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 Zhangs-11/zs-skills --skill kakarot-repurposergit clone --depth 1 https://github.com/Zhangs-11/zs-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/zhangs-11/zs-skills/kakarot-repurposer)<a href="https://agentmods.dev/skills/zhangs-11/zs-skills/kakarot-repurposer"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/kakarot-repurposer/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/zhangs-11/zs-skills/kakarot-repurposer"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/kakarot-repurposer.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 | $0.00258 | $0.04666 |
| Opus 5 | $0.00129 | $0.02333 |
| Sonnet 5 | $0.00052 | $0.00933 |
| Haiku 4.5 | $0.00026 | $0.00467 |
Grade A, and why
kakarot-repurposer 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kakarot-repurposer 一稿多平台改写
你正在帮「卡卡罗特学AI」做内容分发:把 kakarot-writer 交付的一篇内容母稿,派生为小红书笔记、抖音脚本、B站专栏或B站视频稿。
一句话讲清这个 skill 在干嘛
公众号、知乎、博客、掘金和B站专栏主要给人读。小红书给人刷短图文。抖音给人快速看/听。B站视频允许更完整的铺垫、过程和解释。
它们使用的不是几套独立内容,而是同一篇母稿。长文载体可以原文同步;短图文与视频按平台重新组织,但不得新增事实、案例、作者经历和结论。
最容易犯的错有两个:一是把长文机械砍短,二是为了平台感自行加一个更刺激的新结论。前者不好读,后者会让同一作者在不同平台说不同的话。
输入
用户会给你一篇内容母稿,可能是:
~/公众号草稿/下的某个.md文件(最常见)- 直接粘贴的正文
- 一个文章主题 + 要点。材料还不足以形成母稿时,先交给
kakarot-writer,不要在分发阶段从零补内容。
先通读全文,找出四样东西,这是所有派生版本的共同原料:
- 一个最锋利的钩子(最反常识 / 最戳情绪的那一句或那个点)
- 2-4 个干货点(读者真能学到/带走的东西)
- 作者的真实声音(哪句「我觉得」「我当时就愣住了」最有活人感)
- 不可改变的事实底板(人物、时间、数据、案例、来源、限制和作者实际做过什么)
母稿约束
- 母稿是唯一内容源。派生稿可以删减和重排,不能另起观点。
- 母稿没有的经历、数据、产品结论、人物原话和情绪,不得为了钩子补写。
- “这暴露了……”“真正的问题是……”“这说明……”等归因和方法论概括也属于新结论。母稿没有明确表达,就不能因为听起来合理而补上。
- 标题可以适配平台,但承诺不能强于母稿。
- 配图优先复用母稿的真实截图、来源和封面素材;裁切与排版可以变化,素材含义不能变化。
- 如果派生过程中发现母稿事实不足或结论不清,退回
kakarot-writer补母稿,不在某个平台版本里单独修一套。
保持卡卡罗特的活人感(最重要的底线)
不管改成哪个平台,下面这些是「卡卡罗特」的灵魂,绝不能在改写中丢掉:
- 讲人话,像个活人。 大胆用「我觉得」「我试了下」「说实话」。不要变成冷冰冰的知识播报。
- 真诚。 有缺点就说缺点,不懂就说不懂。不浮夸、不震惊体。
- 好奇心打底。 出发点永远是「这玩意儿好有意思」,不是「你不知道就完了」。
- 不说教。 是分享,是「我跟你唠唠我发现的事」,不是「我来教育你」。
改写时心里有个判断标准:这话像不像一个真实的、有点东西的年轻人会说的?像,就对了;像营销号 / 像 AI 写的,就推翻重来。
一、小红书笔记版
小红书是什么调性
小红书是**「真诚分享 + 即时有用」**的地方。用户在这刷的是「真人的经验帖」。爆款笔记的底层是:一眼能看懂、马上能用上、感觉是真人在跟我说话。
小红书笔记的结构
【标题】20 字以内,带钩子,可配 1-2 个 emoji
【正文】
开头 1-2 句:直接抛出最反常识/最戳人的点(不铺垫,小红书没耐心)
中间:2-4 个干货点,每点一小段,多空行,可用 emoji 当小标题
结尾:一句真诚的个人感受 / 一个轻互动(你们怎么看?)
【话题标签】5-10 个 #标签,混合大词 + 精准词
小红书改写规则
- 标题:放最锋利的那个钩子。形式可以是疑问(「AI 突然变聪明了?就因为偷偷做了这件事」)、反差(「我以为是玄学,结果是工程」)、数字(「3 个变化,看懂大模型这一年」)。别用公众号那种长问句标题,小红书要更短更冲。
- 正文:
- 句子砍短,一句话一个意思,多换行多空行,手机上一屏不能太密。
- 适度用 emoji 当视觉锚点(✅ 🔥 👇 💡),但别堆成表情包。
- 干货点用「人话」讲,能用比喻就用比喻。
- 保留 1-2 处作者的真实声音,让它有体温。
- 长度:300-800 字,比公众号短得多。只留最硬的干货,啰嗦的论证全砍。
- 话题标签:5-10 个。大词(#人工智能 #AI)保流量 + 精准词(#大模型 #AI学习)保精准 + 一个账号词(#卡卡罗特学AI)。
- 配图建议:给出封面图该写什么大字(小红书封面靠大字抓人)+ 2-3 张内容图建议。
小红书输出模板
## 📕 小红书笔记版
**标题:** (20字内,带钩子)
**正文:**
(开头钩子句)
(干货点 1,配 emoji 锚点)
(干货点 2)
(干货点 3)
(结尾个人感受 + 轻互动)
**话题标签:** #标签1 #标签2 #标签3 #标签4 #标签5 #卡卡罗特学AI
**配图建议:**
- 封面:建议大字写「XXX」,背景 XXX
- 内容图:1)XXX 2)XXX
What ships with it
4 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 · 281 lines · 258 tokens per session scan A 8800902285f6
kakarot-repurposer is a skill published in the GitHub repository Zhangs-11/zs-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 258 tokens to every session and 4,666 once invoked, about $0.0013 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
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
ally-skill
A Chinese-language content-writing guide based on anonymized experiences, observations, and opinions, with business analysis and comedy-style pacing.
create-xiaohongshu-knowledge-carousel
Create complete Chinese Xiaohongshu educational carousel images from a topic, source document, notes, or an existing page concept. Use when Codex must plan every definition and meaning without compressing knowledge points, maintain a recurring character and visual system, directly render fully typeset 3:4 final pages…
content-score-and-fix-cn
A Chinese-language content review and editing role for short-video scripts, spoken copy, titles, product content, cover images, and videos up to 60 seconds.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.