequence includes an explicit Verify checkpoint, satisfying validation for this batch operation; it lacks a full validate-fix-retry feedback loop that would reach a 5. | 4 / 5 |
Progressive Disclosure | Well-organized sections with a single clearly signaled one-level reference (docs/AGENTS.md) for terminology and style detail; no bundle files exist that require splitting. | 4 / 5 |
Total | 16 / 20 Passed |