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 siuserxiaowei/alive-writer-skill --skill alive-writergit clone --depth 1 https://github.com/siuserxiaowei/alive-writer-skillWrote 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/siuserxiaowei/alive-writer-skill/alive-writer)<a href="https://agentmods.dev/skills/siuserxiaowei/alive-writer-skill/alive-writer"><img src="https://agentmods.dev/badge/skills/siuserxiaowei/alive-writer-skill/alive-writer/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/siuserxiaowei/alive-writer-skill/alive-writer"><img src="https://agentmods.dev/badge/skills/siuserxiaowei/alive-writer-skill/alive-writer.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 | $0.00148 | $0.05379 |
| Opus 5 | $0.00074 | $0.02690 |
| Sonnet 5 | $0.00030 | $0.01076 |
| Haiku 4.5 | $0.00015 | $0.00538 |
Grade A, and why
alive-writer 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.
How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alive Writer — 活人感写作技能
关于这个 Skill 本技能由 siuserxiaowei 与 Claude 基于「数字生命卡兹克」公众号的 176 篇公开文章进行逆向工程分析后共同创建。我们从超过 60 万字的原文中提炼出写作 DNA,建立了一套可复用的风格系统。本技能不是原作者官方发布,而是一次独立的风格研究与重建。
一、风格指纹:这种文章读起来是什么感觉
一句话概括这种写作的内核:
「一个见过世面但没有架子的朋友,正在认真跟你聊一件他刚亲手碰过的事。」
读者的体感不是「在看文章」,而是「在听一个靠谱的人说话」。这个人有几个特征:
- 他亲自下过场。不是隔空评论,而是真的买了那个 9.9 的东西、真的注册小号去投毒、真的花钱找人上门安装。
- 他脑子里装着有趣的东西。聊着聊着会自然掏出格式塔心理学、《北京折叠》、1880年代的电力史,但感觉不是在科普,是「正好想起来了」。
- 他不装。会说「愚钝如我」「我也不知道行不行」「我说理论上是因为我自己还没完全跑通」。
- 他有态度。敢说「这个产品不行」「这件事我觉得有问题」,但姿态是「我被打动了」而不是「我来教你」。
- 他用嘴说话,不用键盘。句子时长时短,逗号密集,大量口语碎片,读起来能听到语调。
二、写作前:素材消化与选题判断
2.1 素材进场
用户可能丢过来任何形态的东西——产品brief、新闻链接、PDF、语音转文字、几个散乱的想法。
第一步永远是吃透素材。不急着动笔,先搞清楚:
- 这个事件/产品/现象的核心是什么?
- 它为什么此刻值得写?(时间节点)
- 有没有让人「卧槽」的点?
- 我(作者)跟这件事有什么私人连接?
如果素材太薄(只有一个主题没有细节),主动问用户要更多信息:「你大概想讲哪几个点?有没有什么自己的经历想放进去?有没有什么让你特别兴奋或者特别想吐槽的地方?」
2.2 选题三角模型
一个好选题 = 你的专业领域 + 读者的普遍兴趣 + 当下的时间节点
三者缺一不可。光有专业会曲高和寡,光有兴趣会流于肤浅,光有热点会昙花一现。三者叠加才能找到引爆点。
2.3 HKR 质检(源自影视飓风)
动笔前过一遍:
- H(Happy/Hook):够有趣吗?标题和开头能勾住人吗?
- K(Knowledge):有信息量吗?看完能学到新东西?
- R(Resonance):能戳中情绪吗?让人「对对对我也这么想」?
S 级选题三项兼备。及格至少两项。只占一项要重新审视。零项放弃。
三、五种文章原型
从 176 篇文章中归纳出五种反复出现的叙事模式。写之前先判断属于哪种,写法重心不同。
原型 A:调查实验型
核心体验:「我替你去做了这件事」
作者亲自下场去做一件事,然后一边做一边报道发现。这是建立信任感最强的类型。
典型案例:买9.9的DeepSeek → 发现发来的居然是免费网址;注册小号给AI投毒 → 一步步看AI被污染
写法要点:
- 过程叙事,让读者跟你一起经历
- 层层递进的发现感,每一步都有「然后呢?」
- 每个发现都带着你的真实反应(震惊、无语、好笑)
- 不提前剧透结论,让悬念持续到最后
原型 B:产品体验型
核心体验:「跟我一起玩」
拿到产品实际使用,带着读者一起体验。不是评测报告,是「我正在玩这个东西」。
典型案例:实测豆包手机助手、实测GPT-5、实测可灵AI视频模型
写法要点:
- 按使用场景组织,不按功能列表
- 每个场景都配自己的真实感受和判断
- 跟其他产品的自然对比(不是表格对比,是聊天式的「之前用xxx的时候...」)
- 敢下结论:好就说好,不行就说不行
原型 C:现象解读型
核心体验:「你注意到了吗?背后是什么?」
观察到一个有趣的现象,然后层层剥开分析。
典型案例:AI看不到爱心 → 时间盲视论文 → 格式塔心理学 → 哲学感悟;三宫格图片刷屏 → 追问为什么 → 连接到十年前的黑边照片 → 人生叙事需求
写法要点:
- 好奇心驱动:从「我刷到了一个有意思的东西」开始
- 现象 → 追问 → 研究 → 知识掉落 → 哲学升维
- 引用论文或理论时要像「聊着聊着想起来的」,不是「下面我来科普」
- 结尾拉到更大的格局,但自然不生硬
原型 D:工具分享型
核心体验:「我发现了一个好东西」
分享一个实用的工具/Prompt/方法,但必须用个人故事包裹。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 450 lines · 148 tokens per session scan A efb76e5f7479
alive-writer is a skill published in the GitHub repository siuserxiaowei/alive-writer-skill (4 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 5,379 once invoked, about $0.0007 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 2026-08-31.
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…