storm-research

仓库创建 2026年7月6日最近提交 21 天前SkillHot 收录 20 天前
▸ 精选理由

系统化地将多角度分析合成为经审校的研究结论,适合深度调研任务。

这个 Skill 做什么

用 STORM 四阶段方法从多专家视角生成并合成有排序的研究报告并同行评审。

用 STORM 的四阶段把一个问题从多位“专家”视角拆解、列出分歧点,再合成按优先级排序的研究报告并做同行式复核。当你需要深度、平衡的多角度分析或接近 PhD 级别的综述时用。优势是显式展示不同立场和证据强弱,不给单一结论,而是给可复核、排序清晰的建议。

▸ 展开 SKILL.md 英文原文

Turn Claude into a multi-perspective researcher using the STORM method — analyze a topic through several distinct expert lenses, map where they contradict each other, synthesize a single ranked research report, and peer-review the result. Use this whenever the user wants deep research, a thorough analysis, a "PhD-level" or rigorous breakdown of a topic, a balanced multi-viewpoint take, a literature-review-style summary, or explicitly mentions STORM, multi-perspective research, or turning Claude into a researcher. Prefer this over a single flat answer any time the user asks to "really dig into," "research," "give me the full picture on," or "analyze from every angle" a non-trivial topic.

研究检索研究方法多视角合成报告通用
0
Stars
0
Forks
2
仓库内 Skill
+0
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/MaddyMOK/claude-skills/main/skills/storm-research/SKILL.md
或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/MaddyMOK/claude-skills/main/skills/storm-research/SKILL.md"
SKILL.MD 节选查看完整文件 ↗
# STORM Research

A four-phase research method that produces grounded, multi-perspective analysis instead of a single flat answer. Inspired by Stanford OVAL Lab's STORM paper (Shao et al., NAACL 2024), adapted into a repeatable prompt pipeline.

The core idea: **don't ask one question from one angle — interrogate a topic through several distinct experts, surface where they disagree, then synthesize and self-review.** This reliably produces more organized, better-calibrated output than a one-shot answer.

## When to use

Trigger this skill when the user wants genuine depth on a non-trivial topic: research requests, "analyze this from every angle," decision memos, literature-review-style summa
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有