Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/arpsych-organizing-framework
Use when imposing an analytical structure or taxonomy on a psychology literature for an Annual Review of Psychology (ARPsych) review — the "spine" that turns a reading list into an argument about the field. Designs the framework; it does not gather the literature (arpsych-literature-synthesis) or judge coverage and balance (arpsych-comprehensiveness-and-balance).
Passed 22 of 22 test cases with the skill, and 4 of 22 without it.
and 20 more in the full report
18 fixed4 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have finalized the primary spine, MECE categories, reconciliation, and stress testing for my review paper on spatial navigation in rodents and humans. Complete the framework block and specify the exact next procedural step.
| Checked | Without skill | With skill |
|---|---|---|
| Includes the key 【Next step】. | Passed | Passed |
| Outputs the pointer → arpsych-comprehensiveness-and-balance (cover the cells fairly). | Missed | Passed |
The instructions your model reads when the skill loads.
The most-cited reason review articles fail is that they are annotated bibliographies: study-after-study summaries with no organizing idea. A great ARPsych review imposes a structure the field did not have — a taxonomy, a unifying model, a sequence of questions, or a process diagram — that makes scattered work legible to a psychologist from an adjacent area. The framework is the contribution; the citations are the evidence. ARPsych's accessibility mandate raises the bar: the spine must be graspable by a non-specialist psychologist (a social psychologist reading a memory review) on one read. Choose it deliberately:
| Spine type | Organizes the field by | Best when |
|---|---|---|
| Taxonomy | mutually-exclusive categories of mechanism/construct | the field is fragmented into incommensurable subliteratures |
| Process model | stages of a mechanism (input → process → output) | the topic is a pathway (e.g., emotion generation, encoding→retrieval) |
| Levels of analysis | from neural to behavioral to social | the value is integrating across explanatory levels |
| Question sequence | a logical chain of sub-questions | the field has a natural "first know X, then Y" order |
| Paradigm/era | how thinking evolved and why | the evolution of ideas is itself the lesson |
| Theory contest | rival accounts of the same phenomenon | progress hinges on adjudicating competing theories |
Pick one primary spine; a second axis can order studies within a section, but a review with two competing spines reads as two reviews.
Stress-test by placing 5 hard cases (studies that resist categorization). If three have no home, the spine is wrong — redesign before drafting.
The spine is also what lets an ARPsych review 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. This is how you honor coverage and the assigned-length envelope at once (检索于 2026-06；以官网为准). Design the spine before deciding what to foreground.
test cases passed, vs 4 / 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.