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

Sci Framing

ASecurity

Use to lock the conceptual advance and the "why now" before drafting — converts a correct result into a Science-shaped narrative that leads with the advance, not the background.

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

Works with

cli

Security Analysis

A100/100

Scanned 6/6/2026

Install to Claude Code

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

Installs into .claude/skills of the current project.

Are you the author of Sci Framing?

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

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

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

Download with Pro
Files
SKILL.md
---
name: sci-framing
description: Use to lock the conceptual advance and the "why now" before drafting — converts a correct result into a Science-shaped narrative that leads with the advance, not the background.
---

# Advance Framing (sci-framing)

## When to trigger

- The science is solid but the manuscript reads like a lab report.
- The introduction opens with three paragraphs of background before the contribution.
- Reviewers/colleagues say "so what?" or "I don't see what's new."
- You can state the result but not the *lesson*.

## The one-sentence advance

Force the entire paper into a single sentence of the form:

> "We show that **[surprising, general claim]**, which means **[consequence for a broad field]**."

If you cannot fill both brackets without jargon, the framing is not ready. This sentence seeds the one-sentence summary (`sci-abstract`), the cover letter (`sci-cover-letter`), and the last line of the intro.

## Science introduction shape (≈3 short paragraphs)

1. **The gap that matters broadly** — what the community has been unable to do/explain, stated so a non-specialist grasps the stakes. One paragraph, not a literature dump.
2. **Why it has been hard / why now** — the obstacle, and what (new tool, idea, dataset, scale) finally makes it tractable. This is the "why now" that journalists and editors look for.
3. **What we did and found** — the advance, in plain terms, ending on the broad implication. The reader should know your result before the Results section.

## The "why now" checklist

Editors favor work that is timely. Name explicitly which applies:

- [ ] A new method/instrument made the impossible measurable.
- [ ] A new dataset/scale reached a threshold that changes conclusions.
- [ ] A field-wide controversy is ripe for resolution.
- [ ] A theoretical prediction is now testable.
- [ ] A real-world event (pandemic, climate milestone) makes it urgent.

If none apply, the work may be correct but not *Science-timely* → revisit `sci-fit`.

## Title discipline

- **Declarative and specific** beats vague and grand. "X regulates Y by Z" > "Insights into the regulation of Y."
- Avoid "Towards", "A study of", "Investigating", "Novel".
- Keep it parseable by a non-specialist; the noun phrase should carry the advance.
- Science titles are short (often < 90 characters). No question marks unless the question is the point.

## Narrative anti-frames (rewrite these)

| Anti-frame                                      | Reframe                                              |
|-------------------------------------------------|-----------------------------------------------------|
| "We applied method M to system S."              | "We discovered that S does X — revealed by M."      |
| "Little is known about…"                        | "Whether [specific question] has been unresolved because…" |
| "Our results are consistent with…"              | "Our results decide between competing models, favoring…" |
| Chronological lab-notebook order                | Logical order toward the single claim               |

## Output format

```
【One-sentence advance】 "We show that ... which means ..."
【Why-now trigger】 which of the 5 applies
【Intro 3-paragraph skeleton】 gap / why-now / advance+implication
【Working title】 declarative, < 90 chars
【Risk】 is the implication demonstrated or asserted? (link back to sci-fit if asserted)
【Next】 sci-writing
```

## Anti-patterns

- **Do not** bury the advance below the fold; the broad claim belongs in the first 150 words.
- **Do not** inflate with "novel/unprecedented/paradigm-shifting" — show, don't label.
- **Do not** frame around the method when the discovery is the point (method-led framing is for methods journals).

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 →