# Develop Article Ideas Through Thought Mining

Writers often lose useful ideas before they become clear article topics. This skill guides a staged conversation that captures insights, selects a topic, validates facts, and reviews drafts.

## Install

```bash
npx skillstore add yunshu0909/thought-mining
```

## Metadata

- Status: approved
- Slug: yunshu0909-thought-mining
- Skillstore revision: r1
- Version status: missing
- Tree hash: e8cb9fc81d2d6cee64267ca840969f5110d0bc2e425cd86581fe6fddc839a67d
- Author: yunshu0909
- GitHub username: yunshu0909
- License: MIT
- Repository: https://github.com/yunshu0909/yunshu\_skillshub/tree/master/thought-mining
- Ref: 64ca8af0f54a325752f08bd54e52151061ea659a
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 69
- Public page: https://skillstore.pages.dev/skills/yunshu0909-thought-mining
- Manifest: https://skillstore.pages.dev/api/skills/yunshu0909-thought-mining/manifest

## Capabilities

- Guides users through five writing stages from idea capture to final review.
- Creates insight and writing record files using provided templates.
- Helps identify three to five promising ideas from collected insights.
- Validates technical or product claims through web research when needed.
- Reviews draft logic, wording, memorable lines, and publication readiness.

## Use Cases

- Develop Article Angles: Capture scattered thoughts, identify useful insights, and turn them into a focused article direction.
- Prepare Product Thought Leadership: Explore product opinions, validate claims, and shape a publishable narrative before drafting.
- Organize Research Notes: Turn exploratory notes into a clear thesis, supporting structure, and final review checklist.

## Prompt Templates

### Start Thought Mining

```
Use thought-mining to help me explore an article idea about [topic]. Ask one question at a time and record useful insights.
```

### Choose a Core Topic

```
Use thought-mining stage 2. Review my collected insights, identify the strongest three to five ideas, and help me choose one article direction.
```

### Validate an Argument

```
Use thought-mining stage 3. Check my proposed argument against official or authoritative sources and list any corrections I should make.
```

### Review a Final Draft

```
Use thought-mining stages 4 and 5. Review this draft for logic, factual consistency, memorable lines, and publication readiness: [draft].
```

## Limitations

- The source instructions are mainly Chinese and optimized for Chinese writing sessions.
- It requires agent file access to create or read local note files.
- Web validation depends on available search tools and source quality.
- It does not replace expert legal, medical, financial, or technical review.

## Best Practices

- Start with a clear topic and desired output format.
- Pause before web validation when notes include confidential or unpublished information.
- Keep generated insight and writing record files in a trusted project folder.

## Anti Patterns

- Publishing factual claims without checking the referenced sources.
- Letting the agent write files from unsafe topic names or broad paths.
- Skipping early idea capture and asking for a complete article immediately.

## Security Audit

- Audited at: 2026-07-08T11:09:06.788\+00:00
- Summary: The static command findings are false positives caused by markdown inline-code markers and a fenced file tree. The entropy findings are false positives from readable Chinese markdown prose, not binary or encrypted content. A separate filesystem safety issue remains because the workflow creates local files from user-provided topic names.

## Stats

- Views: 141
- Downloads: 31
- Favorites: 1
- Popularity score: 0