Use when you need to understand how Cognitive Psychology (Elsevier) evaluates a manuscript — editorial triage for theoretical impact and fit, expert review weighing model rigor, recovery, design, and reproducibility, and the long revision cycles typical of a model-driven journal. Use when stress-testing a paper before submission or interpreting a decision letter. Sets expectations and shapes the paper to survive review; it does not contact editors.
SkillScore80Maintained
Automatic
◆Research pack
Last verified 9/1/2026
What it changes
Passed 20 of 25 test cases with the skill, and 8 of 25 without it.
Without skill32%
With skill80%
Checks it passed that the model alone missed
Output includes the line header 【Realistic outcome】
Output specifies cogpsych-rebuttal in the 【Next】 line
Output specifies cogpsych-submission in the 【Next】 line
and 13 more in the full report
15 fixed5 passed either way2 still failing3 broke
Pass-rate lift
+48 pp
Tokens
+4%
Agent turns
0%
Response time
-37%
Model gemini-3.6-flashMeasured 9/1/2026v120 of 25 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
Cognitive Psychology returned a Minor Revision decision on our model-driven paper. Reviewers requested a minor sensitivity analysis for hyperpriors and additional comments in our R code script. Please produce the standard review assessment checklist for this stage and specify the next action.
What was checked, without and with the skill
Checked
Without skill
With skill
Output classifies the realistic outcome as minor revision
Passed
Passed
Output specifies cogpsych-rebuttal in the 【Next】 line
Missed
Passed
case-15 · 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.md100 linessingle file
Review Process (cogpsych-review-process)
Cognitive Psychology combines selectivity for theoretical impact with deep methodological and
modeling scrutiny. Reviewers and editors weigh not only whether the finding is interesting, but
whether the model is well-specified, identifiable, and properly compared, whether the experiments
discriminate the accounts, and whether the work is reproducible. Knowing this lets you pre-empt
the common rejection reasons. Confirm the current process on the official page (检索于 2026-06；以官网为准).
When to trigger
Before submitting, to stress-test the manuscript
Interpreting a decision letter and setting expectations
Deciding how to fit a long, model-driven program to a demanding review
How review works (typical Elsevier journal pattern)
Editorial triage. A handling editor assesses theoretical impact, scope, and fit; thin,
single-effect, or atheoretical submissions may be rejected without external review at this
long-form, model-driven venue.
Expert peer review. Typically multiple referees with cognitive-modeling and experimental
expertise. Expect detailed scrutiny of model specification, identifiability/recovery, model
comparison, experimental confounds, and the strength of the inference.
Reproducibility is checked. Reviewers may attempt to run model/analysis code; fits that don't
regenerate, or undocumented model choices, weaken the paper (see
cogpsych-open-science-and-transparency).
Decisions and cycles. Reject, major/minor revision, or accept; integrative model-driven papers
often go through substantial, sometimes multiple, revision rounds — added experiments, recovery
analyses, or model comparisons are common requests.
Verify the review model (single- vs. double-anonymized), referee count, and timelines on the journal's
current guide for authors — these are volatile (检索于 2026-06；以官网为准).
Shape the paper to pass
Make the theoretical advance explicit and early; show the experiments discriminate the models.
Fit and compare models under matched flexibility; include parameter and model recovery.
Respect the data hierarchy (mixed/hierarchical models) and report effect sizes with intervals.
Make the modeling reproducible from deposited code; complete Elsevier declarations.
Separate confirmatory from exploratory model work honestly.