Use when triaging a study before any writing — stress-tests whether it clears Cell's bar (a complete, mechanistic, hypothesis-driven story with multiple converging lines of evidence) or belongs at a sibling. Use this first to decide Cell vs Molecular Cell vs Cell Reports vs Cell Reports Medicine before investing in framing or figures.
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/31/2026
What it changes
Passed 19 of 22 test cases with the skill, and 14 of 22 without it.
Without skill64%
With skill86%
Checks it passed that the model alone missed
Assigns significance rung 4
Assigns significance rung 1
Assigns significance rung 5
and 5 more in the full report
5 fixed14 passed either way3 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+13%
Agent turns
0%
Response time
-26%
Model gemini-3.6-flashMeasured 8/31/2026v119 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 completed a study identifying a protein complex that repairs DNA-protein crosslinks during replication. We demonstrated mechanism via reconstituted biochemistry, gene-edited cell line knockouts/rescues, and sensitivity assays across multiple DNA damaging agents. Could you run a scope and fit assessment for us? Please format the output as follows:
- Significance rung (1-5) with brief justification
- Complete-story test results for phenomenon, mechanism, convergence, causality, and significance
- Presence of any fatal triggers
- Recommended target venue
- One-line conceptual advance if targeting Cell
- Recommended gap-closing experiment
- Next step (e.g., framing vs reconsidering venue)
What was checked, without and with the skill
Checked
Without skill
With skill
Assigns significance rung 4
Missed
Passed
Recommends Cell as primary target venue
Missed
Passed
case-03 · 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.md75 linessingle file
Scope & Significance Fit (cell-fit)
Why this is skill #1
Cell triages most submissions to rejection without external review. The gate is not "is it correct" and not even "is it a striking result" — it is "is this a complete, mechanistic story of broad importance to the life sciences." A single beautiful observation with no mechanism is desk-rejected. Run this before investing in prose.
When to trigger
Before drafting, to decide if Cell is even the right Cell Press venue.
When a co-author says "this is a Cell paper" and you need a sober second opinion.
When choosing between Cell, Molecular Cell, Cell Reports, Cell Reports Medicine, and Nature/Science.
The "complete story" test
Cell wants a hypothesis-driven narrative where multiple independent lines of evidence converge on a mechanism and a clear conceptual advance. Ask:
Phenomenon: is the central finding established robustly (not one assay)?
Mechanism: do you explain how it works at a molecular/cellular level — not just that it happens?
Convergence: do genetics + biochemistry + cell biology + (in vivo, where relevant) point the same way?
Causality: loss-of-function and gain-of-function (or equivalent perturbation pair) where feasible?
Significance: does it change how a broad community thinks, beyond your subfield?
If any of mechanism / convergence / causality is missing, it is likely not yet a Cell paper — name what experiment closes the gap.
Significance ladder (weak → strong)
Describes a phenomenon with no mechanism. (Weak — not Cell.)
Extends a known mechanism to a new system incrementally. (Borderline — Cell Reports.)
Defines a new mechanism within an established framework. (Strong — Molecular Cell or Cell.)
Reveals a previously unknown mechanism / pathway / principle, fully worked out. (Strong — Cell.)
Overturns or unifies a textbook model with decisive, multi-angle evidence. (Strongest — Cell.)
If you cannot place the work at rung 4+ with completeness, Cell is a long shot — be honest and name the realistic Cell Press venue.
Fatal pre-review-reject triggers
Descriptive only: a phenotype or correlation with no mechanism.
Single line of evidence: one technique carrying the whole claim.
Incremental over the authors' own prior paper.
Mechanism asserted, not demonstrated (a model cartoon unsupported by perturbation).