Content
86%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 tight, well-structured instruction-only skill that avoids padding and uses clear sections plus a quality gate. Its main weakness is actionability depth: several research modes (especially market sizing) point at what to collect without concrete methods or worked examples.
Suggestions
Add one or two concrete methods per Research Mode (e.g., name specific source types or a worked top-down/bottom-up sizing formula) to lift actionability toward fully executable.
Add an explicit feedback loop to the Quality Gate ('if any check fails, revise the flagged section before delivering') to strengthen workflow clarity.
Optionally surface key synonyms (TAM/SAM, competitive landscape) in the description's trigger list for fuller trigger coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean bullet-driven body with no padding and no explanation of concepts Claude already knows; every section earns its place and assumes Claude's competence. | 5 / 5 |
Actionability | Actionable collect-lists, a concrete output template, and a quality-gate checklist give mostly executable guidance, but market sizing and several modes lack concrete methods or worked detail, keeping it below a 5. | 4 / 5 |
Workflow Clarity | A clear deliverable sequence (Output Format steps 1-6) plus an explicit 'Before delivering' Quality Gate provides a checkpoint, but there is no error-recovery feedback loop, so it is not a 5. | 4 / 5 |
Progressive Disclosure | No bundle files exist and none are needed; the self-contained body is well-organized into clearly labeled sections (When to Activate, Research Standards, Research Modes, Output Format, Quality Gate), meeting the simple-skill bar. | 5 / 5 |
Total | 18 / 20 Passed |