Use when building tables and figures for a British Journal of Political Science (BJPS) manuscript so exhibits are self-contained, accessible, fit Cambridge's size limits, and earn their place under the word budget. Designs exhibits; it does not run the analysis.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill95%
Checks it passed that the model alone missed
The response recommends using did_summary_to_latex.
The response specifies page box dimensions of 190 by 120 millimeters.
The response specifies Cambridge page box dimensions of 190 by 120 millimeters.
and 2 more in the full report
4 fixed17 passed either way1 still failing0 broke
Pass-rate lift
+18 pp
Tokens
+89%
Agent turns
0%
Response time
-13%
Model gemini-3.6-flashMeasured 8/15/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
Which Stata helper command exports formatted LaTeX tables directly from stored difference-in-differences estimation results?
What was checked, without and with the skill
Checked
Without skill
With skill
The response recommends using did_summary_to_latex.
Missed
Passed
case-06 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md92 linessingle file
Tables & Figures (bjps-tables-figures)
Exhibits are where an expert reviewer checks whether the result is real. At BJPS they must also fit
Cambridge's physical limits — tables within roughly 190 × 120 mm, figures within roughly
200 × 133 mm at ≥ 300 dpi (待核实 exact current figures) — and they count against the word budget,
so every exhibit must pull its weight.
When to trigger
Designing the main results table/figure or a key descriptive exhibit
Deciding what belongs in the article vs. the online appendix
A reviewer found an exhibit unclear, mislabeled, or non-self-contained
Trimming to the word cap by moving exhibits to the appendix
Principles
Self-contained. A reader should understand each exhibit from its title, axis/column labels, and
note alone — without hunting through the text. State units, sample, N, and what the estimate is.
Figures over dense tables for effects. Coefficient/forest plots, marginal-effects and
predicted-probability plots, event-study and RD plots communicate magnitude and uncertainty better
than a wall of coefficients. Show intervals.
Accessible. Colourblind-safe palettes; legible in grayscale; no chartjunk, no 3D, no needless
colour. Reviewers and readers must parse it quickly.
Fit Cambridge's limits. Size tables/figures to the page box; supply figures at ≥ 300 dpi in a
vector or high-resolution format; keep fonts legible after reduction (待核实 exact specs).
Main text vs. appendix. Keep the few exhibits that carry the argument in the article; move
balance tables, full specifications, and robustness grids to the online appendix (excluded from
the word count). This is also how you fit under the word cap.
Reproducible. Each exhibit is generated by the master script; numbers match the deposited
replication package exactly (see bjps-transparency-and-data).
Discipline-specific exhibits
Maps for geographic/spatial variation; network diagrams where structure is the point.
Use when designing tables and figures for a Comparative Political Studies (CPS) manuscript so each exhibit is self-contained, comparative-legible, and SAGE-ready. Improves the exhibits; it does not run the analysis or set the data policy.