Use when systematically gathering, reading, and synthesizing a large body of sociological research for an Annual Review of Sociology (ARSoc) review — coverage discipline and avoiding citation gaps across theoretical traditions. Builds the evidence corpus and synthesis notes; it does not impose the analytical spine (arsoc-organizing-framework) or write prose (arsoc-writing-style).
SkillScore100Maintained
Automatic
◆Research pack
Last verified 8/15/2026
What it changes
Passed 22 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill100%
Checks it passed that the model alone missed
Includes 【Snowball status】 in the output
Outputs the exact tag → arsoc-organizing-framework
Specifies → arsoc-organizing-framework as the next step
and 18 more in the full report
13 fixed9 passed either way0 still failing0 broke
Pass-rate lift
+59 pp
Tokens
+9%
Agent turns
0%
Response time
-37%
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 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
I have completed the literature sweep, documented saturation, and populated my evidence matrix. What is the explicit next stage tag in the synthesis workflow?
What was checked, without and with the skill
Checked
Without skill
With skill
Outputs the exact tag → arsoc-organizing-framework
Missed
Passed
case-12 · 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.md70 linessingle file
Literature Synthesis (arsoc-literature-synthesis)
When to trigger
The topic was commissioned and it is time to read the subfield thoroughly
Reading feels unsystematic; you fear missing important contributions or a whole tradition
You have many studies but no way to weigh, compare, or reconcile their findings
A Committee/referee at ARSoc is likely to ask "why did you omit X / the Y literature / the qualitative work?"
Coverage discipline: read the subfield, not a convenience sample
An ARSoc review's credibility rests on the reader's belief that you read everything that matters across methods and schools. Sociology spans quantitative, qualitative, computational, and theoretical work, and reviewers notice when one mode is slighted. Build coverage systematically rather than from memory:
Seed set. Start from the field's canonical pieces and the references behind the commissioned topic.
Forward + backward snowball. Backward: every study's reference list. Forward: who cites the seeds (Google Scholar / Web of Science / Scopus). Iterate until new searches stop turning up unseen important work (saturation).
Database + keyword sweep. Search Sociological Abstracts, Web of Science, Scopus, JSTOR, and Google Scholar by topic keywords and by the names of the rival theoretical traditions, to catch work indexed under adjacent labels.
Mind-the-modes coverage. Deliberately sweep for qualitative and ethnographic work, computational / big-data studies, demographic analyses, and the theoretical statements, not only the quantitative articles you know best — siloing by method is a recurring ARSoc referee complaint.
Recent + adjacent. Include recent papers and forthcoming work (the frontier) and the bordering literatures the subfield draws on, or referees will flag staleness and siloing.
Saturation log. Record when each search stops yielding new must-cite work — this is your documented evidence of comprehensiveness for arsoc-comprehensiveness-and-balance and arsoc-transparency-and-reproducibility.
From reading to synthesis (not summary)
Summarizing is restating each study; synthesizing is making the studies talk to each other. Maintain an evidence matrix as you read:
Column
What to capture
Study
author–year, the result you will cite it for
Question/claim
exactly what it argues or measures (so non-comparable studies are not pooled)
Method/data
design, sample, mode (quant / qual / computational / theoretical) — so you can weight credibility
Finding
direction + magnitude, or the central claim (for who-found-what tables)
Tradition
which theoretical school / school it speaks for
Credibility
identification strength, sample, analytic transparency — your appraisal, since ARSoc runs no new analysis
Tension
which other studies it agrees/conflicts with, and why
This matrix is the raw material for the organizing framework, the summary tables, and the even-handed treatment of debates. Crucially, you appraise primary studies (you are the subfield's referee-of-record for the wider discipline); you do not re-analyze them.
Checklist
Seed set drawn from canonical pieces + the commissioned topic's references
Forward and backward snowball iterated to saturation