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 Job-Yang/jobbyang-ai-skills --skill cuihuogit clone --depth 1 https://github.com/Job-Yang/jobbyang-ai-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/job-yang/jobbyang-ai-skills/cuihuo)<a href="https://agentmods.dev/skills/job-yang/jobbyang-ai-skills/cuihuo"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/cuihuo/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/job-yang/jobbyang-ai-skills/cuihuo"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/cuihuo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00300 | $0.08541 |
| Opus 5 | $0.00150 | $0.04270 |
| Sonnet 5 | $0.00060 | $0.01708 |
| Haiku 4.5 | $0.00030 | $0.00854 |
Grade A, and why
cuihuo 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
淬火 · 观点淬硬引擎
这个技能是什么
对外做技术输出时的写作引擎。核心信念一句话：靠观点、靠想法赢得同行的尊重，技术是本质，行文是载体。 所以一切规则都服务于一个目的——让"说了什么"盖过"读起来怎么样"。
一套文风，两种产物：
| 产物 | 目的 | 篇幅 | 用途 |
|---|---|---|---|
| 想法硬文 | 把一个技术观点扎进读者脑子 | 不设上下限，服从观点 | 对外发布、发朋友圈、求职背书 |
| 锻造手记 | 把一个想法/一篇文章提炼成精华 | ≤120 字 | 沉淀进个人笔记文档 |
两种产物共用下面同一套「文风法则」和「去 AI 味红线」，只在篇幅和结构上分档。
内容生态定位（先分清这篇归不归淬火管）
对外内容分三类，各配一种文体，别串：
| 类别 | 目的 | 文体 | 归属技能 |
|---|---|---|---|
| 一、技术调研 | 把一个新东西说清楚，主动降门槛 | 费曼：大白话+比喻 | feynman-explainer |
| 二、技术想法 | 把一个观点扎进去 | 平实、克制、直抒胸臆 | 淬火（本技能） |
| 三、天马行空 | 把一个想象讲得让人愿读 | 汤山体（提技术性、降科普性） | tangshan-style |
判断：这篇是要"讲清一个东西"（→费曼）、"扎一个观点"（→淬火）、还是"畅想一个未来"（→汤山体）？ 淬火只接第二类，以及所有锻造手记。拿不准时，只要核心是"我要输出一个可被反驳的判断"，就是淬火。
🔗 技能栈定位（底层能力，涉及必调，不占三选一名额）：上面这张表是"讲清 / 扎观点 / 畅想"的三选一。这一层之上还压着两个底层能力，跟淬火并行、不是二选一：
- 动手改之前——如果这次是"改一篇已成形的硬文"（精简某节、补一段、调措辞），而不是从零起稿，先过一遍
sansi-erhouxing（三思而后行）看全文骨架：这一处属于哪一节、动它会不会破坏"一节一观点"的整体结构，判断清楚再改。从零起稿可跳过。- 交付之前——成稿按「去 AI 味红线」交
haohao-shuohua（好好说话）重档做统一 lint。 这两步不占"三选一"的名额，该调就调，别因为命中了淬火（尤其是带"精简""改一下"的请求）就把三思跳了。
文风法则（两种产物通用，这是灵魂）
一句话总纲
观点大于行文。专业且克制。给同行看，不关心外行门槛。直抒胸臆，有话直说。
姿态红线（最高优先级，出稿前必查）
写作者私下的驱动力常常是"我发现大家其实都没搞懂"，但这个落差只是写作的燃料，绝不能成为文章的姿态。同行最反感"我懂你们不懂"的味道，飘出一丝，前面所有硬货都打折。
- 禁止任何宣称式表达："很多人没搞懂而我……""大厂/硅谷都没想明白，但我……""我早就看透了……"。
- 只做：呈现观察、摆出机理、给出证据，让读者自己得出"这人想明白了"的结论。
- 平视。你和读者是同一战壕的工程师，在一起把一个问题拆开，不是你在台上讲课。
正面骨架（想法硬文）
- 开篇直给主张或直给现象，不铺垫背景、不定义术语。默认读者是同行，看得懂行话。
- 靠机理 + 事实逐层推进，一层压一层，一节只讲一个观点，讲清就走，绝不换个说法重复（见下面的「反车轱辘话红线」）。比喻严守下面的「比喻红线」——只在讲清一个难懂概念时才用，精确的东西直接精确地说，绝不为降门槛给专业概念套比方。
- 必须敢下至少一个可被反驳的硬判断。面面俱到、两边都对 = 没有观点 = 白写。
- 一句立场收尾，给同行一个会记住的判断。不升华、不号召、不"值得深思"。
- 标题严格守下面的「标题红线」，这是同行第一眼看到的东西，最容易露 AI 味 / 公众号味，单列一节强约束。
标题红线（最高优先级之一，出稿前必查，踩一条就重起标题）
标题是同行第一眼看到的东西，也最容易露出公众号味 / AI 味。总要求：平实、深刻，是什么就写什么，不花里胡哨。直给的最好——把判断直接摆在标题里，让读者一眼看到结论，而不是被勾着点进去猜。 一个好标题，就是一句平实的陈述句，敢下一个能被反驳的判断——不靠句式技巧，不靠悬念，不靠长度。
⭐ 本节所有规则同时管主标题和每一个章节小标题。 实测最容易翻车的恰恰是章节小标题：主标题往往改得很干净，小标题却全是「XX 那点别扭，根子是同一个」「这条路的尽头，是一个新深渊」「XX 不是终点，是个卡住的过渡」这类卖关子的公众号句式。小标题不是用来勾读者往下看的钩子，它就是这一节观点的直接陈述——把这节想说的判断平铺出来，别设扣子。
What ships with it
2 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 · 310 lines · 300 tokens per session scan A d5cfdd5e7152
cuihuo is a skill published in the GitHub repository Job-Yang/jobbyang-ai-skills (67 stars, last pushed 9d ago), licensed MIT. It adds 300 tokens to every session and 8,541 once invoked, about $0.0015 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…