From ajs-skills
Provides guidance for planning and auditing data analysis in American Journal of Sociology manuscripts, covering uncertainty, robustness, and triangulation across quantitative and qualitative methods.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ajs-skills:ajs-data-analysisThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
At AJS the analysis exists to make the **theoretical claim credible** — not to display technique. A
At AJS the analysis exists to make the theoretical claim credible — not to display technique. A generalist, double-blind reviewer will ask whether the evidence actually warrants the claim and whether candor about uncertainty is present. This skill stress-tests the analysis chain in the idiom of your work.
AJS often rewards convergent evidence — a mechanism shown through more than one window (e.g., statistics + cases, or interviews + administrative data). When methods disagree, say so and theorize the discrepancy rather than hiding it.
At a theory-forward generalist journal the analysis is judged by whether it makes the claim credible, not by technical novelty:
| Referee writes… | The AJS-specific fix |
|---|---|
| "Robustness theater." | run the one check the mechanism hinges on; drop filler |
| "Mechanism under-theorized." | map each estimate to an implication from ajs-theory-building |
| "Causal language the design can't bear." | restate as descriptive/associational and theorize it |
| "Methods disagree, unexplained." | theorize the discrepancy, don't suppress a window |
Orienting heuristics; confirm against the journal's current submission guidelines. AJS rewards convergent evidence and candor over a dense methods display, judging each tradition by its own standard; where a parsimony-first sibling prizes one clean estimate, AJS often prizes a mechanism shown through more than one window. Illustrative: a paper claims a mentoring program narrows a promotion gap "by building cross-rank ties" (an illustrative 6-point reduction, 95% CI ~2–10). A referee writes "the mechanism is asserted, not shown." The fix maps it to an observable implication (mentees gain cross-rank ties), triangulates with an illustrative 24 interviews, reports two units where the gap did not close, and softens causal phrasing to "consistent with."
Treat this skill as an executable review pass, not a prose hint. First lock the social process, data leverage, causal or interpretive warrant, and theoretical payoff; then judge whether the current manuscript answers the venue's real reader: sociology reviewers who value deep theory, durable empirical leverage, and careful social-mechanism claims.
claim / evidence / risk / manuscript location rows, so the next agent can edit rather than rediscover the issue.resources/official-source-map.md has been checked for volatile rules and the manuscript has one concrete fix for the largest venue-specific risk.【Claim under test】from theory-building
【Primary evidence】the analysis that carries the claim
【Uncertainty】how it is reported and bounded
【Robustness / negative cases】load-bearing checks done? [Y/N]
【Triangulation】convergent evidence across windows? [Y/N/NA]
【Confirmatory vs. exploratory】labeled where relevant? [Y/N]
【Next】ajs-tables-figures
../../resources/external_tools.md — analysis packages (R / Stata / Python / CAQDAS / QCA)../../resources/official-source-map.md — AJS evidence expectations and live-check boundary for data policynpx claudepluginhub brycewang-stanford/awesome-journal-skills --plugin ajs-skillsGuides analysis and reporting for ASR manuscripts to meet masked review standards across quantitative, demographic, comparative-historical, and computational sociology.
Defends the research design of an American Journal of Sociology manuscript on its own methodological terms—quantitative, comparative-historical, ethnographic, network, or formal. Provides tradition-specific guidance and referee-pushback patterns.
Guides transparent reporting of qualitative data-to-theory construction (coding, evidence tables, negative cases) and quantitative robustness checks for ASQ manuscripts.