Use when building tables and figures for a Communication Research (CR) manuscript so exhibits are self-contained, accessible, and formatted to APA. CR is quantitative, so exhibits must show effect sizes and uncertainty, not just stars. Designs exhibits; it does not run the analysis.
SkillScore91Maintained
Automatic
◆Research pack
Last verified 9/1/2026
What it changes
Passed 20 of 22 test cases with the skill, and 10 of 22 without it.
Without skill45%
With skill91%
Checks it passed that the model alone missed
Includes the bracketed header 【APA format?】.
Includes the bracketed header 【Accessible?】.
Includes the bracketed header 【Main exhibit】.
and 22 more in the full report
10 fixed10 passed either way2 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+34%
Agent turns
0%
Response time
-15%
Model gemini-3.6-flashMeasured 9/1/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
In the standard exhibit review output template for Communication Research manuscripts, what is the exact final line indicating the next stage in the review workflow?
What was checked, without and with the skill
Checked
Without skill
With skill
Outputs 【Next】commres-writing-style as the final workflow tag.
Missed
Passed
case-21 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md95 linessingle file
Tables & Figures (commres-tables-figures)
Exhibits are where a CR reviewer checks whether the result is real and whether the mechanism holds.
Because CR is a quantitative, APA-reporting journal, every table and figure must show effect sizes
and uncertainty, not significance stars alone, and follow APA formatting.
When to trigger
Designing the main results table/figure or a key descriptive/measurement exhibit
Deciding what belongs in the article vs. the online supplement
A reviewer found an exhibit unclear, mislabeled, or not self-contained
Presenting mediation/moderation results readably
Principles
Self-contained. A reader should understand each exhibit from its title, column/axis labels, and
note alone — without hunting through the text. State units, sample, N, and what the estimate is.
Show magnitude and uncertainty. Report effect sizes (d, η²ₚ, standardized β, R²) with CIs or
SDs. Coefficient/forest plots, marginal-effects and predicted-value plots, mediation path
diagrams, and interaction (simple-slopes) plots communicate better than a wall of coefficients.
APA format. Table/figure numbering, titles, and notes per APA; consistent decimals;
report the statistics APA expects (M, SD, test statistic with df, effect size, exact p).
Measurement exhibits. For SEM/CFA, show the measurement model (loadings, fit indices); for
content analysis, report category frequencies and intercoder reliability by category.
Accessible. Colorblind-safe palettes; legible in grayscale; no chartjunk, no 3D, no needless
color. Reviewers must parse it quickly.
Main text vs. supplement. Keep the few exhibits that carry the argument in the article; move
full specifications, robustness grids, scale items, and codebooks to the online supplement
(also anonymized) — this also helps you fit the page budget.
Reproducible. Each exhibit is generated by the master script; numbers match the deposited
materials (see commres-transparency-and-data).
Discipline-specific exhibits
Experiment cell means with CIs; ANOVA effect-size tables.
Mediation/moderated-mediation path diagrams with indirect-effect estimates and bootstrap CIs.
Simple-slopes / Johnson–Neyman plots for interactions.
SEM/CFA measurement-model tables (loadings, AVE/CR, fit indices).
Content-analysis reliability tables (alpha by category) and category-frequency exhibits.
Use when building tables and figures for an American Journal of Political Science (AJPS) manuscript. AJPS counts table/figure headers and notes toward the word limit, and the deposited code must regenerate every exhibit exactly for third-party verification. Designs self-contained, reproducible exhibits; it does not run the analysis.