---
title: "storm"
description: "Wikipedia-style long-form article generation via multi-perspective question asking and retrieval, a Claude-native port of Stanford STORM's two-stage research-to-article pipeline"
canonical: https://agentpluginsdirectory.com/plugins/storm
last-updated: 2026-09-16
---

# storm
Wikipedia-style long-form article generation via multi-perspective question asking and retrieval, a Claude-native port of Stanford STORM's two-stage research-to-article pipeline
- Slug: storm
- Publisher: Frad LEE
- Repository: https://github.com/slurpyb/skills
- Manifest: wip/plugins/storm/plugin.json
- Version: 0.1.0
- License: MIT
- Category (editorial): other
- Skills: 6 (engine, generate, outline, polish, research, write)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-02-03
- Repository last pushed: 2026-09-15
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/storm
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What storm does, in the publisher's words

A Claude Code plugin that ports Stanford STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking) into a Claude-native, zero-dependency skill pipeline.

Given a topic, STORM produces a Wikipedia-style long-form article with inline [n] citations and a trailing References list, grounded in web search, not parametric memory.

Each phase is independently runnable and resumable, completed phases are loaded from the artifact directory, mirroring STORM's stage-gated runner.

- Multi-perspective research: one Task subagent per persona runs the simulated Q&A concurrently.
- Retrieval: prefers connected MCP search tools (e.g. exa-mcp-server), falls back to built-in WebSearch + WebFetch.
- Citation hygiene: inline 1 + trailing References section; source snippets are citation-stripped before reuse.
- Stage gating: each phase writes to a predictable path under the output dir; re-invocation skips completed phases.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/slurpyb/skills/HEAD/wip/plugins/storm/README.md

## Skills

- engine: Provides the shared STORM methodology, artifact layout, stage-gating contract, citation hygiene, and retrieval fallback. Use when executing any /storm:* skill (generate, research, outline, write, polish). Internal knowledge; never user-invocable.
- generate: Run the full STORM pipeline end-to-end. This skill should be used when the user asks to "generate a storm article", "write a wikipedia-style article about X", "research and write a long-form piece on X", or invokes /storm:generate. Orchestrates research -> outline -> write -> polish, skipping alrea…
- outline: Run STORM phase 2: outline generation. This skill should be used when the user asks to "generate an outline for a storm article", "draft a wikipedia-style outline", or invokes /storm:outline. Produces a draft outline from parametric knowledge then refines it using the research information table.
- polish: Run STORM phase 4: article polishing. This skill should be used when the user asks to "polish the storm article", "finalize the article", or invokes /storm:polish. Adds a summary section, removes duplicate content, and verifies citation integrity.
- research: Run STORM phase 1: multi-perspective research. This skill should be used when the user asks to "research a topic for an article", "find sources on X from multiple perspectives", "do storm research on X", or invokes /storm:research. Discovers personas, runs simulated Q&A per persona in parallel, and…
- write: Run STORM phase 3: per-section article writing. This skill should be used when the user asks to "write the article sections", "draft the storm article", or invokes /storm:write. Writes each outline section in parallel with inline citations grounded in the research sources.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.