Use when running the final pre-submission preflight for Cognitive Psychology (Elsevier) via Editorial Manager — scope/length fit, abstract and keywords, APA-style reporting, model-comparison completeness, reproducible model/analysis code, and the Elsevier research-data and competing-interest declarations. Final checks; it does not draft content. Verify volatile specifics on the official guide for authors.
SkillScore58Maintained
Automatic
◆Research pack
Last verified 9/1/2026
What it changes
Passed 15 of 26 test cases with the skill, and 4 of 26 without it.
Without skill15%
With skill58%
Checks it passed that the model alone missed
The response outputs the five bracketed categories.
The response maintains the required bracketed schema.
The response uses the required five bracketed header schema.
and 21 more in the full report
12 fixed3 passed either way10 still failing1 broke
Pass-rate lift
+42 pp
Tokens
+19%
Agent turns
0%
Response time
-35%
Model gemini-3.6-flashMeasured 9/1/2026v115 of 26 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
Review my submission details for Cognitive Psychology and output the five bracketed checks with [Y/N] and the final action line. Details: A single reaction time experiment showing a 15ms priming difference across 30 participants. Standard APA formatting used. Data uploaded on GitHub as a CSV. No formal model or computational fitting was conducted.
What was checked, without and with the skill
Checked
Without skill
With skill
The response evaluates 【Shape】 with [N] because a single-effect experiment without modeling lacks the required long-form theoretical scope.
Missed
Passed
The response evaluates 【Modeling】 with [N] due to the lack of model comparison and recovery.
Missed
Passed
case-04 · gemini-3.6-flash · 9/1/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md113 lines2 files
Submission Preflight (cogpsych-submission)
The last check before submitting through Elsevier Editorial Manager. Two things sink Cognitive
Psychology submissions most often: a wrong-shape contribution (single effect, no model/theory, or a
model that is never compared) and non-reproducible modeling (fits that can't be regenerated, no code
deposit). Verify volatile specifics (length, abstract limit, review model, current editor, declarations)
on the official guide for authors first (检索于 2026-06；以官网为准).
When to trigger
"Submitting tomorrow" — last pass before upload
Unsure what the scope, format, and declaration requirements demand
Confirming the abstract, exhibits, model comparison, code deposit, and declarations are in order
Process facts (verify volatile items on the official page)
Owner / publisher: Elsevier. (检索于 2026-06；以官网为准)
Portal:Elsevier Editorial Manager (linked from the ScienceDirect guide for authors).
Identity: a leading cognitive-science journal favoring longer, integrative, model-driven
articles; multi-experiment programs combined with formal/computational modeling.
Scope: attention, perception, memory, learning, language, categorization, reasoning,
problem-solving, judgment and decision-making; modeling/neuroscientific approaches and substantive
reviews welcome.
Style: APA-style statistical reporting and references; Elsevier formatting via the guide for
authors. Confirm the current reference style and any structured-abstract requirement.
Open science: authors are strongly encouraged to share data, model/analysis code, and
materials; complete the Elsevier research-data statement and declaration of competing
interest.
Review model / length / abstract limits: volatile — confirm single- vs. double-anonymized review,
any word/length guidance, and the abstract limit on the live page. 待核实.
Preflight checklist
Scope & shape
Contribution is a theoretical advance carried by a program (multi-experiment and/or a model)
If a model is central, it is fit and compared to a rival under matched flexibility
Not a single-effect / atheoretical paper better suited to a short-report venue
Front matter & format
Abstract present (confirm length/structure on the official page); keywords included