Content
72%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is lean and well-organized but offers reporting guidance rather than a sequenced, executable meta-analysis workflow with concrete methods and validation checkpoints. Specifying effect-size metrics, formulas/tools, and a verification step would materially raise actionability and workflow clarity.
Suggestions
Add concrete specifics: name effect-size metrics (e.g., standardized mean difference, odds ratio) and a tool/library for forest plots so guidance is copy-paste ready.
Reframe the list as a short sequenced workflow (compute effect sizes -> assess heterogeneity -> pool -> visualize -> check bias) with a verification step that confirms CIs and heterogeneity are reported.
Include a minimal code or command example (e.g., a Python snippet computing a pooled effect size) to lift actionability from guidance to executable instruction.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Seven terse numbered directives with no padding or explanation of concepts Claude already knows; every line earns its place. | 3 / 3 |
Actionability | Directives are concrete reporting requirements ("Report effect sizes", "Use forest plots", "Report confidence intervals") but lack executable specifics such as which effect-size metric, computation formulas, or a concrete tool for forest plots. | 2 / 3 |
Workflow Clarity | The items are enumerated best-practice considerations rather than a sequenced process, and there are no validation/checkpoint steps to confirm the aggregate analysis is sound. | 2 / 3 |
Progressive Disclosure | A simple, under-50-line single-purpose skill with a single well-organized section and no need for external references; no bundle files exist, so the inline structure is appropriate. | 3 / 3 |
Total | 10 / 12 Passed |