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 wot-ui/wot-starter --skill wot-ui-cligit clone --depth 1 https://github.com/wot-ui/wot-starterWrote 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/wot-ui/wot-starter/wot-ui-cli)<a href="https://agentmods.dev/skills/wot-ui/wot-starter/wot-ui-cli"><img src="https://agentmods.dev/badge/skills/wot-ui/wot-starter/wot-ui-cli.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.00958 |
| Opus 5 | $0.00046 | $0.00479 |
| Sonnet 5 | $0.00019 | $0.00192 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
wot-ui-cli 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 7d 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.
What it actually says
Wot UI CLI Skill
这个 skill 用于让 Agent 在处理 @wot-ui/cli 本身相关的问题时，优先基于本仓库 README 与实际命令能力回答，而不是把它误当成纯组件库文档。
适用场景
- 用户询问
wot命令怎么用。 - 用户需要区分
list、info、doc、demo、token、changelog、doctor、usage、lint、mcp、extract的用途。 - 用户要接入 MCP Server，或需要
wot mcp的配置与调试方法。 - 用户要在本仓库中调试
@wot-ui/cli、验证构建产物、重新提取数据。 - 用户的问题本质上是 open-wot 仓库维护问题，而不是单纯的 wot-ui 组件使用问题。
适用范围
- 关注对象是
@wot-ui/cli这个工具包，以及仓库open-wot的开发维护流程。 - 重点覆盖命令能力、通用参数、MCP、离线数据来源、提取流程、本地调试和发布包边界。
- 如果任务是生成
wd-*页面代码、解释组件 props 或给出主题定制方案，应优先使用wot-ui-v2skill。
推荐流程
- 先确认用户是在问 CLI 工具本身，还是在借 CLI 查询组件知识。
- 如果是命令使用问题，优先按命令类别回答：组件知识、项目分析、MCP、数据提取、仓库开发。
- 如果是仓库维护问题，优先给出本仓库里的实际调试命令，而不是泛泛而谈。
- 如果涉及组件内容本身，可引导或切换到
wot-ui-v2skill。
命令分组
组件知识查询
wot listwot info <Component>wot doc <Component>wot demo <Component> [name]wot token [Component]wot changelog [version] [component]
项目分析
wot doctor [dir]wot usage [dir]wot lint [dir]
MCP
wot mcp
数据提取与仓库维护
pnpm extract:cli --wot-dir ../wot-ui --output data/v2.jsonpnpm extract:clonepnpm exec tsx src/index.ts <command>pnpm buildnode dist/index.mjs <command>
工作规则
- 包名是
@wot-ui/cli，实际可执行命令是wot。 - 回答命令问题时，优先用仓库 README 中已承诺的行为和参数，不臆造未声明子命令。
- 回答本地调试问题时，优先给源码入口：
pnpm exec tsx src/index.ts ...。 - 回答构建产物问题时，再给
node dist/index.mjs ...。 - 回答 MCP 问题时，要说明
wot mcp走 stdio，终端无交互输出通常是正常现象。 - 回答提取逻辑问题时，要说明数据主要来自上游
wot-ui/wot-ui的 markdown 与 SCSS 源码。 - 当用户问的是组件知识但入口是 CLI，也要保留“这是通过 CLI 查询组件知识”这一层语义。
参考资料
What ships with it
1 file 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.
- 7d ago First seen · 74 lines · 93 tokens per session scan A 3ed0d47fb5d0
wot-ui-cli is a skill published in the GitHub repository wot-ui/wot-starter (386 stars, last pushed 9d ago), licensed MIT. It adds 93 tokens to every session and 958 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
tinyvue-develop-spec
Development rules for a TinyVue component library that supports Vue 2 and Vue 3, desktop browsers, and mobile-first layouts. They separate templates, reusable logic, styles, design rules, localization, and tests.
export-component-to-other-repo
Port a component from nextjs-css-agent-components into a different repo without losing the design-system precision. Use when the user says "copy this component to ", "lift Button into ", "bring the Thin layout over", or otherwise wants a faithful transplant of one or more components from this codebase. Carries over…
build-app-page
Construct a new app page from scratch using this repo's component system. Use when the user says "build a new page for X", "create a settings page", "add a dashboard for Y", "scaffold an app screen", or otherwise wants a Next.js page assembled from the project's elements/components/patterns. Produces a route under…
next-upgrade
Upgrade Next.js to the latest version following official migration guides and codemods.
admin-net-frontend
Use when building Vue 3 admin dashboard frontends with dynamic routing, permission-based menus, and CRUD page generation. Admin.NET Frontend: Vue 3 + Vite + TypeScript admin UI for Admin.NET backend.
project-bootstrap
A setup workflow for creating or formally onboarding a Nuxt project into a shared project-management system called Clade.