ajs-research-design — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ajs-research-design (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
AJS is method-pluralist: it publishes leading quantitative, comparative-historical, ethnographic, network, and formal work, and it judges each by the standards of its own tradition. The job here is to make the design defensible to a generalist, possibly cross-method, double-blind reviewer — and to show the design actually supports the theoretical claim from ajs-theory-building.
precision. Where the design is descriptive or associational, say so and theorize accordingly.
typical / deviant, scope of the comparison).
evidence, not decoration.
the theoretical weight.
SAOM) to the relational question.
challenge the model.
The single most common AJS reviewer objection: the design cannot bear the theoretical claim. Walk the chain: claim → mechanism → observable implication → the design's leverage on it. If a step is weak, tighten the claim or strengthen the design — do not overclaim.
The most common AJS design rejection is "the design cannot bear the theoretical claim." Recurring objections by tradition; confirm method expectations against the journal's current submission guidelines.
| Referee writes… | Tradition | The AJS-appropriate fix |
|---|---|---|
| "Selecting on the outcome." | comparative-historical | add a non-outcome case or acknowledge the limit |
| "Representativeness asserted." | ethnographic | argue why this case bears the theoretical weight |
| "Identification overclaimed." | quantitative | restate as descriptive/associational and theorize it |
AJS judges each tradition by its own standard, not a single template; unlike a parsimony-first sibling that privileges a clean causal estimate, it accepts a richly defended interpretive or comparative design when it bears the claim. Illustrative: an author selecting four states that all underwent revolution, then theorizing "state breakdown causes revolution," is flagged for selecting on the outcome; the fix adds two negative cases (comparable fiscal crises that did not break down) so the comparison can see the mechanism fail as well as fire. Confirm method guidance against the journal's current submission guidelines.
Estimate and audit the design, don't only describe it. Full map: execution-with-mcp. AJS is general sociology with a strong theory tradition; apply the chain below to its quantitative-empirical lane.
detect_design → recommend → fit with as_handle=true → audit_result.callaway_santanna / sun_abraham +bacon_decomposition + honest_did_from_result); IV (effective_f_test + anderson_rubin_ci); RDD (rdrobust + mccrary_test).
romano_wolf for many-outcomefamily-wise control, and mediate for mediation (not naive controlling-away).
oster_delta / sensemakr for observational claims.Report the effect size in interpretable units; route the full battery to the appendix/supplement. A run end-to-end (synthetic data, real returns) is in the JF execution walkthrough.
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.【Tradition】quantitative / comparative-historical / ethnographic / network / formal / mixed
【Claim it must support】from theory-building
【Design leverage】how this design bears on the claim
【Key assumptions / threats】identification, selection, access, boundary, etc.
【Evidentiary trail】sources → claims is legible? [Y/N]
【Verdict】supports the claim / needs tightening / overclaims (fix)
【Next】ajs-data-analysis../../resources/external_tools.md — design and method tooling by tradition../../resources/official-source-map.md — AJS method-pluralism and reviewer-matching policy~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.