Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Cell Fit

ASecurity

Use first, before any writing, to stress-test whether a study clears Cell's bar — a complete, mechanistic, hypothesis-driven story with converging evidence. Decides Cell vs Molecular Cell vs Cell Reports vs Cell Reports Medicine.

1,052 stars
0 votes
0 copies
0 views
Added 6/4/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill cell-fit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cell Fit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cell Fit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-cell-fit/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-cell-fit)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: cell-fit
description: Use first, before any writing, to stress-test whether a study clears Cell's bar — a complete, mechanistic, hypothesis-driven story with converging evidence. Decides Cell vs Molecular Cell vs Cell Reports vs Cell Reports Medicine.
---

# 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)

1. **Describes** a phenomenon with no mechanism. (Weak — not Cell.)
2. **Extends** a known mechanism to a new system incrementally. (Borderline — Cell Reports.)
3. **Defines** a new mechanism within an established framework. (Strong — Molecular Cell or Cell.)
4. **Reveals** a previously unknown mechanism / pathway / principle, fully worked out. (Strong — Cell.)
5. **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).
- **Over-claiming**: conclusion outruns the data (top post-review rejection reason).
- **Scope mismatch**: deep but narrow molecular detail with no broad lesson → Molecular Cell, not Cell.

## Venue routing within Cell Press and beyond

| Situation                                                          | Recommend                |
|--------------------------------------------------------------------|--------------------------|
| Rung 4–5, complete mechanism, broad, converging evidence           | **Cell** (Article)       |
| Deep **molecular** mechanism, rigorous, narrower domain            | **Molecular Cell**       |
| Solid and complete but less broadly transformative                 | **Cell Reports** (more accepting) |
| Translational / clinical complete story                            | **Cell Reports Medicine** |
| Developmental / cell-bio mechanism, strong but specialist          | **Developmental Cell** / field journal |
| Complete and broad but you want the widest general audience        | also consider **Nature / Science** |
| Strong but mechanism incomplete                                    | add perturbation experiments before submitting |

## Output format

```
【Significance rung】 1–5 + one-line justification
【Complete-story test】 phenomenon / mechanism / convergence / causality / significance → which are met
【Fatal triggers present】 [...]
【Recommended venue】 Cell / Molecular Cell / Cell Reports / Cell Reports Medicine / Dev Cell / Nature-Science
【If staying with Cell, the one-line conceptual advance】 "..."
【Gap-closing experiment, if any】 ...
【Next】 cell-framing (if pass) | reconsider venue (if fail)
```

## Anti-patterns

- **Do not** mistake a striking observation for a complete story — Cell wants the mechanism worked out.
- **Do not** rationalize a single-technique result into "multiple lines of evidence" with adjectives.
- **Do not** confuse technical difficulty or data volume with conceptual significance.
- **Do not** let sunk cost drive the venue decision; Cell Reports is an honest landing spot.

> Confirm scope expectations against current Cell Press author guidelines and recent Cell issues.

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693161 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →