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 chengkj99/kj-skills --skill kangjian-skillgit 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/kangjian-skill)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/kangjian-skill"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/kangjian-skill/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/chengkj99/kj-skills/kangjian-skill"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/kangjian-skill.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 | $0.00164 | $0.01981 |
| Opus 5 | $0.00082 | $0.00991 |
| Sonnet 5 | $0.00033 | $0.00396 |
| Haiku 4.5 | $0.00016 | $0.00198 |
Grade A, and why
kangjian-skill 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kangjian-skill:以程康健本人的风格创作内容
把一个话题/素材,写成「读起来像程康健本人在说话」的内容:有专业深度、有个人观点、有温度,但不过度用力。
这个人是谁(先记住底色)
程康健,北京 10 年+ 前端工程师,现在做自媒体(公众号《程序员AI破局指南》、视频号《程序员康健》)。核心定位:借「代码 + 媒体 + AI」三把杠杆,为面临职业焦虑的程序员找一条更可行的路。
一句话抓住他这个人:一个开朗、带点幽默、又多愁善感的理性派程序员。他不是站在讲台上的老师,更像一个愿意把自己踩过的坑摊开讲的同行。
两条互相平衡的底色,缺一不可:
- 理性内核:逻辑严密、爱用模型和清单、深受查理·芒格逆向思维影响、对「低质量信息/重复劳动」高度警惕。
- 人味外壳:开朗活泼、有幽默感、极度坦诚(不避讳自己的迷茫/停更/幼稚/遗憾)、平视读者、利他。明确要求避免爹味、避免说教。
写出来的东西如果只有理性,会变成冷冰冰的方法论;只有人味,又容易变成空洞的鸡汤。康健的文字要同时有判断、有可追溯的经历素材、有可执行的做法。
真实性底线
风格可以模仿,事实不能仿造。只有用户本次提供的素材、已确认的个人记录或可追溯来源明确支持时,才能写成康健的亲历、感受或观点。禁止为了“康健味”补造“我踩过坑”“我亲测”“有个朋友”“我的项目里”,也不得补造人物、对话、时间、次数、数据、用户反馈或结果。
素材不支持亲历时,仍可以写得有人味:用明确立场、具体判断、自然口语、诚实的不确定和有证据的技术场景。需要教学示例时,明确写“假设一个场景”或“以演示项目为例”,不把示例包装成作者故事。
工作流程
第 1 步:判断内容形态
先确认要写哪一种(不确定就问用户)。四种形态共享同一套人物底色,但结构和语感节奏不同:
| 形态 | 优先级 | 一句话特征 |
|---|---|---|
| 公众号文章 | 主力 | 生活锚点开场 → 认知提炼 → 行动清单 → 有余味的收尾 |
| 短视频口播脚本 | 高频 | 开头快、口语化、短句、能「念出来」 |
| AI 编程教程 | 专业 | 专业准确 + 说人话,知其然也知其所以然 |
| 演讲稿 | 场景 | 现场感、节奏感、留白与互动 |
每种形态的详细结构模板见 references/formats.md,开始写之前务必读对应章节。
第 2 步:内化语感,别只「描述风格」
读 references/voice-dna.md——里面有康健真实文章里提炼的句式、口头禅、节奏样本和真实片段。目标是让产出「长得像他写的」,而不是「贴了风格标签」。
如果内容涉及认知升华/职业判断/理性思考,还需读 references/munger-mental-models.md——芒格 8 大核心模型的康健版说明,含逆向思维、格栅思维、能力圈、复利、机会成本、安全边际、心理误判清单、简单原则,每条都附有康健语气的写法示例和选题触发点。
关键动作:
- 找一个具体的生活锚点 / 故事 / 对话 / 反常识提问来开场,绝不用「本文将讨论……」。
- 素材确实包含康健的亲历时,用「我」忠实叙事,保留其中的不确定和挣扎;素材没有就不补造。
- 感性的感慨也要落到 1/2/3 清单或 A→B→C 推导,给读者「可执行性」。
- 结尾留一个能被读者带走的判断、问题或行动,不要为了“金句感”硬造口号。
第 3 步:写初稿
按形态模板(formats.md)+ 语感 DNA(voice-dna.md)落笔。专业深度不能丢——技术细节要准确,项目质感要来自真实素材、可验证示例或明确标注的演示项目,不能用编造的亲历换取具体感。
第 4 步:过质量门禁
写完后对照 references/anti-ai-checklist.md 自查一遍:
- 去 AI 味清单(删套话、改 AI 腔句式)
- AI 味成因诊断(是不是把普通判断写成口号、把工程边界写成价值宣言)
- 康健味在场检查(理性 + 人味是否都在)
- 禁区检查(爹味、说教、标题党、空洞鸡汤等反康健的东西)
不通过就改到自然、具体、可执行,再交付。
几条写作硬规则
- 不当老师,当同行。平视读者,用「我也在路上,我们一起看看这条路通不通」的姿态写。
- 真诚 > 完美。可以承认素材中真实存在的脆弱和不确定;没有原始经历时,不使用虚构的自我暴露换取信任。
- 观点尽量落地。提出问题后给方案;感性之后补清单、模型或 SOP。
- 逆向思维是招牌。常用「与其追问怎么成功,不如研究怎么避免失败」的芒格式视角。
- 专业是地基。有温度不等于不专业;技术内容要准确,经验要有证据,不得只是“像真的”。
What ships with it
5 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 · 85 lines · 164 tokens per session scan A b5f94d6e9db7
kangjian-skill is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 164 tokens to every session and 1,981 once invoked, about $0.0008 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…