Content
76%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 concise and gives concrete, executable command examples with sensible external references, but it lacks input/output validation for financial modeling and does not document how to invoke the underlying scripts. Adding verification steps and script usage examples would raise the weaker dimensions.
Suggestions
Add validation/sanity-check steps (e.g., verify ARR ≈ 12×MRR, confirm churn and growth rates are consistent, reject negative inputs) for the metrics and simulate subcommands.
Document each script's invocation signature and which subcommand uses it, so the referenced tools are directly executable rather than just listed.
Show a brief expected-output example for one command so Claude can verify a correct result against a known benchmark.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is lean and assumes Claude's competence, providing usage syntax, concrete examples, and script pointers without padding or explaining basic SaaS concepts. | 5 / 5 |
Actionability | Provides copy-pasteable command invocations with concrete numeric examples, but the referenced scripts lack invocation signatures or usage examples, leaving a minor gap in executable guidance. | 4 / 5 |
Workflow Clarity | Subcommand branches are clear but there are no validation checkpoints or sanity checks for the financial calculations and 12-month projection, capping workflow clarity at 3 per the feedback-loops guidance. | 3 / 5 |
Progressive Disclosure | Well-organized sections with clearly signaled one-level references to scripts and a sibling SKILL.md, though the referenced paths are external rather than local bundle files and scripts are not mapped to subcommands. | 4 / 5 |
Total | 16 / 20 Passed |