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 Framing

ASecurity

Use to lock the single narrative arc before drafting — converts a set of correct results into one Cell-shaped story that runs hypothesis → mechanism → significance, not a list of experiments.

1,052 stars
0 votes
0 copies
1 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-framing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cell Framing?

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

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

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

Download with Pro
Files
SKILL.md
---
name: cell-framing
description: Use to lock the single narrative arc before drafting — converts a set of correct results into one Cell-shaped story that runs hypothesis → mechanism → significance, not a list of experiments.
---

# Single-Narrative Framing (cell-framing)

## When to trigger

- The science is solid but the manuscript reads like three loosely related sub-projects.
- The introduction opens with paragraphs of background before any contribution.
- Reviewers/colleagues say "what's the one thing this paper shows?"
- You can list the results but not the single story they tell.

## Cell tells ONE story

A Cell Article is a single argument with a beginning, middle, and end:

> **Hypothesis / question → the mechanism we uncovered → why it matters broadly.**

Every figure is a chapter that advances this one arc. If a result does not serve the central story, it belongs in supplement or a different paper. Force the whole paper into one sentence:

> "We show that **[surprising mechanism]**, which explains **[phenomenon]** and means **[broad consequence]**."

If you cannot fill all three brackets without jargon, the framing is not ready — and possibly the story is not complete (`cell-fit`).

## The "complete story" expectation

Cell readers expect the arc to feel **airtight**: each claim is set up, tested with converging evidence, and alternatives are excluded before you move on. Map your figures to the arc:

1. **Fig. 1** — establish the phenomenon / set up the hypothesis.
2. **Figs. 2–3** — identify the mechanism (the molecular/cellular cause).
3. **Figs. 4–5** — perturb it both ways (loss + gain of function) to prove causality.
4. **Fig. 6+** — generality / in vivo relevance / the broad implication.

If a chapter is missing, the reviewers will ask for it — better to see the gap now.

## Cell introduction shape (≈3–4 short paragraphs)

1. **The broad problem** — what the field cannot yet explain, framed for a general life-scientist.
2. **The specific gap / hypothesis** — what is unknown and the question you pose.
3. **Why now / why tractable** — the tool, system, or idea that finally lets you answer it.
4. **What we found** — the advance in plain terms, ending on the broad implication. The reader knows your mechanism before Results.

## The "why now" hooks

Name explicitly which applies:

- [ ] A new tool/system (CRISPR screen, cryo-EM, single-cell, organoid) made the mechanism testable.
- [ ] A longstanding paradox in the field is now resolvable.
- [ ] A clinically/biologically urgent problem makes the mechanism timely.
- [ ] A prediction from a model is now directly testable.

## Title discipline

- **Declarative and specific**: "Protein X drives Y by mechanism Z" beats "Insights into Y."
- The noun phrase carries the mechanism, not just the system.
- Avoid "Towards", "A study of", "Characterization of", "Novel".
- Cell titles are short and often name the molecular actor and the effect.

## Narrative anti-frames (rewrite these)

| Anti-frame                                   | Reframe                                                |
|----------------------------------------------|--------------------------------------------------------|
| "We characterized protein X."                | "Protein X gates process Y — a previously unknown control point." |
| "Here we report several findings on…"        | "We define the mechanism by which… "                   |
| Three parallel mini-stories                  | One arc; demote side-results to supplement             |
| "Our data are consistent with model M."      | "Our perturbations decide between models, favoring M." |

## Output format

```
【One-sentence story】 "We show that ... which explains ... and means ..."
【Figure-to-arc map】 phenomenon / mechanism / causality (LOF+GOF) / generality
【Why-now hook】 which applies
【Intro skeleton】 problem / gap / why-now / advance+implication
【Working title】 declarative, names the actor + effect
【Risk】 any chapter of the arc missing? (→ cell-fit)
【Next】 cell-writing
```

## Anti-patterns

- **Do not** present parallel mini-stories — Cell wants one arc.
- **Do not** bury the advance below background; the mechanism belongs in the first paragraphs.
- **Do not** inflate with "novel/unprecedented" — show the mechanism, don't label it.
- **Do not** keep results that don't serve the central story in the main text.

> Confirm structural expectations against current Cell Press author guidelines.

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 →