Content
77%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is lean, actionable, and well-sequenced with a strong validation checklist, but its usefulness is undercut by references to a missing `docs/` directory. Fixing those reference paths would lift both actionability and progressive disclosure.
Suggestions
Restore or create the referenced docs/ files (interpretation-guide.md, report-templates.md, alphagenome-api.md, and the examples/ subfolders) so the in-body links resolve.
Add the existing scripts/generate_ontology_mapping.py to the Script Reference table, since it is present but undocumented.
Verify every markdown link target against the bundle and drop or redirect any path that has no corresponding file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense but high-signal: hard-won gotchas (column names, strand errors, ontology_curie KeyErrors) and executable patterns rather than generic concept explanations Claude already knows. It assumes competence and avoids padding. | 3 / 3 |
Actionability | Provides executable `uv run` commands and complete code blocks, but several in-body references point to a `docs/` tree (e.g. docs/interpretation-guide.md, docs/report-templates.md, docs/examples/) that is not present in the bundle, so key guidance is not actually reachable as written. | 2 / 3 |
Workflow Clarity | The Workflow Checklist is an explicit sequenced list with MANDATORY markers and a Step 7 self-critique that re-reads report.md to verify links and claims, giving a clear validate-then-fix feedback loop. | 3 / 3 |
Progressive Disclosure | Structure is well organized with one-level references, but the frequently-cited `docs/` paths do not exist in the bundle while scripts do, so navigation is partly broken and references are not verified against the actual file tree. | 2 / 3 |
Total | 10 / 12 Passed |