STORM

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 already-completed phases.

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 produces an information table + deduplicated sources.

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.

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.

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.

Use this agent to run ONE persona's simulated conversation in the STORM research phase. Spawned in parallel by /storm:research — one agent per persona. The agent conducts a multi-turn WikiWriter↔TopicExpert dialogue grounded in retrieval and returns a structured conversation log. Do not spawn for general research; only for the STORM persona-conversation subprocess. <example>Context: /storm:research is running for topic "transformer architectures" with 3 personas. user: "research transformer architectures from multiple perspectives for a storm article" assistant: "I'll spawn one storm-researcher per persona in parallel to run the simulated conversations." <commentary>One agent per persona, launched in a single message for parallelism.</commentary></example> <example>Context: /storm:research discovered a "Historical context" persona. user: "run the historical-context persona conversation for the transformer article" assistant: "I'll launch a storm-researcher with that persona definition and max_turns=3." <commentary>Single persona subprocess; returns a JSON conversation log.</commentary></example> <example>Context: user wants general research, not STORM. user: "research the history of RLHF" assistant: "I'll research that directly with WebSearch — storm-researcher is only for STORM persona subprocesses." <commentary>Do not spawn this agent for non-STORM research.</commentary></example>

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.

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 already-completed phases.

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.

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.

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 produces an information table + deduplicated sources.