Use when building tables and figures for an American Sociological Review (ASR) manuscript. ASR excludes tables and figures from the 15,000-word count but still expects them to be clear, self-contained, and ASA-formatted. Designs exhibits; it does not run the analysis.
SkillScore91Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 20 of 22 test cases with the skill, and 13 of 22 without it.
Without skill59%
With skill91%
Checks it passed that the model alone missed
specifies stating validation against labels
specifies that the note must state the estimator
specifies reporting the coding scheme in the note
and 6 more in the full report
7 fixed13 passed either way2 still failing0 broke
Pass-rate lift
+32 pp
Tokens
+46%
Agent turns
0%
Response time
-31%
Model gemini-3.6-flashMeasured 8/15/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
I am calculating the word count for my ASR manuscript submission. My main text body has 13,200 words, references have 1,500 words, footnotes have 400 words, and my 5 tables and figures total 1,200 words. Does my submission exceed ASR's 15,000-word limit?
What was checked, without and with the skill
Checked
Without skill
With skill
identifies that text, references, and footnotes total 15,100 words
Missed
Passed
states that tables and figures are excluded from the word limit calculation
Missed
Passed
concludes that the submission exceeds the 15,000-word limit
Passed
Passed
case-04 · 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.md117 linessingle file
Tables & Figures (asr-tables-figures)
Exhibits are where a masked reviewer checks whether the result is real. ASR excludes tables and
figures from the 15,000-word limit (text, references, and footnotes count) — so you are not penalized
for a clear exhibit, but it must earn its place and stand on its own.
When to trigger
Designing the main results table/figure or a key descriptive exhibit
Deciding what belongs in the article vs. supplementary materials
A reviewer found an exhibit unclear, mislabeled, or not self-contained
Presenting qualitative or comparative-historical evidence in tabular/visual form
Principles
Self-contained. Title, row/column labels, and a complete note make each exhibit intelligible
alone. State the sample, N, units, weighting, and what the estimate is.
Show magnitude and uncertainty. Effect sizes and intervals — not stars alone. Coefficient and
marginal-effects plots often beat dense coefficient walls.
Sociology-specific exhibits. Mobility/transition tables and flow diagrams; survival curves and
Lexis/age-period-cohort surfaces for demography; network graphs; sequence-analysis chronograms;
evidence tables linking claims to sources for comparative-historical/ethnographic work.
Accessible. Colorblind-safe palettes; legible in grayscale; no chartjunk or 3D.
Reproducible. Generated by the master script (quantitative) so numbers match shared materials;
for qualitative exhibits, excerpts must be faithful to the coded data.
Format
Follow the ASA Style Guide for table/figure formatting and notes.
Double-spaced manuscript, Times New Roman 12 pt; place tables/figures per the guidelines.
Keep identifying information out of exhibits (masked review).
Exhibit conventions a masked ASR reviewer expects
The ASA flagship admits exhibits from every tradition but holds them to one standard: a reviewer who
may not share your method must be able to read the evidence unaided. Match the exhibit to the
tradition, then verify it carries magnitude and uncertainty.
Use when building tables and figures for an American Journal of Sociology (AJS) manuscript to AJS house conventions — discrete consecutive numbering, appendix-table lettering, separate exhibit sections after the text, and mandatory alt text for every figure at submission. Prepares exhibits; it does not generate data.