Use when responding to Cancer Cell (Cell Press) reviewer reports — planning new experiments, writing a point-by-point response, and calibrating claims for revision. It structures the rebuttal and revision; it does not run the experiments or design them from scratch.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 8/31/2026
What it changes
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill95%
Checks it passed that the model alone missed
Specifies executing the submission preflight check before resubmission.
Uses the header tag 【Decision】 to classify the manuscript revision status.
Requires specifying exact manuscript figure numbers for each itemized response.
and 3 more in the full report
5 fixed16 passed either way0 still failing1 broke
Pass-rate lift
+18 pp
Tokens
+29%
Agent turns
0%
Response time
-15%
Model gemini-3.6-flashMeasured 8/31/2026v121 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
We have completed all experimental revisions, updated the Key Resources Table, revised the text, deposited our RNA-seq data to GEO, and finalized the point-by-point response document for our Cancer Cell submission. What is the final operational step required prior to resubmitting the package?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies executing the submission preflight check before resubmission.
Missed
Passed
case-15 · gemini-3.6-flash · 8/31/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md119 linessingle file
Peer Review & Revision (cc-peer-review-revision)
When to trigger
A decision letter with reviewer reports has arrived (major/minor revision)
You must triage requested experiments vs. textual changes
Reviewers ask for additional in vivo / human validation or rigor fixes
A consultative / cross-referee comment requires reconciling reviews
Cell Press review context
Cancer Cell uses editorial assessment plus external peer review, and Cell Press can run consultative (cross-referee) review where reviewers see each other's comments. Practical implications:
Reviewers may converge on shared concerns — address the cross-cutting issue, not just each bullet.
The editor's letter signals which points are essential vs. optional; prioritize those.
New experiments that strengthen orthogonal validation (in vivo / human) carry the most weight.
Triage every comment
Reviewer ask
Response mode
"Does this hold in vivo / in patients?"
New experiment (highest priority) — plan via cc-study-design
"Cell line unauthenticated / antibody not validated"
Rigor fix — cc-reporting-standards
"n unclear / pseudo-replication / wrong test"
Reanalyze + report — cc-statistics
"Representative image without quantification"
Quantify across replicates — cc-figures-tables
"Overstated claim"
Narrow the claim — cc-writing-style
"Missing control / rescue"
Add control experiment
Disagreement / out-of-scope request
Respectful, evidence-based pushback
Point-by-point response structure
For each comment:
Quote the reviewer's point verbatim.
State the change: new data, reanalysis, or text edit.
Point to where in the revision it appears (new Figure 4C, Methods p. X, lines Y–Z).
If you disagree, give a courteous, data-backed rationale — do not ignore it.
Open the response with a brief summary of the major new experiments and how the paper improved. Keep tone professional and concrete; reviewers and editor read this closely.