meta-analysis-forest-plotter
Use when creating forest plots for meta-analyses, visualizing effect sizes across studies, or generating publication-ready meta-analysis figures. Produces high-quality forest plots with confidence intervals, heterogeneity metrics, and subgroup analyses.
84
86%
Does it follow best practices?
Impact
64%
1.42xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specialized niche in meta-analysis visualization. It uses proper third-person voice, includes explicit 'Use when' guidance with natural trigger terms, and lists specific capabilities that would help Claude distinguish this skill from general plotting or statistics skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creating forest plots', 'visualizing effect sizes across studies', 'generating publication-ready meta-analysis figures', 'confidence intervals', 'heterogeneity metrics', and 'subgroup analyses'. | 3 / 3 |
Completeness | Explicitly answers both what ('Produces high-quality forest plots with confidence intervals, heterogeneity metrics, and subgroup analyses') and when ('Use when creating forest plots for meta-analyses, visualizing effect sizes across studies, or generating publication-ready meta-analysis figures'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'forest plots', 'meta-analyses', 'effect sizes', 'studies', 'publication-ready', 'confidence intervals', 'heterogeneity', 'subgroup analyses'. These are domain-appropriate terms researchers would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in statistical meta-analysis visualization. Terms like 'forest plots', 'heterogeneity metrics', and 'meta-analyses' are specific enough to avoid conflicts with general data visualization or charting skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized, concise skill that efficiently communicates forest plot generation capabilities. The main weaknesses are the reliance on an unverified custom module and the absence of data validation steps, which are important for publication-quality outputs where errors could be costly.
Suggestions
Add a data validation step showing how to verify input data format and handle common issues (missing CIs, invalid effect sizes) before plotting
Clarify whether scripts/forest_plotter.py is a real module in the project or provide installation/setup instructions for the actual library being wrapped
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary information without explaining what forest plots or meta-analyses are. Every section delivers actionable content without padding. | 3 / 3 |
Actionability | Code examples are concrete and appear executable, but they reference a custom module (scripts/forest_plotter.py) without showing its implementation or confirming it exists. The API shown is illustrative but not verifiably copy-paste ready. | 2 / 3 |
Workflow Clarity | The skill presents clear usage patterns but lacks validation steps for a data-driven workflow. No guidance on verifying data format, handling missing values, or validating output quality before publication. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from quick start to advanced features. References to external files (forest-plot-styles.md, sample-plots/) are one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- aipoch/medical-research-skills
- Commit
ca9aaa4
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.