asr-writing-style — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited asr-writing-style (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.
An ASR paper must be readable by a sociologist outside its subfield, formatted to the ASA Style Guide, and disciplined to a word cap that includes the reference list. This skill is about reaching the discipline and respecting the format — not generating claims.
argument, the evidence, and why it matters to sociology broadly.
follow a demographic paper and vice versa.
concept (from asr-theory-building) explicit.
(manage with Zotero/BibTeX). References count toward the 15,000-word limit.
acknowledgments, and contact. You may cite your own work but must not word it to identify yourself ("in our prior study" → "in a prior study").
asr-literature-positioning).At the ASA flagship the reader of record is a sociologist outside your subfield, so the writing does disciplinary translation a specialty journal does not require.
| Weakness | Cross-subfield reader experiences | Prose fix |
|---|---|---|
| Jargon undefined | stalls on a term of art | define on first use; spell out acronyms |
| Stakes buried | doesn't know why to read on | front-load significance in the intro |
| Evidence-first paragraphs | can't find the claim | lead with the claim, support with evidence |
| Over-long reference strings | length burned, argument thin | prune; references count toward 15,000 |
| Self-citation in identifying voice | masking broken | "in a prior study," not "in our prior study" |
A network-study introduction is rewritten to reach the discipline.
Before: "We extend ERGM specifications of tie formation in adolescent friendship networks..."
→ a generalist stops reading
After: "How do everyday social ties reproduce racial segregation? A small set of formation rules
generates large-scale separation..." → stakes first, method second
Abstract: trimmed 224 → 188 words, finding plain, no institution named → in range
Length: pruned 40 redundant citations, recovering ~600 words against the cap incl. referencesThe contribution leads, the method follows, and the prune is treated as a budget item.
pages so a generalist commits early.
disciplinary language.
footnotes count, tables and figures do not.
readability plus author-date conventions and masking discipline.
15,000 words — budget citations from the first draft.
decision-relevant; the broad shape is stable.
【Contribution stated by end of intro?】[Y/N]
【Reads past the subfield?】jargon defined / acronyms spelled? [Y/N]
【Abstract】word count (<= 200), non-identifying?
【Word count】Article ≤ 15,000 incl. text + references + footnotes?
【ASA style + masked + separate title page】[Y/N]
【Next】asr-data-and-transparency../../resources/official-source-map.md — word/abstract caps, ASA Style Guide, masking, formatting~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.