Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, well-structured research-and-template workflow that assumes Claude's competence and avoids concept padding. Its main weaknesses are duplicated trigger sections, absent verification checkpoints in the batch-research flow, and a monolithic structure that keeps a large output template inline.
Suggestions
Merge the 'When to Use' and 'Trigger Phrases' sections to remove the duplicated trigger phrasing and tighten token use.
Add an explicit validation checkpoint between Phase 2 and Phase 3 (e.g. 'Confirm evidence exists for every Win/Lose/Tie claim before drafting the battlecard') to gate the batch-research output.
Extract the full Phase 3 battlecard template into a references/ file (e.g. battlecard-template.md) and link to it from the body, leaving SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and free of concept-explanation padding, but the 'When to Use' and 'Trigger Phrases' sections duplicate each other and the large output template carries placeholder repetition, so not every token earns its place. | 2 / 3 |
Actionability | Provides copy-paste-ready search strings (e.g. site:g2.com OR site:capterra.com), concrete fetch targets, per-section extraction checklists, and a fully scaffolded battlecard template with sample objection handlers — concrete and executable guidance. | 3 / 3 |
Workflow Clarity | Phases are clearly sequenced (Intake → Research 1A-1E → Analysis → Output), but there is no explicit validation/verification checkpoint before battlecard generation — only an implicit 'Confidence' label — leaving the batch-research workflow without a completeness gate. | 2 / 3 |
Progressive Disclosure | Well-organized with clear headers and no nested references, but it is a monolithic >50-line file with the ~130-line output template inline — content that could reasonably live in a separate reference file rather than the overview. | 2 / 3 |
Total | 9 / 12 Passed |