Use when drafting or polishing a Cognitive Psychology (Elsevier) manuscript — a long-form, integrative article that must weave multiple experiments and a formal model into one continuous theoretical argument. Tightens structure, the experiment-to-model narrative, and APA-style reporting; it does not invent content. Verify the journal's current length and format guidance on the official page.
SkillScore87Maintained
Automatic
◆Writing & Editing pack
Last verified 9/1/2026
What it changes
Passed 20 of 23 test cases with the skill, and 10 of 23 without it.
Without skill43%
With skill87%
Checks it passed that the model alone missed
Output includes "【Reporting】"
Output includes "【Model integrated】"
Output includes "【Experiments cohere】"
and 8 more in the full report
12 fixed8 passed either way1 still failing2 broke
Pass-rate lift
+43 pp
Tokens
+34%
Agent turns
0%
Response time
-14%
Model gemini-3.6-flashMeasured 9/1/2026v120 of 23 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
I am preparing a manuscript for Cognitive Psychology that combines four psychophysics experiments with a formal decision-making model. I want to make sure the manuscript doesn't read like a list of separate studies and that the computational model isn't treated as a standalone section. Could you review my structural outline below and evaluate it? Please output your feedback using the standard diagnostic checklist format, marking bracketed sections with [Y/N] for front-loaded theoretical claims, experimental narrative cohesion, model integration, discussion synthesis, and statistical reporting rigor, and finish with the next skill step tag.
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends front-loading theoretical claims and rival accounts in the Introduction before Experiment 1.
Passed
Passed
Output includes "【Next】cogpsych-open-science-and-transparency"
Missed
Passed
case-01 · 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.md99 linessingle file
Writing Style (cogpsych-writing-style)
Cognitive Psychology publishes longer, integrative articles, so the challenge is the opposite of a
short-report journal: the danger is not the word limit but losing the argument across many
experiments and a model. Writing well here means making a multi-experiment program plus a formal
model read as one cumulative theoretical argument, in clear scientific prose with rigorous
(APA-style) statistical reporting.
When to trigger
Drafting the Introduction/General Discussion or doing a structural pass
A series of experiments reads as a list rather than a single argument
Integrating the model exposition with the empirical sections
Aligning statistical reporting and references to the journal's style before submission
Writing the long-form, model-driven paper
Front-load the theoretical claim. State the question, the rival accounts, and the contribution in
the Introduction (see cogpsych-literature-positioning). The reader should know what is at stake
before Experiment 1.
Make each experiment a step in the argument. Open each experiment with the specific question it
answers and what it adds (rules out a confound, tests a divergent prediction); close with a brief
bridge to the next. Avoid a flat "Experiment N: Method/Results" list.
Integrate the model, don't append it. Introduce the model where it does explanatory work — often
alongside the experiments it explains — not as a detached final section the empirical reader skips.
General Discussion earns its length. Synthesize across experiments and the model fit; state the
theoretical advance and its scope; keep limitations honest. This is where the integrative payoff is
delivered, not a restatement of each Results section.
Report statistics rigorously. Effect sizes with intervals for behavior, model-comparison criteria
for fits, exact test statistics; APA-style author-date citations and reference formatting. Confirm
the current style requirements on the official guide for authors.
Structure that keeps a multi-experiment paper coherent
Use when analyzing data and fitting/comparing models for a Cognitive Psychology (Elsevier) manuscript. The journal expects principled model fitting and comparison (AIC/BIC/Bayes factors), parameter and model recovery, (generalized) linear mixed models or hierarchical Bayesian estimation where apt, and effect sizes with uncertainty — all reproducible from shared code. Guides the analysis and modeling; it does not fabricate results.