Use when writing the response to a Cognitive Psychology (Elsevier) major/minor revision. Reviews here often demand added experiments, more model comparisons, recovery analyses, or fuller reproducibility, so the response must address every point and strengthen the model-driven inference. Structures the response letter; it does not fabricate new results or model fits.
SkillScore87Maintained
Automatic
◆Writing & Editing pack
Last verified 9/1/2026
What it changes
Passed 20 of 23 test cases with the skill, and 8 of 23 without it.
Without skill35%
With skill87%
Checks it passed that the model alone missed
Report penalized model comparison across all candidate models.
Fit additional candidate rival models under matched flexibility.
Summarize the parameter recovery result in one main-text sentence.
and 13 more in the full report
12 fixed8 passed either way3 still failing0 broke
Pass-rate lift
+52 pp
Tokens
+46%
Agent turns
0%
Response time
+0%
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
Reviewer 1 asked where the updated model code and raw data for the new model recovery simulations can be verified. Should we paste the 500 lines of code into an appendix, or record it in an Open Practices statement? Draft a response entry with 'Response:' and 'Change:' lines.
What was checked, without and with the skill
Checked
Without skill
With skill
Reference the deposited code repository location in the Open Practices statement.
Passed
Passed
State that code execution reproduces model fits and recovery in a fresh session.
Missed
Passed
case-23 · 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.md114 linessingle file
Revision Rebuttal (cogpsych-rebuttal)
A Cognitive Psychology revision typically asks for more modeling rigor — an additional
experiment, a further model comparison, parameter/model recovery, alternative priors, or reproducible
code — because the contribution is a model-driven theoretical claim. The response letter must convert
every reviewer and reassure the editor that the model adjudication is now airtight, while keeping
the integrative argument coherent.
When to trigger
A major/minor revision arrived and you are planning the revision + response letter
Reviewers requested added experiments, model comparisons, recovery, or open-code changes
A requested analysis or model would change the conclusion
Writing the cover note to the handling editor
Strategy
Read the editor's letter as the rubric. Solve the decisive points first; the editor adjudicates
among reviewers and decides the next round.
Point-by-point, every comment. Quote each comment, then respond; never skip one.
Strengthen the model inference, don't just defend. Many requests (fit a further rival, add
recovery, cross-validate, refit hierarchically, share code) make the adjudication stronger — do them
and say where. A request that exposes overfitting must be addressed, not waved away.
Keep the program coherent. A new experiment or model should slot into the argument; update the
General Discussion so the synthesis still holds (see cogpsych-writing-style).
Concede or rebut with evidence. Did what was asked (cite the location), or push back respectfully
with a reason (e.g., why a requested model is not identifiable) — don't add an analysis that quietly
undercuts the claim without saying so.
Keep the modeling reproducible. New analyses must be reflected in the deposited model/analysis
code and regenerate in a fresh session (see cogpsych-open-science-and-transparency).
Response-letter format
For each reviewer comment:
> [Quoted reviewer comment]
Response: [What we did / why we respectfully disagree].
Change: [Manuscript section, supplement/appendix section, table/figure, or
Use when writing the response to a British Journal of Political Science (BJPS) revise-and-resubmit. The response must convert each of the (usually two-plus) double-blind referees while keeping the editor confident the revision is convergent. Structures the response letter; it does not fabricate new results.