Content
56%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 thorough, well-sequenced research skill with concrete templates and worked examples, but it is noticeably verbose and inlines the bulk template content that its own references point to as separate (and currently missing) files. Tightening the body and actually providing template.md would meaningfully improve it.
Suggestions
Move the nine step template blocks into the referenced template.md (and provide examples/sample.md), keeping only a concise overview and one-line pointers in SKILL.md to reduce length and fix the missing bundle files.
Trim padding sections such as 'Why This Works' and 'When to Use This' (which duplicates the frontmatter description's triggers) and consolidate the repeated per-step 'Sources to check' lists into a single shared source-checklist reference.
Add an explicit final verification step (e.g., a completeness/source-citation checklist applied to the drafted brief) to close the workflow with a clear validation checkpoint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~388-line body is noticeably verbose: nine near-identical fill-in template blocks, repeated 'Sources to check' lists per step, and padding sections like 'Why This Works' and 'When to Use This' (which duplicates the description's triggers) restate obvious points and could be trimmed. | 2 / 5 |
Actionability | Concrete step templates with specific fields, per-step 'Sources to check' lists, and worked Stripe examples give mostly executable guidance; it is not a 5 because some sections are conditional/high-level ('If applicable, capture PLG strategies') and the deliverable is templates rather than copy-paste code. | 4 / 5 |
Workflow Clarity | A clear nine-step sequence with partial checkpoints (Step 3 'Quality checks' and the 'Common Pitfalls' section), but no consolidated final verification or feedback loop, leaving minor validation gaps; the destructive-cap-at-3 rule does not apply to this research skill. | 4 / 5 |
Progressive Disclosure | Section structure is good and references to template.md and examples/sample.md are clearly signaled, but the nine inlined template blocks are exactly the content the skill says belongs in template.md — and that file does not exist in the bundle — so content that should be separate is inline. | 3 / 5 |
Total | 13 / 20 Passed |