Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/arsoc-organizing-framework
Use when imposing an analytical structure or taxonomy on a sociology literature for an Annual Review of Sociology (ARSoc) review — the "spine" that turns a reading list into an argument about the subfield. Designs the framework; it does not gather the literature (arsoc-literature-synthesis) or judge balance (arsoc-comprehensiveness-and-balance).
Passed 20 of 22 test cases with the skill, and 8 of 22 without it.
and 14 more in the full report
14 fixed6 passed either way0 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
I've compiled a set of 30 papers for a sociology literature review on platform capitalism and gig labor, but right now my outline reads like a study-by-study list of summaries. I need to move past an annotated bibliography and establish a strong conceptual framework that gives this subfield a clear spine. Please analyze my topic and produce a structured organizing plan. In your response, format the output with the following sections: 【Spine type】 【Argument about the subfield】 【Categories】 【Reconciliation】 【Open questions】 【Hard-case test】 【Next step】
| Checked | Without skill | With skill |
|---|---|---|
| The Spine type field selects a single option from taxonomy, mechanism, levels-of-analysis, question-sequence, or paradigm-debate. | Missed | Passed |
| The argument about the subfield is stated in exactly one sentence. | Passed | Passed |
| The hard-case test evaluates placement for 5 hard-case or awkward studies. | Missed | Passed |
The instructions your model reads when the skill loads.
The single most-cited reason ARSoc reviews disappoint is that they are annotated bibliographies: study-after-study summaries with no organizing idea. A great ARSoc review imposes a structure the subfield did not have — a taxonomy, a unifying mechanism, a sequence of questions, or a simple analytic model — that makes scattered work legible to a sociologist from another area. The framework is the contribution; the citations are the evidence. Choose the spine deliberately:
| Spine type | Organizes the subfield by | Best when |
|---|---|---|
| Taxonomy | mutually-exclusive categories of mechanism / theoretical approach | the area is fragmented into incommensurable camps |
| Mechanism / process | the causal or social process linking inputs to outcomes | results disagree because they tap different stages of one process |
| Levels of analysis | micro / meso / macro, or individual / organizational / institutional | the field spans levels and the lesson is how they connect |
| Question sequence | a logical chain of sub-questions | the area has a natural "first we must know X, then Y" order |
| Paradigm / debate | rival theoretical traditions and what divides them | the contest of perspectives is itself the subfield's structure |
Pick one primary spine; a second axis can be a within-section ordering, but a review with two competing spines reads as two reviews.
Stress-test by trying to place 5 hard cases (studies that resist categorization). If three of them have no home, the spine is wrong — redesign before drafting.
The framework is also what lets you be selective without being incomplete: once each cell is defined, confirmatory studies can be cited in clusters within their cell while the prose discusses only the cell-defining work. A review without a spine cannot do this — it must either summarize everything (bloat) or omit silently (gaps). Design the spine before you decide what to foreground, and note which cells are thin — those become the research agenda the ARSoc voice closes on.
test cases passed, vs 8 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.