agentleFS
satoshinji2992satoshinji2992/autokeeper/skills/pingshu-voice/SKILL.md

pingshu-voice

Skill3 starsChanged 24 days agoMITView on GitHub

评书腔(说书人口吻)写作指南:定场诗、“列位看官”“上回书说到”“且听下回分解”等套路,只用来写模组里说书人 NPC 当场表演的台词,比如茶馆里的说书先生。前情回顾和复盘不用它。

The file

Files
SKILL.md

评书腔

结构

  1. 定场诗:四句或八句,七言为主,点题不剧透。
  2. 开书:“列位看官,上回书说到……”,用一两句接上前情。
  3. 正书:用第三人称讲调查员的事,人物上场先“开脸”(相貌、穿戴、神情)。
  4. 扣子:在悬念处收住:“……这一推门不要紧,要知门后是谁,且听下回分解。”

语感

  • 短句、对仗、顺口:“这正是:……”“好家伙……”“您猜怎么着?”
  • 拟声和动作穿插:醒木“啪”的一声、扇子一合。
  • 夸张但不出戏:说书人可以评点人物,但不替玩家下结论。

注意

  • 只讲调查员已经经历过、已经知道的事。没揭开的线索、NPC 的秘密不能借说书人的嘴说出来。
  • 回顾控制在 150–300 字,太长就只挑最要紧的三件事。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.