Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/arecon-organizing-framework
Use when imposing an analytical structure or taxonomy on a literature for an Annual Review of Economics (ARE) review — the "spine" that turns a reading list into an argument about the field. Designs the framework; it does not gather the literature (arecon-literature-synthesis) or appraise evidence and balance (arecon-evidence-standards).
Passed 21 of 23 test cases with the skill, and 6 of 23 without it.
and 18 more in the full report
16 fixed5 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
After finalizing my organizing framework and confirming category fit for a review on health economics mandates, what specific skill or step comes next in the review pipeline?
| Checked | Without skill | With skill |
|---|---|---|
| The response identifies arecon-evidence-standards as the next pipeline step. | Missed | Passed |
| The output includes the tag 【Next step】. | Missed | Passed |
The instructions your model reads when the skill loads.
The most-cited reason review articles fail is that they are annotated bibliographies: paper-after-paper summaries with no organizing idea. A great ARE review imposes a structure the field did not have — a taxonomy, a unifying framework, a sequence of questions, or a simple model — that makes scattered work legible to an economist from an adjacent field. The framework is the contribution; the citations are the evidence. ARE's accessibility mandate raises the bar further: the spine must be graspable by a non-specialist on one read. Choose it deliberately:
| Spine type | Organizes the field by | Best when |
|---|---|---|
| Taxonomy | mutually-exclusive categories of mechanism/approach | the field is fragmented into incommensurable camps |
| Unifying model | a simple framework whose parameters index the studies | results disagree because they estimate different parameters of one structure |
| Question sequence | a logical chain of sub-questions | the field has a natural "first know X, then Y" order |
| Chronological/paradigm | how thinking evolved and why | the evolution of ideas is itself the lesson |
| Methods spectrum | from least to most credible designs | the review's value is appraising what is actually known |
Pick one primary spine; a second axis can order papers within a section, but a review with two competing spines reads as two reviews.
Stress-test by placing 5 hard cases (papers that resist categorization). If three have no home, the spine is wrong — redesign before drafting.
The spine is also what lets an ARE 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 ~25–40-page accessibility 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 6 / 23 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.