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 a well-structured, actionable methodology with a concrete output template, scoring high on actionability and structure. It loses conciseness points to conceptual/motivational prose that Claude does not need.
Suggestions
Trim the 'Why Most Assumptions Are Wrong' section to one or two lines, or fold it into the opening, to reduce conceptual padding Claude already knows.
Convert the implicit output template into an explicit validate-then-act checkpoint (e.g., 're-run steps 2-3 if a counter-evidence item materially changes the downside model') to add a feedback loop.
Consider moving the per-assumption-type patterns (Revenue, Market Size, Moat, Hiring, Competitive Response) into a reference file to keep SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient actionable content, but the 'Why Most Assumptions Are Wrong' section and motivational prose ('Founders are optimists by nature...') explain framing Claude already understands and could be trimmed. | 3 / 5 |
Actionability | Provides concrete stress questions, a quantitative scenario table with explicit percentage deltas, per-assumption-type failure/test structure, and a fill-in output template — actionable with only minor gaps. | 4 / 5 |
Workflow Clarity | Clear 5-step sequence (Isolate, Counter-Evidence, Model Downside, Sensitivity, Hedge) plus an output template that acts as a checklist; validation is implicit rather than an explicit fix-retry loop. | 4 / 5 |
Progressive Disclosure | Single self-contained SKILL.md with no bundle files, well-organized into clearly headed sections; under the simple-skill exception, well-organized single-file content scores 5. | 5 / 5 |
Total | 16 / 20 Passed |