Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is concise and well-organized with a useful content map, checklist, and anti-patterns, but it references per-topic files and an overview that do not exist in the bundle and lacks explicit validation checkpoints in its workflow.
Suggestions
Add the referenced reference files (api-style.md, rest.md, response.md, etc.) to ./references/, or remove the content-map rows that have no backing file.
Add an explicit validation/feedback loop to the decision workflow — e.g. run `python scripts/api_validator.py` and iterate until critical issues resolve before proceeding.
Tighten the script table and 'When to Use'/'Limitations' sections, which currently read as generic boilerplate rather than API-specific guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and table-driven, assuming Claude's competence — it avoids explaining what REST or GraphQL are and lets every section earn its place via a content map, checklist, and anti-patterns. | 3 / 3 |
Actionability | It points to a real executable script (`python scripts/api_validator.py <project_path>`) and gives concrete DO/DON'T rules, but the core design guidance lives in referenced files that are not present, so on-the-page instruction is incomplete. | 2 / 3 |
Workflow Clarity | The decision checklist sequences pre-design steps, but there are no explicit validation checkpoints or feedback loops (validate -> fix -> retry) for the destructive/batch operations the validator script targets. | 2 / 3 |
Progressive Disclosure | A clear content map signals one-level-deep references to per-topic files, but none of the listed reference .md files actually exist in the bundle, so the promised progressive structure is not realized. | 2 / 3 |
Total | 9 / 12 Passed |