Content
65%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 content is highly actionable with a concrete workflow, clear change taxonomy, and a complete output template. It loses points for lacking an explicit verification step in the workflow and for keeping a large template inline rather than splitting it into a referenced file.
Suggestions
Add an explicit verification step before output generation, e.g. 'Verify every section from both documents appears in the comparison and that the change-count totals reconcile.'
Move the full CONTRACT-COMPARISON.md output template into a referenced template file (e.g. references/OUTPUT_TEMPLATE.md) and summarize its structure inline to reduce monolithic bulk.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean and free of basic-concept padding, but the role preamble ('You are an AI Legal Analyst...') and the large fully-embedded output template could be tightened. | 2 / 3 |
Actionability | Provides highly concrete, copy-paste-ready guidance: explicit change-type taxonomy, a dangerous-pattern checklist, and a complete markdown output template with exact instructions to quote source text. | 3 / 3 |
Workflow Clarity | Five steps are clearly sequenced, but there is no explicit validation or verification checkpoint (e.g., confirm every section was compared or that the change totals reconcile), so checkpoints are only implicit. | 2 / 3 |
Progressive Disclosure | A single well-organized file with no nested references, but it is monolithic with a large inline output template that could reasonably be split into a separate reference file. | 2 / 3 |
Total | 9 / 12 Passed |