Installable skillMIT

Science Communication — Making Research Accessible

# Science Communication — Making Research Accessible

BY beita6969UPDATED Oct 27, 2026
INTENDED FOR✳Claude Code>_Codex◈OpenClaw↗CursorInstall in a listed agent.

instructions.md

---
name: science-communication
description: # Science Communication — Making Research Accessible
---

# Science Communication — Making Research Accessible

## Overview
Translate complex scientific findings into engaging content for non-specialist audiences.

## Output Types

### Press Release
- **Headline**: Active voice, no jargon, emphasize significance
- **Lead paragraph**: Who, what, when, where, why — in plain language
- **Quote**: From the lead researcher, expressing significance
- **Background**: 1-2 paragraphs of accessible context
- **Implications**: What this means for patients/society/technology
- **Contact info**: PI, institution press office

### Plain-Language Summary
- Write at 8th-grade reading level
- Replace jargon: "gene expression" → "how active a gene is"
- Use analogies: "DNA methylation is like a dimmer switch for genes"
- One key finding per paragraph
- End with "Why it matters"

### Social Media (Twitter/X Thread)
- Hook tweet: surprising finding in <280 chars
- 3-5 thread tweets explaining the story
- Include: figure, emoji for visual breaks, relevant hashtags
- Tag relevant accounts (journal, institution, collaborators)

### Blog Post / Explainer
- Catchy title (question or surprising fact)
- Opening hook: a story, analogy, or question
- Background: what was known before
- The breakthrough: what's new
- Implications: what happens next
- Further reading: links to paper and resources

## Principles
- **Accuracy**: Never oversimplify to the point of being wrong
- **Engagement**: Tell a story, not a lecture
- **Honesty**: Include limitations and caveats
- **Accessibility**: No acronyms without expansion, no undefined jargon
COMPATIBILITY & REFERENCES

Platform guidance

Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.