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 tangshan-stylegit 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/tangshan-style)<a href="https://agentmods.dev/skills/job-yang/jobbyang-ai-skills/tangshan-style"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/tangshan-style/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/tangshan-style"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/tangshan-style.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 | $0.00319 | $0.09103 |
| Opus 5 | $0.00160 | $0.04551 |
| Sonnet 5 | $0.00064 | $0.01821 |
| Haiku 4.5 | $0.00032 | $0.00910 |
Grade A, and why
tangshan-style 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 — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
汤山体 · 天马行空畅想文写作引擎
一句话定位：这个技能不生产观点，它把一个面向未来的想象/推演，锻造成"每个句子都耐嚼、每段都有历史纵深"的畅想长文。 只服务一类文章：天马行空的畅想/极端外推（如 Token 战争、AGI 畅想、某个技术趋势推到尽头会怎样）。技术观点硬文（直抒胸臆、讲一个可被反驳的判断）不归它管——走
cuihuo（淬火）。 服务对象：面向读者的对外写作（畅想类稿子、任何要发给别人看的想象力长文）。 面向谁：专业读者。降科普、提技术性——比喻是给硬机制"叠"一层画面感，不是拿来给外行扫盲、更不是拿来替换机制本身。 它偷的是谁的手艺：B站/公众号财经博主"汤山老王"——从他 3 个视频逐字稿 + 8 篇公众号文章里逆向拆出的选题内核与炼句手艺。 核心信条：不是文采好，是有一套过滤网把口水话全滤掉。引擎共用，燃料是你自己的（客户端 + AI 一线经验）。这是引子，不是洗稿。
0. 触发边界（先想清楚：这是"畅想"，还是别的？）
汤山体只管一类活：把一个面向未来的想象/推演写成一篇让人愿读的畅想长文。别的写作任务一律不碰——分给下面对应的技能。
| 你的动作 | 意图 | 用谁 |
|---|---|---|
| 写一篇技术畅想 / 未来推演 / 极端外推（Token 战争、AGI 畅想…） | 把一个想象讲得让人愿读（畅想） | ✅ 汤山体（内部按需喊费曼） |
| 写技术观点硬文 / 直抒胸臆讲一个可被反驳的判断 / 记锻造手记 | 把一个观点扎进去（观点输出） | ❌ 走 cuihuo（淬火），汤山体沉默 |
| 调研一个 GitHub 项目 / 总结一篇文档 / 搞懂一个原理 | 我自己要看懂（输入） | ❌ 走 feynman-explainer，汤山体沉默 |
| 纯翻译 / 一句话快答 / 只要提纲不要正文 | —— | ❌ 都不启用 |
⚠️ 防误触发铁律一（畅想 vs 观点）：如果这篇的核心是"我要下一个当下就能被同行反驳的硬判断"（如"AI 打开 iOS 工程和打开 txt 没区别"），那是观点硬文，归
cuihuo，不是汤山体。汤山体只在核心是"推演一个尚未发生的未来图景"时才醒。判断句式：这篇是"我认为现在是怎样"（→淬火），还是"未来会变成怎样"（→汤山体）？ ⚠️ 防误触发铁律二（畅想 vs 调研）：当任务是"调研/总结/搞懂/讲透"时，即使句子里出现"深入浅出""写得好懂"这类词，也不要启用汤山体——那是费曼的活。
🔗 技能栈定位（底层能力，涉及必调，不占三选一名额）：汤山体是"畅想 / 观点硬文 / 调研讲透"这一层里、三选一的写作引擎之一。它之上还压着两个底层能力，跟本技能并行、不是二选一：
- 动手改之前——如果这次是"改一篇已经成形的畅想稿"（改开头、调某段、精简某节），而不是从零起稿，先过一遍
sansi-erhouxing（三思而后行）看全文骨架，判断这处怎么改才不破坏整体，再动笔。从零起稿可跳过。- 交付之前——成稿按 §5 交
haohao-shuohua（好好说话）重档做统一去 AI 味。 这两步不占"三选一"的名额，该调就调，别因为命中了汤山体就把它们跳了。
0.5 读者设定 · 降科普、提技术性（写畅想文的前置开关）
稿子发给专业读者（同行工程师、AI 从业者、定向朋友圈）。他们不需要被扫盲，最烦车轱辘话和廉价比喻。所以汤山体在"畅想"这条赛道上，必须比它原生的财经科普腔更硬。
- 默认读者是同行，不是外行。 行话直接用，不为每个术语停下来打比方扫盲。只有当某个概念"不解释同行也会卡住"时才喊费曼（§6），且讲完立刻收回畅想节奏。
- 比喻的唯一合法用途是"叠加画面感"，不是"替换机制"。 一个比喻若删掉后读者对机制的理解毫无损失，它就是纯装饰——留一个当锚点即可，其余删。绝不通篇打比方。
- 畅想≠空想。 天马行空的外推也要踩在真实机制/数据/趋势上起跳：先有一块硬地基（真实的技术事实、论文、数据），再往未来蹦。地基部分强制走 §4.5 保真层，不许为了畅想的爽感把它炼没。
- 一句话开关：写这篇时先问自己——"如果读者是比我更懂的同行，这段科普他会不会觉得多余？"会，就删到只剩硬货 + 畅想。
1. 汤山手艺全景（五层过滤器 + 一次握手）
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.
- 12d ago First seen · 304 lines · 319 tokens per session scan A 8cd18f316a6c
tangshan-style is a skill published in the GitHub repository Job-Yang/jobbyang-ai-skills (67 stars, last pushed 9d ago), licensed MIT. It adds 319 tokens to every session and 9,103 once invoked, about $0.0016 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…