Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/arpsych-writing-style
Use when drafting or polishing prose for an Annual Review of Psychology (ARPsych) review so it lands the authoritative-yet-accessible house voice for a broad psychology readership. Shapes voice, abstract, and intro; it does not design the spine (arpsych-organizing-framework) or run final checks (arpsych-submission).
Passed 21 of 22 test cases with the skill, and 14 of 22 without it.
and 7 more in the full report
7 fixed14 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am finishing up a co-authored review paper on working memory capacity for a broad psychology audience, but it currently reads like a dry grant application with lists of individual studies. Can you evaluate my draft's prose to ensure it fits Annual Review style standards? Please provide a checklist assessment evaluating our writing register for non-specialists, whether the core argument drives each section, if technical terms are introduced properly, whether our certainty claims are well-calibrated, if the abstract/intro sequence is correctly handled, whether future research gaps are thoroughly addressed, if our multi-author voices are unified, and what our next workflow step should be.
| Checked | Without skill | With skill |
|---|---|---|
| Recommends balancing authoritative expertise with accessibility for adjacent field readers | Passed | Passed |
| Advises organizing section narratives around theoretical mechanisms rather than study lists | Passed | Passed |
| Recommends evaluating reporting transparency and open data practices as the next step | Missed | Passed |
The instructions your model reads when the skill loads.
ARPsych reviews are read across all of psychology and by adjacent fields. The register is authoritative but accessible: written by a leading expert, readable by a smart psychologist outside the subfield, and usable in a graduate seminar. The two failure poles are (1) a dense specialist treatise only insiders can parse, and (2) a chatty overview with no analytical edge. Aim between them: deep but legible.
| Principle | In practice |
|---|---|
| Argument forward | Every section advances the spine; the reader always knows where they are in the framework |
| Define on first use | Spell out constructs, paradigms, and acronyms for the adjacent reader |
| Show the mechanism | Explain why an effect occurs, not just that N studies found it |
| Synthesize, don't list | Discuss cell-defining work; cluster confirmatory studies in citations |
| Calibrated confidence | "Robust", "mixed", "contested", "unknown" used precisely (ties to balance) |
| Active, concrete prose | Prefer plain verbs over nominalizations; one idea per sentence |
The introduction must promise exactly what the review delivers — so write it once the spine is final. A strong ARPsych intro:
The abstract is the most-read paragraph: organizing question, the framework, the headline synthesis, and the open agenda — no method-section throat-clearing.
ARPsych reviews are expected to end by pointing forward: the open questions, the methodological needs, the contradictions awaiting resolution — ideally the empty cells of your framework (检索于 2026-06；以官网为准). This section is a large part of why the field reads the review; it is not a perfunctory wrap-up.
A co-authored review must read as one author. Assign a single integrator to do a unifying pass; differing section voices are a common reviewer complaint.
test cases passed, vs 14 / 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.