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 yan-labs/yan-skills --skill rankupgit clone --depth 1 https://github.com/yan-labs/yan-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/yan-labs/yan-skills/rankup)<a href="https://agentmods.dev/skills/yan-labs/yan-skills/rankup"><img src="https://agentmods.dev/badge/skills/yan-labs/yan-skills/rankup/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/yan-labs/yan-skills/rankup"><img src="https://agentmods.dev/badge/skills/yan-labs/yan-skills/rankup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 65 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 150 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 262 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 265 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 266 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 267 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.01115 | $0.12939 |
| Opus 5 | $0.00558 | $0.06470 |
| Sonnet 5 | $0.00223 | $0.02588 |
| Haiku 4.5 | $0.00112 | $0.01294 |
Grade A, and why
rankup scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 接入必须**线上实测**：`curl` grep beacon 只证脚本在，CF WA 还要 GraphQL `count > 0` | `site_token` 填成 `site_tag` 不报错，一个站空跑了 45 天 | How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rankup 3.0
给独立开发者用：做产品，也做关键词流量站、AI 工具、桌面客户端上架商店、付费订阅。
共同点是靠 SEO + GEO 拿免费曝光导到自己的平台；市场是全球，任何语种任何国家，有流量就做。
本文件只做两件事：把一句话落到七段生命周期的哪一段，以及每段的硬规则。怎么干活的纪律在 references/discipline.md。
一句话落到哪一段
用户不会说「跑一下 seo-audit.mjs」，他会说下面这些话。命中就照入口走，不要自己现编步骤。
| 用户会说的话 | 段 | 入口 |
|---|---|---|
| 「看下这批数据有没有能做的关键词」「找几个关键词」「挖点需求」「最近有什么能做的」 | 1 | playbooks/research.md（P0 分流 → 词根调研） |
| 「调研一下这个词」「调研一下这关键词」「调研的关键词」「这个词能不能做站」「这词难不难」「帮我扩词」 | 1 | research.md P2 词根调研：任何词都是词根，先直接搜再扩树（旧 P3 已并入 P2，不再有单独的扩词流水线） |
| 「谁在赚钱」「反查这个站」「竞品最近在做什么」「帖子说月入 X 是真的吗」 | 1 | research.md P4 + demand-sources.md 第十节 |
| 「XX 和 YY 哪个更火」「今天美国/日本在搜什么」「哪个国家有机会」 | 1–2 | trends.md，scripts/gt.py |
| 「有什么游戏站能做」「跑一下小游戏监测」 | 1 | game-opportunity Skill；建站再读 game-sites.md |
| 「这个方向做不做」「做哪个语种」「要不要上多语言」「做成工具还是内容站」 | 2 | lifecycle.md 段 2 |
| 「我们做个网站吧」「新建个站」「想做个工具站」「帮我搭起来」 | 2→3 | 先过段 2 立项定位，再段 3 初始化；手上没有词树先回段 1，不许跳过 |
| 「一步步来」「我们开始执行这个项目的计划」 | check | 先 rankup check 定位当前段与第一个没过的闸，然后按 checklists.md 逐环节推进，每过一闸记 checks.md；不要跳过 check 直接猜段 |
| 「做个功能吧」「加个 X 功能」「把这个做出来」「实现一下这个」 | 3 | 红线先行：任何 UI 一律用脚手架自带的 shadcn 组件库（components/ui/），缺的 shadcn add 或装同生态的现成组件，禁止手写下拉框 / 弹窗 / 日期选择 / 表格分页 / Toast；然后按段 3 硬规则与 checklists.md 段 3 做，做完段 4 全套体检 |
| 开发时挂着当规范：「按 rankup 规范来」「这个页面这样写行不行」「这块要不要 SSR」 | 3–4 | 本文段 3、段 4 硬规则 + checklists.md 对应段 |
| 「我们做个内页吧」「把这个关键词做成内页」「关键词没问题了，做成内页」 | 4 | 一个关键词对应一个内页：目标词登记、TDK、独立 OG 含图、密度、无占位、体检全套；页面上的控件同样只准来自组件库（红线，见 discipline.md 十六）；lifecycle.md 段 4 + checklists.md 段 4 |
| 「看一下 SEO 有没有问题」「看一下 GEO 有没有问题」「GEO/SEO 有没有问题」 | 4 | 段 4 体检：seo-audit.mjs、is-agentic.mjs、aitdk-opencli.sh、seo-webcafe.mjs audit、哥飞 AI；分组见 playbooks/site-review.md A / C / E 组 |
| 「能不能上线了」「上线前还差什么」「TDK」「关键词密度」「标题描述怎么写」 | 4 | checklists.md 段 4 + seo-box.md |
| 「怎么被 AI 引用」「llms.txt」「对 AI 代理友好吗」「AEO/GEO」 | 4 | seo-growth.md 三-B |
| 「AI 会不会推荐我们」「GEO 反推」「试试 AI 搜这个词会推荐谁」 | 4 | seo-growth.md 三-B GEO 反推测试 |
| 「帮我生成 logo / 配图 / 封面 / 海报」「要张 og 图」「画个吉祥物」 | 3–4 | /imagegen：图片必须真实生成，不允许占位图 |
| 「做个好看的页面」「有没有什么好的设计参考」「Hero 怎么设计」「找个组件参考」「landing page 怎么排」「有什么动画效果」「页面设计灵感」 | 3 | 先浏览 design-references.md 收录站的相关分类，选 2–3 个案例参考后再实现；基础控件仍走 shadcn 组件库红线 |
| 「写一下这页的文案」「这稿子 AI 味太重」「帮我改稿」「语言结构理顺一点」「怎么写才会被 AI 引用」 | 4 | 中文：/write（先确认它的五个附属 Skill 都在，缺的用 find-skills 装齐；装不上才退到 /human-writing 起稿 → /shuorenhua 去 AI 味，见 skill-ecosystem.md）；内容形状按 /ai-seo 的 content-patterns；JSON-LD 只取 /seo-geo 的模板 |
| 「文案怎么写才有人点」「定价页怎么排」「用户为什么不买」「还有什么渠道能推」 | 7 | /marketing-psychology（锚定、社会认同、损失厌恶等用在页面与定价上）+ /marketing-ideas（渠道清单）；判据仍以 conversion.md 为准 |
| 「站慢不慢」「跑个性能」「Core Web Vitals」 | 4 | seo-box.md 一，scripts/pagespeed.mjs plan --strategy both |
| 「这个域名能不能用」「域名前世」「域名黑历史」 | 5 | lifecycle.md 段 5 黑历史闸门 + seo-webcafe.md history |
| 「域名买完了」「帮我绑域名」「这个域名绑一下」 | 5 | cloudflare-stack.md §8.5「域名绑定到 Workers（全 API，零界面操作）」：添加 zone → 绑 Workers 自定义域名 → 设 SITE_URL → 告知 NS → 等激活 → 放开索引 |
| 「数据检测平台都接入了吗」「GSC 接了没」「提交 sitemap」「怎么一直不收录」 | 5 | search-platforms.md、analytics-platforms.md |
| 「把 Ahrefs 的检验结果都修了」「全站内链失效」「重定向链」 | 5→4 | scripts/ahrefs-site-audit.mjs 取清单，修完按段 4 全套重跑 |
| 「帮我搞点外链」「去哪发外链」「竞品的外链哪来的」「这些外链有没有毒」 | 6 | backlink Skill + webcafe-topics.md 五 |
| 「发个 Product Hunt」「上架发布平台」 | 6 | product-launch.md |
| 「访客不注册」「没人付费」「定价怎么定」「接 PayPal」「AdSense 被拒」 | 7 | monetization.md、conversion.md |
| 「流量掉了」「排名没了」「是不是被 K 了」 | 7 | webcafe-experiences.md 十七～十九 |
| 「现在该做什么」「到哪一步了」「本轮还差什么」 | check | 本文 rankup check → site-review.md 二 |
| 「review 一下我的站」「帮我看看这个站有什么问题」「查漏补缺」「这项目脱轨了」 | review | 本文 rankup review → site-review.md 一 |
| 「我想让流量涨一点」「今天弄下 SEO」「优化一下我的网站」 | check | 先 rankup check 定位第一个没过闸的段；默认打磨转化链路，不重构（zero-to-one.md） |
| 「把这个老项目接进来」「rankup init」 | init | 本文 rankup init → project-memory.md |
| 「群里怎么说的」「哥飞说过什么」「论坛里搜一下」 | 经验 | webcafe-forum.md，scripts/webcafe-forum.mjs chat-search 拿原文，不问 ask |
| 「我看到一个帖子分享 SEO 的东西，你把这东西记下来更新到源码里」「把这个经验写进 rankup」 | 维护 | 维护 Skill 本身：按 experiences/INDEX.md 收录规则与 evolution.md 晋升门写进对应的现有文件，不新建文件；见文末「经验回流」 |
| 「抓一下后台数据」「导出报表」「数据面板」「Semrush 能查这个吗」 | 取数 | discipline.md 六 + provider-capabilities.md：有脚本先跑，没有才加载 backlink |
| 说的事这张表没有 | — | capability-map.md → skill-ecosystem.md → /skillsmp → 最后才按 integrations.md 用 find-skills；不要现写等价实现 |
| 本文点名的任何兄弟 Skill 本机没装 | — | 加载 find-skills 搜索并安装，装完再继续；不跳过、不现写替代。每台机器装的不一样，文档只保证「该用什么」（skill-ecosystem.md「缺 Skill 的处置」） |
What ships with it
60 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.
- .gitignore 368 B
- data/provider-capabilities.json 226 KB
- data/word-roots.json 17 KB
- references/analytics-platforms.md 14 KB
- references/capability-map.md 34 KB
- references/checklists.md 46 KB
- references/cloudflare-stack.md 33 KB
- references/demand-sources.md 79 KB
- references/design-references.md 6.0 KB
- references/discipline.md 43 KB
- references/evolution.md 23 KB
- references/experiences/conversion.md 15 KB
- references/experiences/demand-discovery.md 44 KB
- references/experiences/INDEX.md 5.3 KB
- references/experiences/webcafe-experiences.md 37 KB
- references/experiences/webcafe-topics.md 20 KB
- references/experiences/zero-to-one.md 12 KB
- references/game-sites.md 10 KB
- references/integrations.md 47 KB
- references/lifecycle.md 112 KB
- references/monetization.md 11 KB
- references/playbooks/INDEX.md 4.7 KB
- references/playbooks/research.md 60 KB
- references/playbooks/site-review.md 49 KB
- references/product-launch.md 8.2 KB
- references/project-memory.md 26 KB
- references/provider-capabilities.md 91 KB
- references/provider-script-gaps.md 18 KB
- references/research-checklist.md 20 KB
- references/search-platforms.md 25 KB
- references/seo-box.md 23 KB
- references/seo-growth.md 157 KB
- references/seo-webcafe.md 53 KB
- references/skill-ecosystem.md 24 KB
- references/trends.md 43 KB
- references/webcafe-forum.md 21 KB
- scripts/ahrefs-setup.mjs 21 KB runs code
- scripts/ahrefs-site-audit.mjs 16 KB runs code
- scripts/archive/gt-v1/gt-browser.mjs 26 KB runs code
- scripts/archive/gt-v1/gt.py 10 KB runs code
- scripts/archive/gt-v1/README.md 2.2 KB
- scripts/cf-agent-baseline.mjs 23 KB runs code
- scripts/cf-analytics-setup.mjs 6.5 KB runs code
- scripts/cf-builds-connect.mjs 19 KB runs code
- scripts/cf-zone-setup.mjs 5.1 KB runs code
- scripts/chatbot-drive.browser.js 20 KB runs code
- scripts/check-version.mjs 17 KB runs code
- scripts/clarity-setup.mjs 12 KB runs code
- scripts/demand/_lib.mjs 18 KB runs code
- scripts/demand/ads-transparency.mjs 15 KB runs code
- scripts/demand/aitdk-lookup.mjs 17 KB runs code
- scripts/demand/appstore-charts.mjs 12 KB runs code
- scripts/demand/boards.mjs 45 KB runs code
- scripts/demand/chrome-ext-gap.mjs 17 KB runs code
- scripts/demand/chrome-stats.mjs 13 KB runs code
- scripts/demand/freelance-demand.mjs 18 KB runs code
- scripts/demand/game-newtitles.mjs 32 KB runs code
- scripts/demand/game-platform-monitor.mjs 13 KB runs code
- scripts/demand/github-skill-search.mjs 17 KB runs code
- scripts/demand/github-trending.mjs 11 KB runs code
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.
- today Changed · +4 lines ca27af6d021c
- 2d ago Changed · +2 lines b76b0ddd3d87
- 4d ago Changed · +1 lines 4308154a36fe
- 8d ago Changed · -699 lines · +320 tokens per session fecf897d869d
- 12d ago First seen · 980 lines · 795 tokens per session scan A 9ae2460400d4
rankup is a skill published in the GitHub repository yan-labs/yan-skills (185 stars, last pushed today), licensed MIT. It adds 1,115 tokens to every session and 12,939 once invoked, about $0.0056 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
ima-dai-sdk
Integrates the Google Interactive Media Ads (IMA) Dynamic Ad Insertion (DAI) SDK into websites, web apps, mobile apps, or TV apps. Use when: - A video player needs to load and play HLS or DASH streams in web apps, Android apps, iOS apps, tvOS apps, Cast (CAF) receivers, or Roku channels. - The app needs to make use of…
migrate-xml-views-to-jetpack-compose
Provides a structured workflow for migrating an Android XML View to Jetpack Compose. This skill details the step-by-step process, from planning and dependency setup, to theming and layout migration, validation and XML cleanup. Use this skill when you need to migrate an XML View to Jetpack Compose in an Android…
baseline-ui
Quickly deslop UI code by fixing spacing, hierarchy, typography, and small layout issues. Use when the interface needs a fast cleanup or polish pass.
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.
cherry-electron-dev
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools inspection, lag or jank investigation, CPU and memory monitoring, leak checks, and startup-performance analysis; reuse a verified workspace instance…