stormlisted

Research a topic from multiple perspectives, grounded in retrieval, and return a cited briefing — an agent-native port of Stanford's STORM. Discovers (or accepts) diverse perspectives, runs grounded question-asking per perspective with retrieval at each step, and curates findings into a source-attributed synthesis. Every claim is cited or tagged [unverified]. Runs standalone (`/storm <topic>`) or as a hand-off target for `team-composer`, inheriting the panel's active roles as seed perspectives. Triggers on "research X", "what's known about Y", "survey the evidence on Z", "build a grounded briefing on…", or an upstream skill needing sourced external knowledge. Does NOT trigger on single-source-of-truth fact-checking or one authoritative report — that's `deep-research`; nor on opinion, critique, planning, or assembling a team — that's `team-composer`. Perspective-breadth, not source-breadth.
sorawit-w/agent-skills · ★ 1 · API & Backend · score 75

Install: claude install-skill sorawit-w/agent-skills

# storm Research a topic the way Stanford's STORM does its pre-writing: **discover the perspectives that matter, ask grounded questions from each, and synthesize the answers into a cited briefing.** The wedge is *breadth of perspectives* — what different lenses surface about a topic — not breadth of sources on a single question. This is an **agent-native port of the STORM mechanism**, not Nav Toor's 4-prompt chat workflow. The agent already holds retrieval, so grounded *is* the default — there is no un-grounded mode. --- ## Phase 0 — Boundary gate Activate `storm` when the request wants **sourced external knowledge across perspectives**. Route away otherwise: | Request shape | Skill | |---|---| | "Research X", "what's known about Y", "survey the evidence on Z", "grounded briefing on…" | **storm** | | An upstream skill (e.g. `team-composer`) needs sourced knowledge it can't reason to | **storm** (hand-off) | | Single-source-of-truth fact-check, one authoritative report, "verify this claim" | `deep-research` | | Opinion, critique, planning, "assemble a team", "review my plan" | `team-composer` | | General agent loop / build work | the harness / `cerby` | The `deep-research` line is the load-bearing one: it owns *source-breadth* (fan-out, fetch, adversarially verify into one report). `storm` owns *perspective-breadth*. If the request wants the ground truth on one question, it's `deep-research`. If it wants what several lenses reveal about a topic, it's `storm`. --- ## P