AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Dialogue

skill-tance-mang-chinese-webnovel-skills-dialogue · by tance-mang

中文网文对话与台词。当用户要写/改对话、设计金句名场面台词、写打脸装13台词、虐心或甜宠台词、抱怨"对话太生硬/太书面/像AI/每个角色一个腔"、或要让人物说话有区分度时使用。产出口语化、有潜台词、符合人设声音的台词。

No reviews yet
0 installs
4 views
0.0% view→install

Install

$ agentstack add skill-tance-mang-chinese-webnovel-skills-dialogue

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-tance-mang-chinese-webnovel-skills-dialogue)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Dialogue? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

对话与台词(dialogue)

对话是"AI 味"最大的破绽,也是网文名场面的核心。AI 对话像书面陈述,网文对话要像真人交锋。

何时用

  • 写一段对话 / 改一段生硬的对话
  • 设计金句、名场面台词
  • 写打脸/装13/反派/虐心/甜宠台词
  • "对话太书面/像 AI/每个角色一个腔"
  • 让不同角色说话有区分度

工作流

A. 写/改对话

  1. 明确:谁和谁、什么场景、要达成什么(推进剧情/暴露性格/制造张力)
  2. 按好台词 5 原则写(调 references/dialogue-library.md):口语化、有潜台词、符合人设声音、留白、每句有用
  3. 去 AI 对话腔:删复述/念设定、打碎长句、删"愤怒地说"改用动作、不同角色不同句式、加潜台词

B. 设计专项台词

按类型从台词库取(打脸/装13/反派/虐/甜/日常):

  • 打脸:越短越狠 + 围观反应("就这?")
  • 装13:不解释、越淡越唬人
  • 反派:文雅的威胁最瘆人
  • 女频情感:克制比嘶吼更虐,偏爱藏细节里

C. 金句设计

要"可截图传播":短 + 狠 + 反差/哲理。一章一两句即可,别硬凑。

D. 人物声音区分(语言指纹 speech_profile)

给每个主要角色定一张语言指纹:风格(粗/雅/毒舌)+ 口癖 + 句长偏好 + 常用词 + 绝不会说的词。保证读者不看名字也知道谁在说。

  • 自检每句:"只有这个角色会这么说吗?"
  • 写对话前先调出该角色的语言指纹对照注入;存进 01_人物.md(格式见 references/project-memory.md 七),由 character 技能产出。
  • 长篇尤其重要:后期最容易"所有人退化成一个口气"——每隔几卷用 continuity 抽查对话是否还守得住各自指纹。

输出

  • 直接给台词/对话,必要时"改前 vs 改后"对照
  • 设计台词时说明:用了什么潜台词、体现了什么人设
  • 不靠"愤怒地/开心地"等副词,靠台词本身 + 动作
  • 引号用弯双引号 ""(嵌套才用弯单引号 ''),不用直角引号「」『』(港台/日式,简体网文不用),也不用英文引号

原则

  • 口语 > 书面:"就这?"胜过"你的实力不过如此。"
  • 潜台词 > 直白:话里有话才有张力。
  • 留白 > 说尽:别把情绪解释完。
  • 一人一声:消灭"所有人一个腔"。
  • 金句精而少,多了做作。

反例对照

  • ❌“我对你的背叛感到非常愤怒和失望。”→ ✅“……行。”(转身,留白更狠)
  • ❌“我的实力远超于你。”→ ✅“就这?”

下一步

台词配进正文 → expand;整体还有 AI 味 → deslop;打脸桥段结构 → shuangdian

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.