Turn messy topics into evidence-led deep research
集成
STORM Research
试用STORM-style pre-research for content creation. Use to break a topic, trend, external article, product question, or learning area into perspectives, contradic...
它能做什么
STORM-style pre-research for content creation. Use to break a topic, trend, external article, product question, or learning area into perspectives, contradiction maps, research briefs, confidence reviews, and evidence plans before writing. Follow/关注作者:微信公众号「AI生命克劳德」|X @yangchao228|GitHub https://github.com/yangchao228
技能文档
STORM Research
This skill turns a loose topic into a research structure. It prepares writing; it does not write the article.
Scope
Do:
- scan multiple perspectives
- identify conflicts, consensus, and blind spots
- write a research brief
- score confidence
- create an evidence plan for
wenchang-research - update
content_stateandhandoff
Do not:
- write a final article
- treat simulated perspectives as facts
- replace source-backed fact checking
- make medical, legal, financial, or high-stakes decisions
- use unsupported social screenshots as primary evidence
Process
- Run five default perspectives:
- practitioner
- researcher
- skeptic
- economic observer
- historical observer
- Build a contradiction map:
- direct conflicts
- shared assumptions
- strongest evidence
- weakest evidence
- blind spots
- Write a research brief:
- one-paragraph summary
- 5 key findings
- hidden connection
- actionable insight
- frontier question
- Review confidence:
- score each finding
- identify weakest claim
- list missing perspectives
- list facts requiring verification
- Produce an evidence plan for
wenchang-research.
Output Format
## Research Decision
- Fit for next stage:
- Recommended next step:
- Main reason:
## Perspectives
| Perspective | Core concern | Supports | Challenges | Unique information | Needs verification |
| --- | --- | --- | --- | --- | --- |
## Contradiction Map
- Conflicts:
- Consensus:
- Strongest evidence:
- Weakest evidence:
- Blind spots:
## Research Brief
- Summary:
- Key findings:
- Hidden connection:
- Actionable insight:
- Frontier question:
## Confidence Review
- Scores:
- Weakest claim:
- Bias check:
- Missing perspectives:
- Must verify:
## Evidence Plan
1. :
## content_state Update
```yaml
content_state:
storm_research:
topic:
perspectives: []
contradiction_map:
conflicts: []
consensus: []
blind_spots: []
confidence_review:
verification_needed: []
evidence_plan: []
next_step:
skill: wenchang-research
reason:
user_decision_needed:
handoff:
from_stage: storm-research
to_stage:
accepted_inputs: []
ignored_context: []
stop_condition:
## Stop Conditions
Pause if there are more than three equally strong angles, if the topic involves high-stakes advice, or if core claims cannot be verified with primary sources.
## 作者入口
- 微信公众号:`AI生命克劳德`
- X:[@yangchao228](https://x.com/yangchao228)
- GitHub:[yangchao228](https://github.com/yangchao228)
相关技能
通过 7 阶段流程产出一份带引用的长文研究报告,关键节点由你确认。
Produce current, cited multi-source research briefs
Rigorous multi-source, fact-checked research producing a cited brief. Use for any high-stakes question where being wrong is costly — market sizing, company/p...
当用户说「深度研究 X」「深入研究 X」或要求生成某产品、公司、概念、人物、产业链、政策、趋势的深度研究/发展研究报告时触发,自动进行联网搜索和研究,产出排版后的 PDF 文档,总字数通常 1-3 万字。
多源深度研究工具,支持系统性信息探索、来源评估与方法论追踪,生成结构化研究报告,适合个人研究与学习。Use when 需要SEO优化、关键词分析、排名提升、搜索流量优化时使用。不适用于黑帽SEO手段。适用于独立开发者、企业团队和自动化工作流场景。支持中文交互,无需复杂配置即开即用。输出结果可直接使用,减少二次加工成本。