Use when deciding whether a cognition project fits Cognitive Psychology (Elsevier) and what contribution shape to target. The journal favors longer, integrative, model-driven work that produces a substantial theoretical advance — not a single isolated effect. Frames the question and the model-or-theory payoff; it does not collect data.
SkillScore77Maintained
Automatic
◆Research pack
Last verified 9/1/2026
What it changes
Passed 17 of 22 test cases with the skill, and 12 of 22 without it.
Without skill55%
With skill77%
Checks it passed that the model alone missed
Marks the scope field 【Scope】 as N.
Marks the scope field 【Scope】 as Y.
Includes the field header 【Fit verdict】 in the output.
and 6 more in the full report
5 fixed12 passed either way5 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+34%
Agent turns
0%
Response time
-22%
Model gemini-3.6-flashMeasured 9/1/2026v117 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Assess a project on reinforcement learning in decision making with 2 experiments and a fit Q-learning model, with open data. Please provide the fit assessment formatted with the required bracketed fields: Question/phenomenon, Theoretical advance, Scope, Formal backbone, Reproducible, Type, Fit verdict, and Next step.
What was checked, without and with the skill
Checked
Without skill
With skill
Marks the scope field 【Scope】 as Y.
Missed
Passed
Marks the formal backbone field 【Formal backbone】 as Y.
Missed
Passed
case-19 · 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.md111 linessingle file
Topic Selection & Fit (cogpsych-topic-selection)
Cognitive Psychology publishes longer, integrative articles that have a major impact on theories of
cognition. The bar is a substantial theoretical advance — usually carried by a multi-experiment
program tied to a formal/computational model, an incisive experimental series, or a modeling/review
contribution. Use this skill to pressure-test fit before investing.
When to trigger
Choosing among possible projects or framings for Cognitive Psychology
A reader said the work feels "one effect," "atheoretical," or "better as a short report"
Deciding whether the contribution needs a formal model, more experiments, or both
A modeling or review project you want to place
The fit test
A strong Cognitive Psychology paper usually clears all four:
Theoretical advance, not an effect. It changes a theory of cognition — adjudicates between
accounts, formalizes a mechanism, or maps a phenomenon's boundary — rather than adding one more
demonstration. State the theory it moves.
Integrative scope. The contribution is carried by a program (multiple experiments and/or a
model fit to data), not a single study. Each piece must add inference.
Formal/computational backbone where apt. Cognition here is often expressed as a model that is
fit and compared; if your account can be formalized, the venue rewards doing so (see
cogpsych-theory-and-hypotheses).
Reproducible and shareable. You can deposit data, model/analysis code, and materials so the
modeling is reproducible (see cogpsych-open-science-and-transparency).
Contribution shape
Multi-experiment empirical — a controlled series that jointly constrains a theory (each
experiment rules out an alternative or extends scope).
Experiment + model — the journal's signature shape: experiments designed to discriminate models,
with a formal model fit to the data and compared to rivals.
Modeling-led — a new model (or analysis) tested by fitting, model recovery, and comparison
against existing or new data.
Theoretical / integrative review — a synthesis that delivers a substantive theoretical advance,
not a literature catalogue.