Use when executing and reporting the analysis for an American Political Science Review (APSR) manuscript so it survives expert, double-anonymous review — honest uncertainty, robustness, and triangulation appropriate to quantitative, experimental, or computational work. Guides analysis norms; it does not fabricate results.
SkillScore96Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 24 of 25 test cases with the skill, and 14 of 25 without it.
Without skill56%
With skill96%
Checks it passed that the model alone missed
Recommends apsr-tables-figures as the next skill phase under 【Next】.
Designates apsr-tables-figures as the next workflow step under 【Next】.
Requires reporting model output stability across different random seeds.
and 10 more in the full report
10 fixed14 passed either way1 still failing0 broke
Pass-rate lift
+40 pp
Tokens
+41%
Agent turns
0%
Response time
-24%
Model gemini-3.6-flashMeasured 8/15/2026v124 of 25 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
We ran a regression handle in our Stata / StatsPAI execution session and want to quickly discover all missing specification checks and recommended helper functions for our model output. What command or function should we execute on the result handle?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies audit_result as the function to list missing specification checks on a model result handle.
Missed
Passed
Explains that the function retrieves recommended helper functions to complete diagnostic testing.
Passed
Passed
case-13 · 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.md127 linessingle file
Data Analysis (apsr-data-analysis)
APSR reviewers are methodologically sophisticated and the editorial office will later re-run your
code against the manuscript's tables and figures (see apsr-transparency-and-data-policy). Analyze
as if both are true — because they are. This skill covers execution and reporting norms; design
decisions live in apsr-research-design.
When to trigger
Running main and supporting analyses; building the results section
A reviewer asked for robustness, heterogeneity, or alternative specifications
Reconciling preregistered vs. exploratory analyses
Making the analysis reproducible before deposit
Analysis norms APSR expects
Report uncertainty honestly. Confidence/credible intervals, not just stars; the magnitude and
substantive meaning of the estimate, not just its significance.
Robustness that probes, not decorates. Show specifications that could break the result
(alternative measures, samples, estimators, fixed effects), and say what you learn.
Heterogeneity with discipline. Pre-specify subgroups where possible; correct for multiple
comparisons; do not mine for a significant interaction and theorize it post hoc.
Right inference. Cluster at the assignment/sampling level; randomization inference for
experiments; small-cluster corrections (wild-cluster bootstrap) when clusters are few.
Preregistration discipline. Clearly separate registered analyses from exploratory
ones; reconcile deviations from the plan and justify them.
Measurement. Validate constructs; report reliability; show that results are not an artifact of
a coding/scaling choice.
Computational / text-as-data specifics
Document model/version, hyperparameters, seeds, and validation against human-labeled samples.
For topic models/embeddings/LLM pipelines: report stability and a validation step; don't treat
outputs as ground truth.
Reproducibility while you work (not at the end)
One master script regenerates every table and figure from the (raw or constructed) data.
Set and report seeds for bootstrap, randomization inference, simulation, and any stochastic step.
Pin software/package versions (renv.lock, requirements.txt, recorded ssc/net installs).
Keep table/figure numbers in the manuscript matched to script outputs — the editors will check.
Use when executing and reporting the analysis for an American Sociological Review (ASR) manuscript so it survives expert masked review — honest uncertainty, robustness, and evidence handling appropriate to quantitative, demographic, comparative-historical, or computational sociology. Guides analysis norms; it does not fabricate results.