storm-research

Storm Research

What this does

Turns one topic into a verified, multi-perspective HTML briefing. It simulates five expert lenses on the topic, maps where they contradict each other, synthesizes everything into a single self-contained HTML report, then adversarially peer-reviews its own output and verifies every citation against its primary source before delivering. The output is one HTML file with no blind spots and no unchecked claims.

Run the full pipeline end to end. Do not shortcut a phase. This is heavier than a quick web lookup; that is the point.

Portability

This skill is self-contained. It depends only on built-in Claude Code tools (the Agent tool with the built-in general-purpose agent, Write, and web search/fetch used inside those agents) plus report-template.html in this same folder. No external scripts, APIs, paid services, or other skills are required. Drop the folder into any .claude/skills/ directory and it works.

Phase 0: Scope the topic

1. If $ARGUMENTS has the topic, use it. Otherwise ask what to research.
2. State your interpretation of the topic in one line and proceed. Only ask a clarifying question if the topic is genuinely ambiguous in a way that changes the research. Default to proceeding.
3. Identify the reader's role so the actionable section can target it. Infer it from the topic and any stated context; if unclear, ask in one line, or default to "a practitioner or decision-maker in this field."
4. Derive a kebab-case topic-slug from the topic for the filename.
5. Tell the user the pipeline is running (5 lenses, then verify). One line.

Phase 1: Five expert lenses (parallel agents)

Spawn five general-purpose agents in a single message so they run concurrently. Each gets the SAME topic framing plus its own lens. Use these exact prompts, substituting {TOPIC} and a one-line {TOPIC_FRAME} (your Phase 0 interpretation):

1. THE PRACTITIONER — You are THE PRACTITIONER for: {TOPIC} ({TOPIC_FRAME}). You work with this daily. Do real web research (prioritize recent sources, case studies, practitioner threads, operator data). Surface the GAP between what hands-on operators know and what academics/pundits miss, and the practical realities (workflow friction, what actually works, where it breaks) that get ignored. Return EXACTLY: 1) CORE POSITION in 2 sentences. 2) STRONGEST EVIDENCE, 3-5 bullets each with a concrete data point/case/named source + URL. 3) THE ONE THING only a practitioner would say. Cite real sources with URLs. Under 400 words.