annotate
Skill97 starsChanged 5 months agoMITView on GitHub
中文网文正文标注与节奏可视化。当用户要在正文里标出钩子/爽点/高潮/打脸/伏笔的位置、看一章的节奏分布、检查爽点密度、或标记和建议修饰词(短平快爽文爱加的强化词)时使用。产出带标签的正文 + 节奏数据表,方便作者直观看数据。
6 other projects use a version of this.
Adopted by
Most recently taken up by
- MacroMan5/autotrain-yolotheir own version, first seen Oct 25, 2026
- jazzpujols34/claude-skillstheir own version, first seen Oct 13, 2026
- dolanmiu/docxtheir own version, first seen Oct 8, 2026
- plustar35/echo-readingtheir own version, first seen Jun 5, 2026
- tranhieutt/software_development_departmenttheir own version, first seen Apr 30, 2026
- marmutapp/superbased-claude-code-plugintheir own version, first seen Apr 12, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- dolanmiu/docx★ 6ksame name
- plustar35/echo-reading★ 142same name
- tranhieutt/software_development_department★ 71same name
- MacroMan5/autotrain-yolo★ 8same name
- marmutapp/superbased-claude-code-plugin★ 1same name
- jazzpujols34/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository38 other files it gives its agents.
- aidetectSkill
- characterSkill
- coachSkill
- continuitySkill
- cowriteSkill
- deconstructSkill
- deslopSkill
- dialogueSkill
- draftSkill
- emotionSkill
- englishSkill
- expandSkill
- fanficSkill
- genre-styleSkill
- globalizeSkill
- goldfingerSkill
- grok-writeSkill
- hookSkill
- humanSkill
- ideaSkill
- intimacySkill
- memorySkill
- model-routerSkill
- nameSkill
- native-editSkill
- outlineSkill
- proofreadSkill
- reviewSkill
- scriptSkill
- shuangdianSkill
- slangSkill
- sparkSkill
- startSkill
- submissionSkill
- titleSkill
- trendsSkill
- warmthSkill
- worldSkill
The file
Files
正文标注与节奏可视化(annotate)
把一章正文"透视"出来:钩子在哪、爽点几个、高潮在第几段、修饰词够不够。让作者一眼看见自己的节奏数据。
何时用
- 想看"这章爽点够不够、钩子在哪、节奏对不对"
- 标记/检查修饰词(短平快爽文的"味儿"词)
- 给一章做发布前的可视化体检
- 和
review的区别:review是整卷/整书的宏观五维诊断;annotate是单章逐段的微观标注
工作流
第 1 步:逐段标注(输出带标签的正文)
把用户的正文按段落标注,行内插入标签:
【钩】钩子(开篇钩/章尾钩/段落悬念)【爽】爽点(逆袭/打脸/碾压等,调references/trope-library.md)【高潮】本章情绪顶点【脸】打脸桥段(标出四拍:嘲讽/沉默/碾压/围观)【伏】伏笔埋点【修】修饰词(标出已用的强化词/围观反应词,调references/xiushi-ci.md)【缓】节奏舒缓段
第 2 步:输出节奏数据表
【本章体检表】
字数:____
钩子:开篇钩 ✓/✗ 章尾钩 ✓/✗ 段落悬念 __ 个
爽点:__ 个(类型:打脸/逆袭/…)|密度评价:达标/偏少(按平台)
高潮:在第 __ 段|情绪强度:__/5
打脸四拍:嘲讽__ 沉默__ 碾压__ 围观__(缺哪拍标出)
修饰词:强化词__ 围观反应__ |密度:合适/偏少/过载(油腻)
伏笔:埋__ 个 回收__ 个
节奏曲线:紧—缓—紧 是否有呼吸感
AI 味(粗判):比喻密度/连续同句式/句长波动 有无异常 → 要量化评分用 `aidetect`第 3 步:给改进建议
- 爽点断档的段 → 建议补什么(指到段)
- 打脸缺了"围观"拍 → 建议加围观反应词(给 2-3 个候选,调
xiushi-ci.md) - 修饰词偏少的爽点句 → 建议在哪句加什么词
- 修饰词过载的段 → 建议删到 2-3 个(避免油腻/AI 味)
- 章尾收尾平淡 → 建议换哪种章尾钩(调
hook-library.md)
原则
- 标注要落到段/句,不空泛。
- 修饰词建议遵循"稀疏使用、峰值集中、频道有别"(见
references/xiushi-ci.md)。 - 按平台判断密度:番茄要密,起点可疏(调
references/platform-profiles.md)。 - 男频重"猛/爽/燃"的强化词与围观反应,女频重神态/情绪词。
下一步
按标注 → 用 expand 重写弱段、shuangdian 补打脸、deslop 清理过载修饰词;要 AI 味量化评分+定位 → aidetect。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

