Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when preparing or checking a Research Article for the journal Psychological Science: apply the journal's own submission spec — the combined word budget, the 150-word abstract content, references, exhibits, transparency statement, and open-science deposits — which cheaper models leave generic or get wrong.
.claude/skills/psci-submission-preflight/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 3 |
| Model | Lift | Δ tokens | Δ turns | Cases | Verified |
|---|---|---|---|---|---|
| gemini-3.6-flashbest | +45% | +48% | 0% | 22 | 54d ago |
| gemini-3.5-flash | pending re-run | — | |||
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | — | — |
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
Given a Research Article being prepared for the journal Psychological Science, state the journal's own submission requirements and check a manuscript against them. The numbers and placements below are the journal's fixed, non-default spec — apply them exactly, not generic "most journals" advice.
acknowledgments + appendices must together total no more than 2,000 words combined. These sections share ONE budget; they are not counted separately.
aim for 2,500 words or fewer for Method + Results together — but they do not count against the 2,000.
reference list. The limit is on the argument sections, not the whole document.
what matters is that Intro + Discussion (+ footnotes/acks/appendices) stays ≤ 2,000.
studied, and the important limitations of the research design. An abstract missing any of these three is non-compliant even if under 150 words.
editors can relax when more are genuinely needed, not a hard cap.
Psychological Association, 7th edition).
the point where they are first discussed — not collected at the end of the document.
not in the Method, not at the end. It does not count toward the word limit.
identifier (a DOI). Justified case-by-case exemptions are allowed, but the default is a public deposit.
repository with a persistent identifier before submission.
publicly accessible persistent identifier (DOI) to the preregistration.
1 January 2024 — the open-science requirements still apply, but do not expect badges.
names, affiliations, and identifying metadata removed, and mask repository / preregistration links (for example, use an OSF anonymized view) so they do not reveal the authors.
precision for the key tests.
mc.manuscriptcentral.com/psci.
BEFORE "Keep the whole manuscript under about 3,000 words." → AFTER "Introduction + Discussion (with footnotes, acknowledgments, appendices) ≤ 2,000 words combined; Method + Results are excluded from that count (aim ≤ 2,500 for those)."
BEFORE "Write a concise 200-word abstract summarizing aims, method, and findings." → AFTER "≤ 150 words, and it must name the sample sizes, the participant populations, and the key design limitation."
BEFORE "Place all tables and figures after the reference list." → AFTER "Embed each table and figure in the text near where it is first discussed."
BEFORE "Add a data-availability note at the end of the paper." → AFTER "Insert a Research Transparency Statement between the Introduction and the Method."
BEFORE "State that data are available from the authors on request." → AFTER "Deposit the data publicly and cite its DOI; do the same for the study materials."
Results are outside the 2,000-word budget.
inside the 2,000; the reference list and abstract are outside it.
justified reason; the default is public deposit with a DOI.
open-data / open-materials requirement.
appendices); DON'T count Method and Results in it, and DON'T use a total-manuscript limit.
ship a generic 200-word summary abstract.
Method or the end matter.
author-identifying links unmasked.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.5-flash | verified | 7/10/2026 | +62% |
Other measured skills in the registry, with their headline benchmark lift.