skills/disease-research/SKILL.md
Generate comprehensive disease research reports using 100+ ToolUniverse tools. The agent creates a detailed markdown report file and progressively updates it with findings from 10 research dimensions, with full source citations. Use when users ask about diseases, syndromes, or need systematic disease analysis.
npx skillsauth add lamm-mit/scienceclaw disease-researchInstall 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.
The agent generates a comprehensive, citation-backed disease research report by creating a markdown file and progressively updating it across 10 research dimensions.
IMPORTANT: The agent should always use English disease names and search terms in tool calls, even if the user writes in another language. Original-language terms should only be tried as a fallback if English returns no results. The agent responds in the user's language.
This skill applies when the user:
The agent should not show the search process to the user. Instead it follows this pattern:
{disease_name}_research_report.md with the full report template| # | Dimension | Key Focus | |---|-----------|-----------| | 1 | Disease Identity & Classification | EFO, ICD-10, UMLS, SNOMED identifiers; synonyms; disease hierarchy | | 2 | Clinical Presentation | HPO phenotypes; symptoms and signs; diagnostic criteria | | 3 | Genetic & Molecular Basis | Associated genes; GWAS associations; ClinVar pathogenic variants | | 4 | Treatment Landscape | Approved drugs; clinical trials; treatment guidelines | | 5 | Biological Pathways & Mechanisms | Reactome pathways; PPI networks; tissue expression | | 6 | Epidemiology & Risk Factors | Prevalence; risk factors; GWAS studies | | 7 | Literature & Research Activity | Publication trends; key papers; research institutions | | 8 | Similar Diseases & Comorbidities | Disease similarity scores; shared genetic basis | | 9 | Cancer-Specific Information | CIViC variants; molecular profiles; targeted therapies (if applicable) | | 10 | Drug Safety & Adverse Events | Drug warnings; trial adverse events; FAERS data |
User: "Research Parkinson's disease"
Agent actions (internal, not shown to user):
1. Create "parkinsons_disease_research_report.md" with template
2. Research DIM 1 → Update Identity section
3. Research DIM 2 → Update Clinical section
4. ... continue for all 10 dimensions
5. Present final report to user
Every piece of data in the report must include its source tool. The agent should use source columns in tables, [Source: tool_name] annotations in lists, and parenthetical (Source: tool_name, query: ...) references in prose. A complete tool usage log belongs in the References section at the end of the report.
For the full report template, complete tool listings per dimension, implementation examples, citation format guide, and quality checklist, see references/tool-reference.md.
See TOOLS_REFERENCE.md for complete tool documentation. See EXAMPLES.md for sample reports.
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.