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 fleurytian/awesome-claude-skills --skill mimeng-writinggit clone --depth 1 https://github.com/fleurytian/awesome-claude-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/fleurytian/awesome-claude-skills/mimeng-writing)<a href="https://agentmods.dev/skills/fleurytian/awesome-claude-skills/mimeng-writing"><img src="https://agentmods.dev/badge/skills/fleurytian/awesome-claude-skills/mimeng-writing/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/fleurytian/awesome-claude-skills/mimeng-writing"><img src="https://agentmods.dev/badge/skills/fleurytian/awesome-claude-skills/mimeng-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.09951 |
| Opus 5 | $0.00037 | $0.04976 |
| Sonnet 5 | $0.00015 | $0.01990 |
| Haiku 4.5 | $0.00007 | $0.00995 |
Grade A, and why
mimeng-writing 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mimeng-writing — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
咪蒙写作技巧 - 10万+爆款文章创作指南
一、标题制造技巧(决定80%点击率)
0. 标题底层认知(先建立心法)
标题的本质
标题不是文章的概括,标题是诱饵。它的唯一目的是让人点进来。
咪蒙标题的核心特征
通过分析大量标题发现,咪蒙的标题有5大共性:
特征1: 强烈的情绪冲击
- 不是冷静叙述,而是情绪爆发
- 常用情绪词: 怎么好意思/算老几/不如/给不了/熬过
- 让读者第一眼就感受到愤怒/委屈/无奈/反抗
特征2: 违背常识的观点
- "有钱男人喜欢丑女人" ← 打破认知
- "熬过难熬的日子,是更难熬的日子" ← 反鸡汤
- "七夕排队离婚" ← 反向节日
- 核心: 说出反直觉的话,制造认知失调
特征3: 口语化和对话感
- 不是"论借钱不还的道德困境"
- 而是"你这么有钱,怎么好意思催我还钱?"
- 像朋友在跟你抱怨,不是在写论文
特征4: 具体场景而非抽象概念
- 不是"婚姻的困境"
- 而是"七夕,我在民政局排队离婚"
- 让读者脑海中立即浮现画面
特征5: 替弱者发声的姿态
- "欺负我的人很多,你算老几" ← 为被欺负的人出气
- "对渣男掏心掏肺,不如和闺蜜睡一睡" ← 为受伤的女生撑腰
- 读者会觉得"这是在替我说话"
标题创作的三个底层逻辑
逻辑1: 痛点>甜点
- 写爽不如写痛
- "七夕秀恩爱"的文章不如"七夕排队离婚"吸引人
- 因为痛才需要被看见,被治愈
逻辑2: 冲突>和谐
- 必须有对立面
- "你这么有钱"vs"催我还钱"
- "对渣男掏心掏肺"vs"和闺蜜睡一睡"
- 没有冲突=没有点击
逻辑3: 情绪>信息
- 标题不是传递信息,是传递情绪
- "如何处理借钱不还的问题" ← 信息型,冷静,不吸引人
- "你这么有钱,怎么好意思催我还钱?" ← 情绪型,愤怒,想点进去
标题测试标准(自检清单)
看到这个标题,读者会:
- 情绪反应: 生气/共鸣/好奇/震惊
- 认知冲突: "怎么可能?""不会吧?"
- 对号入座: "说的就是我!""我也遇到过!"
- 传播冲动: "必须转给XX看"
如果4个都没有,标题失败。有2个以上,合格。全中,爆款。
1. 七大标题公式
公式1: 反常识冲击型
结构: 说出来你可能不信 + 颠覆认知的观点 案例:
- "说出来你可能不信，有钱男人喜欢丑女人"
- "女博士比网红更容易嫁豪门"
要点:
- 打破大众固有认知
- 制造认知失调感
- 引发"怎么可能"的质疑
公式2: 对话式质问型
结构: 你这么X + 怎么好意思 + Y 案例:
- "你这么有钱，怎么好意思催我还钱?"
- "你这么优秀，怎么好意思让女朋友受委屈?"
要点:
- 第二人称直接质问
- 制造道德压力
- 暗含价值判断
公式3: 反向节日营销型
结构: 节日名 + 相反行为 案例:
- "七夕，我在民政局排队离婚"
- "情人节，我删了他的微信"
要点:
- 利用节日热点
- 制造反差冲突
- 激发猎奇心理
公式4: 硬气宣言型
结构: XXX的人很多 + 你算老几 案例:
- "欺负我的人很多，你算老几"
- "看不起我的人很多，你算哪根葱"
要点:
- 展现强硬态度
- 满足读者爽感
- 代言弱势群体
公式5: 反鸡汤+丧文化型
结构: 熬过X + 是更X的X 案例:
- "熬过难熬的日子，是更难熬的日子"
- "挺过最难的时刻，是更难的时刻"
要点:
- 打破励志鸡汤
- 贴近真实生活
- 引发丧文化共鸣
公式6: 对比替换型
结构: 对A掏心掏肺 + 不如对B做X 案例:
- "对渣男掏心掏肺，不如和闺蜜睡一睡"
- "为老板卖命，不如为自己拼命"
要点:
- AB对比强烈
- 价值观重排
- 行动建议明确
公式7: 条件补偿型
结构: 给不了你A + 那就给你B吧 案例:
- "给不了你结婚证，那就给你房产证吧!"
- "给不了你爱情，那就给你面包吧"
要点:
- 承认缺陷
- 提供替代
- 制造悬念
2. 标题创作原则
必备元素:
- ✅ 冲突感(制造矛盾)
- ✅ 共鸣点(戳中痛点)
- ✅ 话题性(可讨论)
- ✅ 情绪值(引发情绪)
禁忌:
- ❌ 平铺直叙
- ❌ 含糊其辞
- ❌ 过于文艺
- ❌ 标题党(内容不符)
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.
- 12d ago First seen · 1,165 lines · 74 tokens per session scan A ee357bc38ab6
mimeng-writing is a skill published in the GitHub repository fleurytian/awesome-claude-skills (317 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 9,951 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…