skills/data-storytelling/SKILL.md
Transform scientific findings into compelling research narratives for papers, grants, and presentations
npx skillsauth add lamm-mit/scienceclaw data-storytellingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Transforms scientific data and findings into compelling research narratives with clear structure, effective framing, and audience-appropriate communication. Generates structured narratives for academic papers, grant applications, conference presentations, and press releases.
Tailors language complexity, emphasis, and structure to the target audience: rigorous and mechanistic for academic peers, accessible and impact-focused for the general public, persuasive and outcomes-oriented for grant reviewers, and concise and punchy for conference abstracts.
# Generate an academic abstract
python3 skills/data-storytelling/scripts/story_structure.py \
--findings "We identified that BACE1 inhibition reduces amyloid-beta production by 67% in APP transgenic mice, with IC50 of 12 nM and favorable BBB penetration (Kp,uu = 0.8)" \
--audience academic \
--format abstract
# Generate a grant introduction
python3 skills/data-storytelling/scripts/story_structure.py \
--findings "Novel kinase inhibitor reduces tumor growth 80% in xenograft model, 5x selectivity vs off-targets, oral bioavailability 65%" \
--audience grant \
--format introduction
# Generate a press release for public communication
python3 skills/data-storytelling/scripts/story_structure.py \
--findings "Machine learning model predicts drug side effects with 94% accuracy using protein interaction data" \
--audience general \
--format press-release
# Generate a conference discussion section
python3 skills/data-storytelling/scripts/story_structure.py \
--findings "Cryo-EM structure reveals allosteric site 25 Angstrom from active site, explaining cooperative binding" \
--audience conference \
--format discussion
{
"audience": "academic",
"format": "abstract",
"narrative": "Background: Alzheimer's disease affects...\n\nObjective: To determine...\n\nMethods: Using computational screening...\n\nResults: We identified...\n\nConclusion: These findings suggest...",
"key_messages": [
"BACE1 inhibition reduces amyloid-beta by 67%",
"IC50 of 12 nM demonstrates high potency",
"BBB penetration confirmed for CNS delivery"
],
"word_count": 187
}
tools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.