Content
92%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 well-structured, highly actionable, and uses progressive disclosure effectively with real reference files. It is instruction-only but the guidance is concrete and specific, with a clear sequenced workflow and self-check checkpoint.
Suggestions
Trim reframing lines like 'The output is not a decorative research deck. It is a working room for debate' and the 'When to use' bullet list that restates frontmatter triggers, to tighten conciseness toward a 5.
The 'When to use this skill' section duplicates the frontmatter trigger guidance; consider consolidating to a single location to avoid redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely lean and assumes competence (concrete ledger schema, scoring scale, memo template), but a few lines restate the frontmatter or add mild framing ('The output is not a decorative research deck. It is a working room for debate') that could be trimmed. | 4 / 5 |
Actionability | Provides concrete, executable guidance throughout — a full ledger row schema with field names and enumerated values, a 1–5 opportunity scoring rubric with defined directionality, a 6-part decision memo template, an 8-section information architecture, and the exact artifact emission block. | 5 / 5 |
Workflow Clarity | Seven explicitly sequenced steps with a self-check/validation checkpoint in Step 7 ('Run the checklist. Then emit...') and the prior instruction to run references/checklist.md before emitting, giving a clear feedback loop. | 5 / 5 |
Progressive Disclosure | Includes a resource map and clearly signals one-level-deep references — 'Read references/evidence-model.md before synthesis and run references/checklist.md before emitting' — both of which exist as real files in references/. | 5 / 5 |
Total | 19 / 20 Passed |