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 Summary

ASecurity

Use to write Cell's Summary — a single unstructured paragraph of ≤ ~150 words that conveys the complete story, the mechanism, and the broad significance, quantified and readable by a general life-scientist. Late-stage polish.

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

Security Analysis

A100/100

Scanned 6/4/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Cell Summary?

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

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

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

Download with Pro
Files
SKILL.md
---
name: cell-summary
description: Use to write Cell's Summary — a single unstructured paragraph of ≤ ~150 words that conveys the complete story, the mechanism, and the broad significance, quantified and readable by a general life-scientist. Late-stage polish.
---

# Summary / Abstract (cell-summary)

## When to trigger

- Significance, framing, and structure are settled (do this late).
- The abstract reads like a method recap with no mechanism or result.
- It exceeds ~150 words, uses subheadings, or is dense with acronyms.
- It states *that* something happens but never *how* (no mechanism).

## What Cell calls it

Cell's abstract is the **Summary**: a **single, unstructured paragraph** (no subheadings, no citations) of roughly **≤150 words**, written for a broad life-sciences readership — not your subfield. It must convey the **complete story**: the question, the mechanism, and why it matters, with quantification.

## Five-move structure (no labels in the text)

1. **Context / stakes** (1 sentence) — the broad biological problem.
2. **Gap / question** (1 sentence) — what was unknown.
3. **What we did + what we found** (2–3 sentences) — the mechanism, with the key quantified results and the converging evidence that makes it a complete story.
4. **Mechanism stated explicitly** — name the molecular/cellular cause, not just the phenotype.
5. **Significance** (1 sentence) — why a broad community should care.

Because Cell demands completeness, the Summary should make clear that the mechanism is *established*, not merely proposed — convey that multiple lines of evidence converge.

## Hard constraints

- [ ] ≤ ~150 words (treat 150 as the ceiling; confirm the current cap).
- [ ] Single paragraph; **no subheadings, no citations**, no figure/table references.
- [ ] Define any acronym on first use, or avoid it.
- [ ] Names the **mechanism** explicitly (the *how*), not only the observation.
- [ ] At least one **quantified** result (e.g., "reduced 3-fold," not "significantly reduced").
- [ ] First sentence is comprehensible to a life-scientist outside the subfield.

## Jargon blacklist (rewrite on sight)

- "Herein we report…", "Importantly,", "Interestingly,", "Notably,", "Strikingly,"
- Strings of ≥2 undefined gene/protein acronyms in one sentence.
- "elucidate", "delineate", "interrogate", "dissect", "leverage" as filler verbs.
- Hedging stacks: "may potentially suggest that it could…".
- Ending on "further studies are needed" — end on significance.

## Quantification check

Every effect claim should carry a number somewhere in the paper, and the headline effect belongs in the Summary: magnitude + unit + (where natural) statistical support. A Summary with zero numbers is not finished.

## Output format

```
【Summary】 single paragraph (word count: N ≤ 150)
【Five moves present?】 context / gap / approach+result / mechanism named / significance
【Mechanism explicit?】 yes/no — the named molecular/cellular cause
【Quantified headline result?】 yes/no + the number
【Jargon hits removed】 [...]
【Next】 cell-highlights
```

## Anti-patterns

- **Do not** use subheadings or a structured-abstract format — Cell's Summary is one paragraph.
- **Do not** describe only the phenomenon; name the mechanism.
- **Do not** open with the organism or assay; open with the biological stake.
- **Do not** pad past ~150 words; the cap is a feature.
- **Do not** confuse the Summary with the eTOC blurb (that one is third-person and lay; see `cell-highlights`).

> The ~150-word cap is a working default — confirm against current Cell Press author guidelines.

Attribution

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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".

1066601 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', ...

686011 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.

651 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 →