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 agentmods add skills/chengkj99/kj-skills/coding-session-to-tutorialnpx skills add chengkj99/kj-skills --skill coding-session-to-tutorialgit clone --depth 1 https://github.com/chengkj99/kj-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/chengkj99/kj-skills/coding-session-to-tutorial)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/coding-session-to-tutorial"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/coding-session-to-tutorial.svg" alt="Measured on agentmods" 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 | $0.00132 | $0.01601 |
| Opus 5 | $0.00066 | $0.00800 |
| Sonnet 5 | $0.00026 | $0.00320 |
| Haiku 4.5 | $0.00013 | $0.00160 |
Grade A, and why
coding-session-to-tutorial 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 6d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
实战案例转教程
把一段原始的实战记录(可以很乱、很碎、有弯路)转化为其他程序员可以直接学习和复用的教程。
这个技能的核心价值:你解决问题用了 1 小时,教程让下一个人 10 分钟搞定。
执行流程(每次必走)
第 1 步:读取和整理输入
接受以下任意形式的输入:
- 终端命令和输出(粘贴即可,不需要整理)
- 一段对话描述(「我先试了 A,不行,然后试了 B,还是不行,最后用 C 解决了」)
- 截图描述(「截图里显示的是 xxx 报错」)
- 多种形式混合
不要催用户整理输入。你来整理。
从输入中提取:
- 问题是什么(现象 + 报错/数据)
- 初步假设是什么(用户当时以为是什么原因)
- 尝试过哪些方法(包括走过的弯路)
- 最终解法
- 有没有预防/验证步骤
只提取素材明确支持的事实。不得为了补齐叙事而推测用户的初步假设、弯路、AI 分析过程、耗时、次数或最终结果。素材未提供的字段标记为“未提供 / 待确认”,或在不影响教程成立时省略。
如果信息明显不够(不知道问题是什么,或不知道最终怎么解决的),只问 1 个最关键的缺失问题,不要问多个。
第 2 步:确认教程定位
在开始写之前,向用户确认一件事(简短即可):
「这篇教程准备放在哪里?」
- A. 公众号文章(更偏叙事,情感节奏)
- B. 个人网站/Wiki(完整技术记录,干货为主)
- C. 内部沉淀(团队内部,注重可复用性)
不同定位影响叙事详细程度,但结构一致。如果用户没有明确偏好,默认 B(完整技术记录)。
第 3 步:按模板生成教程初稿
引用 references/tutorial-template.md,生成完整的教程初稿。
强制要求:
- 初步假设有证据才写:用户说过或日志能支持时,忠实保留;没有就不补造。
- 真实弯路必须保留:素材里确实发生过的失败尝试不能删;素材没有弯路时,不得为了故事性强行添加。
- AI 协作方式按证据写:只记录素材能确认的“给了什么 → AI 怎么分析 → 实际结果”;不完整就标注缺口,不代替用户回忆。
- 通用清单必须用 checkbox + 命令块格式,不能写叙述句
- 方法论要升维,从「这次的步骤」升到「下次遇到类似问题的思维框架」
第 4 步:质量自检
生成初稿后,对照 references/writing-principles.md 里的「常见错误清单」过一遍:
[ ] 素材若包含弯路,是否完整保留;素材若不包含,是否没有强行补造
[ ] AI 协作部分是否只写了证据支持的「给了什么 → AI 怎么分析 → 实际结果」
[ ] 通用清单里是否有分支(情况 A / 情况 B)而不是只有一条路
[ ] 方法论是否升维了(不是步骤复述,是可迁移思维框架)
[ ] 所有命令是否都在代码块里
[ ] 时间、大小、次数等具体数字是否全部来自素材;没有数据时是否保守表述或标记待补充
[ ] 是否无虚构的第一人称经历、报错、对话、命令、用户反馈或验证结果
有不符合的,直接修改初稿,不要列出来问用户。
第 5 步:输出 + 后续推荐
输出完整教程初稿后,附一段简短的后续建议:
---
📌 后续建议:
这篇教程初稿已经可以发布。如需进一步加工:
- 想提升文章的「人味」和传播力 → 用 kangjian-skill 做风格润色
- 想生成配套的短视频脚本 → 用 content-creator 工作流 D
- 想拆解成小红书笔记 → 用 content-creator 工作流 F
- 想直接发公众号 → 用 baoyu-post-to-wechat
如果这篇内容还需要一个更好的「内容角度」定位(比如想做成系列),可以把这篇初稿交给 ai-programming-topic-planner 来规划角度。
输出格式规范
标题格式:# AI 编程实战:[问题动词短语]
导言格式:> [一句话定位]
代码块:全部用 ```bash ``` 或对应语言标注
checkbox 清单:全用 - [ ] 格式
阶段标题:有耗时记录时用 ### 第 N 阶段:[名称](约 X 分钟);无记录时用 ### 第 N 阶段:[名称],不补造时间。
判断是否需要补充信息
以下情况需要主动问用户(只问最关键的那一个):
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.
- 6d ago First seen · 134 lines · 132 tokens per session scan A 162a2806b453
coding-session-to-tutorial is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 1,601 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.