Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tance-mang/chinese-webnovel-skills --skill dialoguegit clone --depth 1 https://github.com/tance-mang/chinese-webnovel-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/dialogue)<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/dialogue"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/dialogue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/dialogue"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/dialogue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.01026 |
| Opus 5 | $0.00050 | $0.00513 |
| Sonnet 5 | $0.00020 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
dialogue scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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
- 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）
- 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 - 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。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 59 lines · 100 tokens per session scan A 5eed768b9d9d
dialogue is a skill published in the GitHub repository tance-mang/chinese-webnovel-skills (58 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 1,026 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
add-cloud-flow
Integrates Power Automate cloud flows into a Power Pages site. Lists available flows, suggests relevant ones based on intent, identifies scenarios and web roles, creates metadata files, and generates client-side code to call flows. Handles both new flow registration and adding already-registered flows to additional…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
deploy-site
Deploys an existing Power Pages code site to a Power Pages environment using PAC CLI. Handles tooling verification, authentication, environment confirmation, building, and uploading. Use when the user wants to deploy, upload, or publish their code site.