Content
67%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 a well-structured meta-skill overview with a clear sequenced workflow and explicit scope-validation guidance. It is light on runnable specifics (no code/commands) and inlines some detail that a dedicated reference file could offload.
Suggestions
Add concrete, executable guidance for at least one stage (e.g. a sample PubMed MeSH query string or a code snippet for fitting a random-effects meta-analysis) to lift actionability.
Insert explicit validation checkpoints between workflow steps (e.g. "Confirm deduplication complete and counts logged before screening") to strengthen the feedback loop.
Move the PRISMA 2020 checklist mapping or database-specific query construction into a reference file and link to it, keeping SKILL.md a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficiently organized into scoped sections and assumes domain competence, but several best-practice and output-format lists are somewhat padded and could be tightened. | 4 / 5 |
Actionability | The workflow lists concrete stages, named tools (RoB 2, GRADE, PubMed), and metrics, but provides no executable code, commands, or step-by-step runnable procedures, leaving guidance at a directive level. | 3 / 5 |
Workflow Clarity | A clear seven-step sequenced workflow with explicit input-validation gating at the end; minor gaps are that inter-step validation checkpoints between stages are implicit rather than explicit. | 4 / 5 |
Progressive Disclosure | Good structure as a meta-skill overview that signals integration points to three specialized skills and lists outputs; no bundle files are present, and some detail (e.g. database query construction, PRISMA checklist mapping) is inlined rather than referenced out. | 4 / 5 |
Total | 15 / 20 Passed |