Coding

Wenchang Review

Try it

Diagnose or edit an existing content draft. Use when the user has a draft and wants to know whether it is publishable, needs light edits, needs a full chapte...

What it does

Wenchang Review evaluates whether a draft deserves more work and what the smallest useful next action is.

The skill document

Wenchang Review

Wenchang Review evaluates whether a draft deserves more work and what the smallest useful next action is.

Modes

Default to diagnosis mode. Use full-edit mode only when the user explicitly asks to edit, rewrite, cut, polish, or produce a publishable version.

Diagnosis Mode

Return issues and minimum fixes. Do not rewrite the full article.

Full-Edit Mode

Return an edited draft after diagnosing. Prioritize:

  1. argument strength
  2. evidence near claims
  3. reader value
  4. readable structure
  5. clean prose

Diagnosis Dimensions

  • core problem clarity
  • structure and flow
  • reader gain
  • evidence and examples
  • human judgment and specificity
  • platform fit
  • long-term asset value
  • risks: empty trend talk, tool manual tone, overpromised title, unsupported claims

Diagnosis Output

## Review Decision
- Recommended action: publish / light edit / full edit / rewrite / switch platform / stop investing
- Main reason:

## Key Issues
1. ...

## Minimum Fixes
1. ...

## Platform Fit
- WeChat:
- Zhihu:
- Xiaohongshu:

## Knowledge Asset Value
- Preserve:
- Could become:

## content_state Update
```yaml
content_state:
  diagnosis:
    recommendation:
    key_issues: []
    minimum_fixes: []
  knowledge_asset:
    should_preserve:
    asset_type:
    suggested_bucket:
  next_step:
    skill:
    reason:
    user_decision_needed:
  handoff:
    from_stage: review
    to_stage:
    accepted_inputs: []
    ignored_context: []
    stop_condition:


## Full-Edit Output

```md
## Edit Decision
- Main original problem:
- What changed:
- Still needs user confirmation:

## Edited Draft


## Change Log
1. ...

## Strongest Line

Boundaries

  • Do not default to full rewrite.
  • Do not preserve unsupported claims for smoother prose.
  • Do not change the author's core position silently.
  • If the core position fails, return a diagnosis instead of hiding the failure with editing.

作者入口

Related skills

Productivity

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

by Iván855 installs69 stars

diagram-generator

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

by nssa.io1.0k installs47 stars

Memory

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

by Iván559 installs18 stars

AdMapix

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

by fly0pants4.3k installs296 stars

Join meeting

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

by johnpatternai22 installs8 stars

More from yangchao228

Browse all skills

简历面试题生成器

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

谛听.skill

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

loop-builder

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

Doc Coauthoring

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

Family Cultivation Coach

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

Long To Cards

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