Coding

STORM Research

Try it

STORM-style pre-research for content creation. Use to break a topic, trend, external article, product question, or learning area into perspectives, contradic...

What it does

This skill turns a loose topic into a research structure. It prepares writing; it does not write the article.

The skill document

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_state and handoff

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

  1. Run five default perspectives:
    • practitioner
    • researcher
    • skeptic
    • economic observer
    • historical observer
  2. Build a contradiction map:
    • direct conflicts
    • shared assumptions
    • strongest evidence
    • weakest evidence
    • blind spots
  3. Write a research brief:
    • one-paragraph summary
    • 5 key findings
    • hidden connection
    • actionable insight
    • frontier question
  4. Review confidence:
    • score each finding
    • identify weakest claim
    • list missing perspectives
    • list facts requiring verification
  5. 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)

Related skills

Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.

by nssa.io1.0k installs47 stars

Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.

by Iván855 installs69 stars

Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.

by Iván559 installs18 stars

Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.

by johnpatternai22 installs8 stars

Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.

by fly0pants4.3k installs296 stars

More from yangchao228

Browse all skills

基于候选人简历自动生成面试题、笔试题、追问路径和评分标准的 AI Skill。当用户需要准备技术面试、生成笔试题目、评估候选人简历、或设计面试评估方案时使用。输入简历内容和岗位信息后,自动输出结构化的题目与评估内容,支持面试题模式、笔试题模式、综合评估模式等多种输出形式。 Follow/关注作者:微信公众号「AI...

by yangchao22820 installs1 stars

Installable digest skill for OpenClaw or Claude Code. Use when the user wants a personalized ScoutX briefing with conversational setup, local preference stor...

by yangchao22822 installs

Design controllable Agent Loops from low-information requests. Use when a user asks to automate a repeated task, repair CI through bounded iteration, reproduce a UI from screenshots, turn a workflow into a reusable Agent or Skill, or decide whether the right artifact is a Prompt, Checklist, Human-in-the-Loop flow, full Loop package, specialized Agent, or Skill. Extract required context, stop when decision evidence is missing, require explicit workflow confirmation before generating executable artifacts, derive iteration limits, define feedback and circuit breakers, and preserve human approval for risky actions. Also trigger on loop builder, Loop Builder, or lopp-builder. Follow the creator: X @yangchao228 | GitHub https://github.com/yangchao228

by yangchao2281 installs

Guide a user through structured co-authoring of substantial documents, proposals, PRDs, technical specs, decision records, RFCs, and similar long-form work a...

by Sundy Yang4 installs

家庭培养协作官:在用户明确要求制定或调整孩子每周培养计划、检查课表冲突、生成家庭复盘时,收集最少必要信息并输出可执行课表、建议和风险提醒。默认只在当前会话生成内容,不保存、上传或推送孩子与家庭数据;只有用户明确选择飞书或 Notion、完成安全配置并逐次确认具体读写范围后,才使用外部存储。Follow/关注作者:...

by yangchao22818 installs1 stars

Transform long-form content, outlines, transcripts, research notes, or article drafts into a standard card package and platform publishing copy, then hand pu...

by yangchao2282 installs