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.
Install with Tessl CLI
npx tessl i github:aipoch/medical-research-skills --skill meta-analysis-forest-plotter95
Does it follow best practices?
Validation for skill structure
Evaluation results
92%
20%Cardiovascular Meta-Analysis Forest Plot
CLI usage and CSV data format
CSV column names
100%
100%
Script entrypoint used
0%
100%
PNG output format
100%
100%
Output filename matches spec
100%
100%
Heterogeneity I² reported
100%
100%
Q statistic reported
100%
100%
Q p-value reported
100%
100%
Heterogeneity interpretation
100%
100%
Dependencies installed
0%
0%
Null value appropriate
100%
100%
Model flag used
0%
100%
Without context: $0.4632 · 2m 6s · 23 turns · 139 in / 7,005 out tokens
With context: $0.6556 · 2m 4s · 27 turns · 30 in / 6,475 out tokens
42%
3%Oncology Treatment Subgroup Meta-Analysis
Subgroup analysis and Python API usage
Correct import path
0%
100%
subgroup_plot() method used
28%
0%
subgroup_col parameter
20%
0%
subgroups list parameter
60%
0%
Statistical annotations included
25%
33%
heterogeneity_stats dict structure
12%
0%
overall_effect dict structure
12%
0%
JSON input parsed correctly
100%
100%
Heterogeneity threshold interpretation
40%
100%
Three subgroups reported
100%
100%
Without context: $0.7200 · 3m 10s · 38 turns · 39 in / 10,310 out tokens
With context: $0.5896 · 2m 53s · 21 turns · 23 in / 9,608 out tokens
60%
36%Preparing a Forest Plot for Journal Submission
Journal styling and publication output format
style='publication'
0%
0%
journal parameter set
0%
0%
color_scheme='monochrome'
0%
0%
show_weights=True
0%
100%
Journal-submission output format
100%
100%
null_value set to 1
0%
100%
Skill library imported
0%
100%
Format justification in checklist
100%
100%
Styling params documented
0%
50%
Without context: $0.5496 · 2m 10s · 35 turns · 42 in / 5,533 out tokens
With context: $0.7544 · 2m 50s · 30 turns · 221 in / 8,208 out tokens
- Evaluated
- Agent
- Claude Code
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.