Content
71%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 body is well-structured, actionable, and concise for a domain-rich advisory skill, with clear workflows and gating checkpoints. Its main weakness is that every referenced reference file and script is missing from the bundle, so the progressive-disclosure navigation is broken in practice.
Suggestions
Bundle the referenced files (references/contracts_playbook.md, references/ip_and_regulatory.md, references/term_sheet_decoder.md) and scripts (scripts/contract_risk_scanner.py, scripts/term_sheet_analyzer.py) so the signaled references actually resolve.
Tighten the Keywords block, which largely duplicates the description's trigger terms, to reclaim tokens without losing discoverability.
Add an explicit validate/retry checkpoint to the analysis workflows (e.g., confirm the term-sheet JSON parsed before scoring, re-run the scanner after counter-proposals) to lift workflow clarity toward level-5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and domain-specific rather than padded with basics Claude already knows, but the long Keywords block largely duplicates the description and some parenthetical asides could be trimmed, fitting level-4 "efficient; minor instances of over-explanation" rather than the lean level-5. | 4 / 5 |
Actionability | Provides copy-paste-ready commands ("python scripts/contract_risk_scanner.py path/to/contract.txt"), concrete defaults ("1x non-participating is standard"), and a detailed trigger table, but defers schema details to "term_sheet_analyzer.py --help" and the referenced scripts are not bundled, leaving minor gaps that keep it at level-4 rather than fully executable level-5. | 4 / 5 |
Workflow Clarity | Four numbered workflows have clear sequences with gating checkpoints ("Always have a securities/venture attorney review before signing", "/cs:freeze 30"), matching level-4's "clear sequence with most checkpoints present"; it is not level-5 because the analysis workflows lack explicit validate-then-fix feedback loops. | 4 / 5 |
Progressive Disclosure | Section structure is clear and references are signaled one level deep ("See references/ip_and_regulatory.md"), but the referenced files (references/*.md, scripts/*.py) do not exist in the bundle, so the progressive disclosure does not actually navigate — the dangling references and inline detail pull it to level-3 rather than level-4's "minor organization gaps." | 3 / 5 |
Total | 15 / 20 Passed |