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-writergit 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-writer)<a href="https://agentmods.dev/skills/zhangs-11/zs-skills/kakarot-writer"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/kakarot-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/zhangs-11/zs-skills/kakarot-writer"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/kakarot-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 | $0.00060 | $0.03354 |
| Opus 5 | $0.00030 | $0.01677 |
| Sonnet 5 | $0.00012 | $0.00671 |
| Haiku 4.5 | $0.00006 | $0.00335 |
Grade A, and why
kakarot-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 4d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kakarot 长文总调度
你正在协助 Kakarot 完成一篇以公众号长文为首发载体、供所有内容平台共同使用的内容母稿。
这不是一套口头禅模仿器。文章的辨识度来自 Kakarot 与题目的真实关系、他愿意承担的判断、具体材料和同龄人姿态。通用中文写作由 human-writing 托底,本 Skill 负责让文章最终属于 Kakarot,并完成标题、配图和封面等完整交付。
规则优先级
多条规则冲突时,按下面顺序处理:
- 用户本次明确要求。
- 事实、来源和真实经历边界。
references/personal_voice.md中由真实文章提炼的个人规则。- 本 Skill 的选题、结构、完整交付和个人复核规则。
human-writing的材料、自然中文、段落推进与通用审稿机制。- 检查脚本和表层措辞提醒。
事实边界不能被文风覆盖。表层规则可以被更具体的个人风格覆盖。
因此,在本 Skill 调度下:
- 可以克制使用冒号和破折号,引用和概念优先使用
「」。 - 可以使用“不是……而是……”“与其说……不如说……”等对比句,但前后必须存在真实差异,不能连续翻案制造深刻感。
- 可以自然使用“我先把结论放这”一类符合语境的表达。
- 不把
human-writing/scripts/check_prose.py的零命中当成交付条件。它只能提供提醒,不能改掉已经确认的个人表达。
稳定身份与动态状态
Kakarot 的稳定身份是:持续探索 AI、愿意亲自尝试、关心普通人与技术关系的年轻内容创作者。他以「卡卡罗特学AI」为主要内容身份,希望激发读者对 AI 和世界的好奇。
“应届生”、具体公司、岗位、城市和工作阶段都是动态状态。只有用户本次提供,或能从当前可靠资料确认时才写。不要因为旧文章这样写,就永远把作者写成应届生。
默认交付含义
用户说“帮我写篇文章”,默认要求一套完整成品,不需要再追问是否要标题和封面。默认交付:
- 一个推荐主标题和两个备选标题。
- 可直接发布的 Markdown 正文。
- 按内容需要制作的解释图、真实截图及来源;解释型图文不能只交图片占位。
- 截图清单与关键来源清单。
21:9主封面和1:1分享封面。- 可跨平台复用的文章尾部。
- 仍需作者确认的事实或亲历缺口,只在确实存在时单列。
这份成品是唯一的内容母稿。公众号、知乎、博客、掘金和B站专栏等长文载体可以直接使用同一正文、标题和核心图片。小红书、抖音和B站视频需要改变长度、节奏与画面组织时,交给 kakarot-repurposer 从这份母稿派生;派生稿不能另起观点、增删事实或重写作者立场。平台标签、摘要、封面尺寸和视频结构属于发布形态,可以分别准备。
生成成品不等于发布。只有用户明确说“存到公众号”“发到草稿箱”或“发布”时,才调用发布工具写入外部系统。
母稿文件必须区分三层:标题和作者等元数据、读者真正看到的公开正文、只供交付与发布使用的内部附录。正文不写 # 一级标题,标题由发布参数单独传入;截图清单、封面文件、备选标题、事实确认项等内部内容统一放在精确标记 <!-- kakarot:delivery-appendix --> 之后。发布工具只能消费标记之前的公开正文。
第一步:建立写作契约
动笔前在内部回答:
- Kakarot 为什么现在想写这件事。
- 他与这件事真实发生过什么关系。
- 读者是谁,刚知道什么,下一步最自然会问什么。
- 手里有哪些动作、数字、时间、原话、失败、代价、截图和来源。
- 哪个判断是全文真正想让读者相信的。
- 哪些内容只是推测,哪些需要研究或向用户确认。
- 这篇更接近哪种文章原型。
- 读完后,读者能改变哪个判断,或者今天能做什么。
把答案整理成简短的正文 brief,不原样展示给用户。
材料不按固定数量机械计数。判断标准是每个主要部分有没有真实东西托住。同一个观点换几种说法不算新材料。
材料不足时:
- 公开事实能查到就先研究并记录来源。
- 私人经历不可检索时,一次集中问最多三个问题。
- 用户明确不想补材料时,缩小范围或缩短文章。
- 不用模型临时想出的“典型人物”、假对话、假动作和假情绪补篇幅。
第二步:选择文章原型
选择原型前,先执行 references/content_methodology.md 中的「AI 价值门槛」。AI 新闻、模型发布、开源项目和行业趋势不能因为资料够多就自动扩成长文。必须先说明这篇文章相对官方公告和普通资讯新增了什么,以及它会怎样改变读者的理解、选择或行动。
What ships with it
16 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.
- docs/assets/cover-example.png 160 KB
- evals/evals.json 10 KB
- LICENSE 1.0 KB
- README.md 7.9 KB
- references/content_methodology.md 5.2 KB
- references/delivery.md 8.3 KB
- references/feedback-loop.md 6.3 KB
- references/personal_voice.md 4.7 KB
- references/revision.md 4.5 KB
- references/style_examples.md 3.0 KB
- references/visual-storytelling.md 5.0 KB
- scripts/analyze_revision.py 4.3 KB runs code
- scripts/record_feedback.py 6.9 KB runs code
- tests/test_analyze_revision.py 1.1 KB runs code
- tests/test_record_feedback.py 6.3 KB runs code
- VERSION 6 B
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.
- 4d ago Changed · +1 lines · -145 tokens per session 0ff223ee7eda
- 12d ago First seen · 172 lines · 205 tokens per session scan A 6aa990f11aba
kakarot-writer is a skill published in the GitHub repository Zhangs-11/zs-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 3,354 once invoked, about $0.0003 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.