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

Human

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

给中文网文加"人味/失控感",治深层AI味。当用户嫌稿子"读着像AI/像说明书/太工整太顺/情绪太平均/人物太正常/没人味/太中立"、或想让文字更像真人写的(不是改修辞,而是加失控感)时使用。用非理性行为、情绪不完整表达、逻辑不完全闭环、私货感,把"说明书"改成"情绪记录"。

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

Install

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

✓ 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-human)

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 Human? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

人味 / 失控感(human)

最高级的一层去 AI 味。"AI 味"的本质是缺少人类失控感——AI 写得像说明书(都解释、都合理、都闭环、都中立),人写得像情绪记录(有失控、有偏执、有省略、有偏心)。

何时用

  • 稿子"读着像 AI / 像说明书 / 太顺太工整 / 情绪太平均 / 人物太正常 / 没人味"
  • 表面修辞都改干净了(deslop 过了),但还是"差点意思"
  • 想让文字更像真人写的——不是改字,是加失控感

> 和 deslop 的分工:deslop 治表面(修辞/标点/符号/重复/极端词);本技能治深层(情绪/冲突/人物/不闭环/私货)。两个一起用最彻底。

工作流

A. 诊断(按 5 种感受找"太 AI"处)

扫稿子,指到段标出(调 references/human-texture.md):

  1. 情绪太平均:都在合理反应,没有真正失控/极端/偏执的爆点。
  2. 冲突太干净:误会→解释→解决,缺"越滚越脏"的链条。
  3. 句子太顺:没有长短变化、断句、停顿、不完整表达 → 句长不均+停顿标点,详见 references/sentence-rhythm.md
  4. 人物太正常:动机合理但不极端,没有"明知错还做"的不理性。
  5. 太中立:没有偏见、情绪判断、私货感。

B. 注入人味(3 个手法,关键处加)

  1. 非理性行为:让角色做"逻辑上不该、情绪上必须"的事(明知会输还赌、当场翻脸不解释、突然极端选择)。
  2. 情绪不完整表达:留没说出口的缺口("他没说完那句话。""她突然不想解释了。""那一刻他有点后悔,但没停。")。
  3. 逻辑不完全闭环:次要的事不解释尽、次要的关系不收干净。

给"原句/原段 → 改后"对照,说明加了哪种。

原则

  • 点睛不发疯:关键处放 1–2 个失控点,不是通篇不理性。
  • 不牺牲爽和钩:番茄仍要节奏;失控感是让爽更可信、人物更立得住。
  • 不闭环 ≠ 烂尾:主线大坑必须回收,留白只留情绪性/关系性的小东西。
  • 自检一句话:这段像说明书,还是像一个人在记录情绪?

反例对照

  • ❌(太干净)“她误会了他,他解释清楚,两人和好。”
  • ✅(越滚越脏)“她没等他说完就挂了电话。他想再打,手指悬在屏幕上,又放下了——算了,解释什么呢。第二天,闺蜜把那张照片发到了群里。”

下一步

加完人味 → deslop 收表面、review 复诊、emotion 强化关键情绪。

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.