Content
82%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.
A lean, well-structured command skill with concrete usage examples and clearly signaled references to purpose-built scripts. The main gaps are interface consistency — examples use flags absent from the Usage spec and no script invocation syntax is given — and referenced file paths that do not resolve within the skill bundle itself.
Suggestions
Document the flags used in examples (--new-customers, --sm-spend, --contraction) in the Usage block, or remove them from the examples, so the accepted interface is unambiguous.
Add a one-line invocation example per subcommand showing how the CLI flags map to the underlying script (e.g. 'python scripts/metrics_calculator.py --mrr 80000 --customers 200 --churned 3').
Make referenced script and SKILL.md paths resolve within the skill bundle (e.g. scripts/metrics_calculator.py relative to the skill directory) instead of repo-absolute paths.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~37-line body is lean and assumes Claude's competence: no concept explanations, no padding, and every section (Usage, Examples, Scripts, Skill Reference, Related Commands) earns its place. This matches the anchor 'Lean and efficient; assumes Claude's competence; every token earns its place' — anchor 4 would require over-explanation to trim, which is absent. | 5 / 5 |
Actionability | Concrete, copy-paste-ready commands with real values ('/saas-health metrics --mrr 80000 --customers 200 --churned 3 ...') cover the common cases. However, the examples use flags (--new-customers, --sm-spend, --contraction) that are not documented in the Usage spec, and no script invocation syntax is shown — minor gaps rather than the missing key details of anchor 3, so anchor 4 fits best. | 4 / 5 |
Workflow Clarity | The subcommand-to-script mapping is unambiguous (metrics→metrics_calculator.py, quick-ratio→quick_ratio_calculator.py, simulate→unit_economics_simulator.py) and operations are read-only calculations, so no validation cap applies. It falls short of anchor 5 because the mapping from CLI flags to script arguments is never stated, leaving a minor execution gap characteristic of anchor 4. | 4 / 5 |
Progressive Disclosure | The body is a concise overview with well-signaled, one-level-deep references, each script annotated with its purpose ('Core SaaS metrics (ARR, MRR, churn, CAC, LTV, NRR, payback)'). However, the referenced paths (finance/skills/saas-metrics-coach/scripts/*.py and the referenced SKILL.md) do not exist in this skill's bundle — they are repo-relative rather than bundle-relative — an organization gap that keeps it at anchor 4 rather than 5. | 4 / 5 |
Total | 17 / 20 Passed |