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 concise, well-structured instruction-only skill with concrete collection checklists, a numbered output format, and a quality gate. It could be strengthened with a brief worked example and an explicit revise-and-recheck loop around the quality gate.
Suggestions
Add a short worked example (e.g. a 3-line competitive-analysis excerpt) to lift actionability to fully copy-paste ready.
Make the Quality Gate an explicit feedback loop: if any gate fails, revise the offending section and re-run the gate before delivery.
Optionally split the per-mode collection checklists into a one-level-deep reference (e.g. modes.md) and keep SKILL.md as an overview to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient throughout — terse headers, bullet checklists, and a punchy opening ('Produce research that supports decisions, not research theater') with no padding or explanation of concepts Claude already knows. | 5 / 5 |
Actionability | Concrete, specific guidance per mode (e.g. collect 'fund size, stage, and typical check size', 'top-down estimates... bottom-up sanity checks') plus a numbered output format; as an instruction-only skill it is actionable, though a worked mini-example would make it fully copy-paste ready. | 4 / 5 |
Workflow Clarity | Clear structure from 'When to Activate' through a numbered 'Output Format' (1-6) and a pre-delivery 'Quality Gate' checkpoint; minor gap is an explicit feedback loop (verify gate fails -> revise -> re-check) rather than just a one-pass checklist. | 4 / 5 |
Progressive Disclosure | Well-organized single-file skill with clear section headers and no nested references; slightly over the 50-line simple-skill threshold and lacks any one-level-deep reference pointers, so it sits just below a 5. | 4 / 5 |
Total | 17 / 20 Passed |