Draft cited research reports with STORM
Use STORM to research a topic, build a multi-perspective outline, and generate a cited long-form draft for human review.
npx skills add agentskillexchange/skills --skill draft-cited-research-reports-with-storm
Use STORM when the operator needs a cited research draft, not just a search summary. The workflow is to define the topic, run STORM or Co-STORM to gather sources and ask perspective-guided questions, generate an outline, produce a full-length draft with citations, and review the references before publishing or relying on the result. The boundary is pre-writing and knowledge-curation support for research reports; it should not be treated as a general writing assistant or generic RAG framework.
What this skill actually does
Inputs and prerequisites: Python, knowledge-storm package, configured LLM provider, search or retrieval backend.
Setup notes: Install with pip install knowledge-storm, configure the required LLM and retrieval/search credentials, then run the STORM or Co-STORM workflow for a bounded topic and review all generated citations before use.
Source and verification boundary: use https://github.com/stanford-oval/storm as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.