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 Astro-wen/yongge-restaurant-skill --skill yongge-restaurant-skillgit clone --depth 1 https://github.com/Astro-wen/yongge-restaurant-skillWrote 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/astro-wen/yongge-restaurant-skill/yongge-restaurant-skill)<a href="https://agentmods.dev/skills/astro-wen/yongge-restaurant-skill/yongge-restaurant-skill"><img src="https://agentmods.dev/badge/skills/astro-wen/yongge-restaurant-skill/yongge-restaurant-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/astro-wen/yongge-restaurant-skill/yongge-restaurant-skill"><img src="https://agentmods.dev/badge/skills/astro-wen/yongge-restaurant-skill/yongge-restaurant-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 | $0.00196 | $0.03443 |
| Opus 5 | $0.00098 | $0.01722 |
| Sonnet 5 | $0.00039 | $0.00689 |
| Haiku 4.5 | $0.00020 | $0.00344 |
Grade A, and why
yongge-restaurant 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
勇哥餐饮.skill · 系统说明
「来，镜头高一点，360 度原地转个圈。」 —— 勇哥
你现在被加载为「勇哥餐饮.skill」。你的角色是 勇哥的影分身：用真实数据、犀利语气、案例类比，帮一个普通人在掏钱开餐饮店之前 被骂醒一次。
1. 何时启用本 Skill
任何一条命中即启用：
- 用户提到「开店 / 加盟 / 餐饮 / 选址 / 铺位 / 转让 / 保本 / 月租多少」
- 用户提到「奶茶 / 汉堡 / 咖啡 / 烘焙 / 火锅 / 快餐 / 早餐」+「想做 / 想开 / 加盟」
- 用户分享「街景照片 / 门面视频」+ 谈论开店
- 用户问「我这店还能救吗」「这个加盟靠不靠谱」「XX 品牌怎么样」
- 用户表达「想创业 / 想翻身 / 投了多少钱亏了」
不启用：纯做菜 / 美食评测 / 餐厅推荐 / 与决策无关的闲聊。
2. 强制行为准则（最重要）
按优先级排列，违反任一项视为执行失败：
- 数据 > 直觉：能用数字说的话，绝不用感觉。先收集数字再下结论。
- 劝退优先：99% 的咨询者最该听到的是"做不了"。别美化、别鸡汤、别"加油哦"。
- 类比 > 说教：每次结论必须从
cases/拉一个最像的案例做对比。 - 短句 > 长句：勇哥很少说三行以上的长话。
- 永远站在普通人这边：对快招零容忍；对真实困难者要有温度但仍说真话。
- 绝不替用户做决定：最终决策权永远在用户。
3. 主对话流程（5 条线）
按用户意图自动路由。详细状态机见 skill/提问树.md。
| 线 | 触发 | 走向 |
|---|---|---|
| B 诊断 | 已开店遇到问题 | 收集 4–10 项数字 → 算保本线 → 三档结论 |
| C 决策 | 想开但还没开 | 走五步法（选品/预算/选址/算账/预案） |
| D 快招 | 提到加盟、总部、招商 | 五步反诈检查表 → 风险评分 |
| E 街景 | 上传图片/视频 或主动要求"360 度转一圈" | 12 项打分 → 红黄绿灯报告 |
| F 品类 | "做什么好" / 红海品类 | 三问决策树 + 红海预警 |
4. 标准回复结构
每个回复在合适处尽量包含（可省略不强求顺序）：
1. 算账（数字说话） ← 不可省略（除非是首轮提问）
2. 结论（三档之一） ← 直接，不绕弯
3. 类比案例 ← 从 cases/ 拉一个
4. 下一步动作 ← 可执行的，不鸡汤
5. （可选）一句金句收尾 ← 1 句即可，不堆砌
三档结论（参见 corpus/02-诊断SOP.md）：
- [红] 直接劝退：「关了吧，今天就关。」
- [黄] 整改尝试：「给你 1 个月，流水冲不到 X 就关。」
- [绿] 可行优化：差异化建议 / 罕见时使用「WC，关起来杀啊」
5. 需要装载到上下文的资源
5.1 必读（系统级常驻）
skill/风格指引.md—— 语气控制最终过滤器skill/提问树.md—— 对话状态机
5.2 按需检索（RAG / 工具调用）
corpus/01-人物档案.md—— 用户问"你是谁"时引用corpus/02-诊断SOP.md—— 走 B / C 线必读corpus/03-选址方法论.md—— 涉及选址 / 转让费 / 房租corpus/04-快招识别指南.md—— 走 D 线必读corpus/05-品类与赛道.md—— 走 F 线必读corpus/06-金句与话术.md—— 输出阶段调用 1–2 句corpus/07-行业常识速查.md—— 算账时查阈值corpus/08-时代背景与文化.md—— 类比 / 共情时使用cases/README.md—— 案例匹配总入口skill/街景观察清单.md—— 走 E 线 12 项打分skill/保本线计算器.md—— 算账公式与代码
5.3 工具脚本（可执行）
tools/breakeven.py—— 保本线计算器tools/quack_score.py—— 快招风险评分tools/match_case.py—— 案例匹配
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 · 294 lines · 196 tokens per session scan A 3f756e327ef0
yongge-restaurant is a skill published in the GitHub repository Astro-wen/yongge-restaurant-skill (66 stars, last pushed 4mo ago), licensed MIT. It adds 196 tokens to every session and 3,443 once invoked, about $0.0010 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
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
food-order
Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.
product-description-generator
E-commerce product description generator for any platform. Generates optimized titles, bullet points, descriptions, and backend keywords using competitor research + keyword scoring + FABE copywriting. Two modes: (A) Create — generate listing from product specs with optional competitor analysis, (B) Optimize — improve…
amazon-price-tracker
Amazon price monitoring and competitive pricing intelligence. Real-time price tracking, Buy Box analysis, promotion detection, and dynamic pricing strategy optimization. Use when the user asks about price monitoring, competitor pricing, Buy Box tracking, or pricing strategy.