Home / renky1025 / agent-skills · GitHub

black-humor-writing SKILL.md skillA

black-humor-writing from renky1025/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add renky1025/agent-skills/black-humor-writing@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: renky1025/agent-skills
Path: black-humor-writing/SKILL.md
Versions recorded: 2
Latest version: v1.0.0, committed Sep 25, 2026
First version recorded: Aug 25, 2026
Size: 7,394 bytes
Repository stars: 11
License: MIT

生成有传播力的黑色幽默/讽刺/搞笑内容（推文、段子、评论文案、文章段落）。基于单立人单口喜剧教材，用五步 SOP 把生活观察变成预期违背式的笑点：定主题+态度+前提 -> 构建预期违背 -> 夸张荒谬点 -> 制造情绪冲突 -> 段子雷达扫描。触发场景：写段子、写搞笑文案、黑色幽默、讽刺文、吐槽向内容、social media satire；用户说「黑色幽默」「搞笑」「段子」「搞笑文案」「幽默写作」「SOP搞笑」，或要求为 X/小红书/微博写讽刺向内容。用法：/black-humor-writing <主题>.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 黑色幽默写作 SOP

幽默不是天赋，是有 SOP 的。基于单立人喜剧教材的核心方法论，从观察生活出发产出有传播力的幽默内容。

## Purpose

把一个主题转成一段有传播力的黑色幽默内容：推文、段子、评论文案或文章段落。价值不在于堆梗，
而在于先找到主题里真实的矛盾，再用"预期违背"把矛盾放大到荒谬但成立的程度。技能输出的是
可直接发布的内容，并附上它的预期违背点、前提和情绪触发点。

## When to Use

- 用户要写段子、搞笑文案、讽刺向内容，用于 X/Twitter、小红书、微博、公众号或短视频脚本。
- 用户明确说「黑色幽默」「搞笑」「段子」「搞笑文案」「幽默写作」「SOP搞笑」。
- 用户给了一个主题，但想要一个有态度、有锋芒、有人味的表达，而非中性陈述。
- 用户要做吐槽向内容、反常识爆论，且愿意接受犀利但可辩护的立场。

## When NOT to Use

- 用户要的是严肃写作、公文、学术、新闻通稿 -> 拒绝使用本技能的夸张与讽刺手法。
- 用户只是要给已有文字去 AI 味、润色语气 -> 交给 `de-ai-writing`。
- 用户要写完整的自媒体长文（含选题、结构、标题体系）-> 交给 `wechat-article-writer`。
- 用户要的是纯信息型科普、产品说明，没有真实矛盾可揭露 -> 本技能没有表达空间，如实告知。
- 笑点依赖羞辱、歧视、人身攻击 -> 不生成（见 Constraints）。

## Workflow

按 1 -> 5 顺序执行，不要跳过前三步直接写。每步的详细机制、正反例和模板见 `## References`。

1. **定主题 + 态度 + 前提**。拿到主题先问"我对这件事的真实感受是什么"，得到态度，再提炼前提。
   三要素缺任一（只有主题没态度 / 只有态度没前提）就不进入下一步，先追问或自己补出候选前提。
2. **构建预期违背**。找出大众对这件事的"默认叙事"，从默认叙事之外找一个意外角度，用它当包袱。
   自检：读者猜得到结局吗？猜得到就不是包袱。
3. **把普通事情夸张化**。描述普通场景 -> 找出场景里的矛盾 -> 把矛盾放大到荒谬程度。
   放大后必须仍保留真实内核，否则见 Constraints 的"不编造"规则。
4. **制造焦虑和冲突**。判断内容是要信息还是要情绪。要传播就选情绪型角度，并为爆论配真实论据。
   自检：这句爆论能不能经得起"是吗？"的追问。
5. **段子雷达复扫**。写完再问三句话：这事是不是有点奇怪？为什么大家觉得正常？放大后会怎样？
   扫出新的矛盾点就回到第 2 步再包一次。

## Decision Rules
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add renky1025/agent-skills/black-humor-writing@sha256:ba2b42bddef4e91c

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_q6dph33unrhmw5ds.svg)](https://markdownregistry.com/a/art_q6dph33unrhmw5ds)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 25, 2026 and Sep 25, 2026, about one every 31 days.

version	committed	commit	size	audit
v1.0.0 latest	2026-09-25	32ce6c0	7,394 B	A	view · diff
v1.0.0	2026-08-25	fd539ff	8,053 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (7394 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

renky1025/agent-skills · 11 stars · license MIT · pushed 2026-10-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_q6dph33unrhmw5ds
GET https://markdownregistry.com/api/v1/resolve?ref=renky1025/agent-skills/black-humor-writing
GET https://markdownregistry.com/api/v1/blob/ba2b42bddef4e91c07a6f36e8694c5ac3aac903c5a664b624e1299950f7dfb64

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.