Alterlab Figure Qa
Published by alterlab-ieu in alterlab-academic-skills
What this skill does
Verify publication figures with a render-then-check QA pass — data-fidelity against every underlying row, axis/label floor-and-ceiling legibility, bounding-box collision detection for overlapping text/markers, and 300-dpi print-readiness. Use when proofing or auditing a finished figure for correctness and print quality, catching mislabeled or overlapping elements, or confirming a plot faithfully represents its data before submission. For CREATING the plot prefer alterlab-matplotlib (or alterlab-
Add Alterlab Figure Qa to your agent
Review the source and files first. When you are ready, copy the prompt instruction or use the CLI command supported by your environment.
Install with a prompt
Paste this into a compatible coding agent:
add this skill "alterlab-figure-qa" from https://github.com/alterlab-ieu/alterlab-academic-skillsInstall with the CLI
Run this command in a controlled environment after reviewing the repository:
npx skills add https://github.com/alterlab-ieu/alterlab-academic-skills --skill alterlab-figure-qaSkill instructions
Figure QA (render-then-verify)
Overview
A finished figure can look fine and still be wrong: a series plotted from the wrong column, a legend covering a data point, tick labels clipped at the axis edge, or a 150-dpi export that pixelates in print. This skill is a render-then-verify QA pass — it re-renders the figure and checks it against a concrete, measurable checklist before submission. It complements the plotting skills (which make figures); it does not create plots.
When to Use This Skill
Use this skill when the user wants to:
- Proof a finished figure for correctness and print-readiness before submission.
- Confirm the plot faithfully represents its data (every row/series accounted for).
- Catch overlapping or clipped labels, legends, and markers.
- Verify resolution / export settings (e.g. 300 dpi, vector where required).
Does NOT Trigger
| Scenario | Use instead |
|---|---|
| Create/plot the figure in the first place | alterlab-matplotlib / alterlab-seaborn / alterlab-plotly |
| Lay out a multi-panel publication figure | alterlab-scientific-viz |
| Draw a schematic / diagram | alterlab-scientific-schematics |
| Build an infographic | alterlab-infographics |
Hand-off rule. When the request matches a row above, open your answer by naming that skill by its exact id (for example alterlab-matplotlib) and saying in one line why it fits better, then stop applying this skill's procedure. Name it even when you also need to ask for missing input. If only part of the request is out of scope, name the skill for that part and do only the in-scope part. A brief general pointer is fine; the named skill does the work.
Core Capabilities
1. Data-fidelity check
Verify the rendered marks against every row of the source data: series count, point count per series, min/max/range on each axis, and that categorical labels match the data's categories. Flag any series plotted from the wrong column or a silently dropped subset.
2. Label floor-and-ceiling legibility
Check that tick labels, axis titles, and annotations are within legibility bounds — a font floor (nothing below the journal's minimum pt at final size) and a ceiling (titles not so large they crowd the panel) — and that nothing is clipped at the axis boundary.
3. Bounding-box collision detection
Compute the bounding boxes of text, legend, and markers and detect overlaps/collisions (legend over data, colliding labels, out-of-axes text). Report each collision with its location so it can be nudged.
4. Resolution and export QA
Confirm the export meets the target: ≥300 dpi for raster, vector format where the venue requires it, correct figure dimensions/column width, and embedded fonts. Fail the check if the raster resolution is below the floor.
5. Report
Emit a pass/fail checklist per criterion with the specific offending element(s), so the fix is
actionable. See references/figure_qa_checklist.md for the full rubric and Matplotlib bbox
recipes.
Resources
references/figure_qa_checklist.md— the full QA rubric, Matplotlib renderer/bbox recipes for collision detection, dpi/vector export checks, and journal legibility floors. Loaded on demand.
Part of the AlterLab Academic Skills suite.
Files included
- evals/evals.json
- evals/fixtures/fidelity/plot_viability.py
- evals/fixtures/fidelity/viability_timecourse.csv
- evals/fixtures/overlap/plot_sites.py
- evals/fixtures/overlap/site_richness.csv
- evals/fixtures/proof/growth_curves.csv
- evals/fixtures/proof/make_fig2.py
- references/figure_qa_checklist.md
- SKILL.md

