Use when executing and reporting the analysis for an American Journal of Political Science (AJPS) manuscript. AJPS will have a third-party verifier re-run your exact code against the numerical results in the main text before publication, so analyze reproducibly from the first line. Guides analysis and reporting norms; it does not fabricate results.
SkillScore100Maintained
Automatic
◆Data Analyst pack
Last verified 8/15/2026
What it changes
Passed 22 of 22 test cases with the skill, and 19 of 22 without it.
Without skill86%
With skill100%
Checks it passed that the model alone missed
The response specifies testing identifying assumptions with diagnostic balance checks
The response requires programmatic output generation to avoid manual typing in tables
The response requires explicitly labeling post-hoc interaction findings as exploratory
and 2 more in the full report
3 fixed19 passed either way0 still failing0 broke
Pass-rate lift
+14 pp
Tokens
+42%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 8/15/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
I am preparing the empirical results for an AJPS manuscript on how local news exposure affects political participation. Could you review my analysis breakdown? Please structure the output to cover the main point estimate with substantive interpretation, identification checks, stress-testing robustness specs, subgroup interaction findings, distinction between pre-registered and exploratory models, and a verification check on code reproducibility.
What was checked, without and with the skill
Checked
Without skill
With skill
The response specifies reporting substantive effect magnitudes alongside confidence intervals
Missed
Passed
The response requires sensitivity analysis to unobserved confounding
Passed
Passed
The response specifies adjusting p-values for multiple comparisons across subgroup interactions
Missed
Passed
The response requires explicitly labeling post-hoc interaction findings as exploratory
Missed
Passed
The response requires setting explicit random seeds for computational reproducibility
Passed
Passed
case-01 · 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.md114 linessingle file
Data Analysis (ajps-data-analysis)
AJPS reviewers are methodologically sophisticated, and after acceptance an independent third-party
verifier re-runs your code against the numbers in the main text before the article is published (see
ajps-replication-and-verification). Analyze as if both facts are true — because they are. This skill
covers execution and reporting; design choices live in ajps-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 so the verifier's re-run will match
Analysis norms AJPS expects
Report uncertainty and magnitude. Confidence/credible intervals and substantive effect sizes,
not just significance stars — say what the estimate means.
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; adjust 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; wild-cluster bootstrap when clusters are few.
Preregistration discipline. Separate registered from exploratory analyses; justify any
deviation from the plan.
Measurement. Validate constructs; report reliability; show results are not an artifact of a
single 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; do not treat raw
outputs as ground truth.
Reproducibility while you work (so the verifier's re-run matches)
One master script regenerates every table and figure from the (raw or constructed) data, in
order, setting the working directory once.
Set and report seeds for every stochastic step (bootstrap, randomization inference, simulation,
jittered plots) — the verifier needs identical draws.
Record exact software versions (e.g., "R 4.3.2", "Stata/MP 18.0") and pin packages
Use when running and reporting the analyses for a Comparative Political Studies (CPS) manuscript — estimation, uncertainty, robustness, and multi-method triangulation on comparative data. Sets analysis norms; it does not choose the identification strategy (see cps-research-design).