agent-browser
Source:SkillHub
v1.0.0
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
autobrowse
Source:Browserbase
v0.0.0
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.
browser
Source:Browserbase
v0.0.0
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with automatic CAPTCHA solving, anti-bot stealth mode, and residential proxies — ideal for scraping protected websites, bypassing bot detection, and interacting with JavaScript-heavy pages.
browser-trace
Source:Browserbase
v0.0.0
Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.
browserbase-cli
Source:Browserbase
v0.0.0
Use the Browserbase CLI (`bb`) for Browserbase Functions and platform API workflows. Use when the user asks to run `bb`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use `bb browse` only when the user explicitly wants the Browserbase CLI path.
company-research
Source:Browserbase
v1.1.0
Company discovery and deep research skill. Researches a company's product and ICP,
discovers target companies to sell to using Browserbase Search API, deeply researches
each using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into
a scored research report and CSV. Supports depth modes (quick/deep/deeper) for
balancing scale vs intelligence.
Use when the user wants to: (1) find companies to sell to, (2) research potential
customers, (3) discover companies matching an ICP, (4) build a target company list,
(5) do market research on prospects. Triggers: "find companies to sell to",
"company research", "find prospects", "ICP research", "target companies",
"who should we sell to", "market research", "lead research", "prospect list".
cookie-sync
Source:Browserbase
v0.0.0
Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.
event-prospecting
Source:Browserbase
v0.1.0
Event prospecting skill. Takes a conference / event speakers URL,
extracts the people, filters their companies against the user's
ICP, then deep-researches only the speakers at ICP-fit companies.
Outputs a person-first HTML report where each card answers "why
should the AE talk to this person?" with all public links and a
one-click DM opener.
Use when the user wants to: (1) find leads at a specific
conference, (2) prep for an event, (3) research event speakers,
(4) build a target list from a sponsor/exhibitor page,
(5) scrape conference speakers and rank by ICP fit.
Triggers: "find leads at {event}", "research speakers at",
"prospect this conference", "stripe sessions leads",
"ai engineer summit prospects", "event prospecting",
"scrape conference speakers", "who should I meet at".
fetch
Source:Browserbase
v0.0.0
Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.
frontend-design
Source:SkillHub
v1.0.0
Create distinctive, production-grade frontend interfaces and visually strong landing pages with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, applications, landing pages, prototypes, demos, or game UIs (examples include websites, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics, enforces restrained composition, image-led hierarchy, cohesive content structure, and tasteful motion.
functions
Source:Browserbase
v0.0.0
Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions.
http-e2e-testing
Source:SkillHub
v1.0.0
Implement end-to-end testing for web applications using HTTP requests. Use when the task requires API endpoint testing, request/response validation, or integration testing. Triggers: API testing, endpoint validation, HTTP test, integration test, e2e test.
playwright
Source:SkillHub
v1.0.0
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
playwright-interactive
Source:SkillHub
v1.0.0
Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
pnpm-catalogs
Source:SkillHub
Project:citado
v1.0.0
Configure and maintain named pnpm catalogs in pnpm-workspace.yaml for this Citado monorepo. Use whenever the task involves centralizing shared dependency versions, moving package.json entries to catalog:<name>, reviewing or extending the catalogs taxonomy, or aligning versions across frontend/viewer packages. Also use for prompts like “整理 catalogs”, “统一依赖版本”, “把依赖收进 pnpm-workspace.yaml”, or “按 frontend/lint/test/build 分类依赖”.
product-design
Source:SkillHub
v1.0.0
Transform natural language feature requirements into standardized YAML definitions. Use when formalizing user stories, creating feature YAML files, modeling product features, or reviewing feature definitions. Triggers: feature design, product spec, requirement modeling, YAML definition.
project-lint
Source:SkillHub
Project:citado
v1.1.0
Runs the real package-local verification commands needed to ensure agent changes are type-safe, buildable, and lint-clean where those checks are actually defined.
project-lint-creator
Source:SkillHub
v1.0.0
Generate a project-specific lint skill (project-lint) for any codebase. Use when setting up automated code quality gates, creating lint/type-check/build verification workflows, or when the user wants to create a project-lint skill for their repository. Triggers: create project-lint, setup lint checks, add code quality gates, generate lint skill, project verification.
reference-ui-debugging
Source:SkillHub
Project:citado
v1.0.0
Use when the user provides one or more reference webpage URLs and wants the frontend to match their layout, spacing, motion, drag-and-drop, hover, pointer feel, or other interaction details. ALWAYS use this skill for reference-driven frontend work such as "参考这个网站实现", "对齐 Google Drive 的交互", "效果不符合预期", "请按这个网页调样式/行为", or whenever a URL is given as the visual or interaction target. This skill requires using
safe-browser
Source:Browserbase
v0.0.0
Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.
search
Source:Browserbase
v0.0.0
Use this skill when the user wants to search the web without a full browser session: find URLs, titles, and metadata for a query. Prefer it over a browser when you just need search results, not page content. Returns structured results with titles, URLs, authors, and dates.
shadcn
Source:SkillHub
v1.0.0
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
shadcn
Source:shadcn-ui
v0.0.0
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
skill-creator
Source:SkillHub
v1.0.0
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
skillctl-operator-guide
Source:SkillHub
Project:skillctl
v1.2.0
Use this skill when an agent needs to understand and operate skillctl capabilities end-to-end (discover, install, version, update, publish, and audit).
skillhub-workflow
Source:SkillHub
v1.0.0
Use this skill whenever the user is working in the SkillHub repository and needs help with end-to-end workflow execution, including creating or updating skills, maintaining sources.json, syncing remote skills, updating registry outputs, preparing merge requests, debugging GitLab CI behavior, and handling release/deploy checks. Trigger this skill for requests like "add a new skill", "update sources", "fix registry build", "why CI failed", "prepare MR", "schedule pipeline", or any request involving SkillHub repo operations and governance.
think-notes
Source:SkillHub
Project:citado
v1.0.0
Records deviations between agent output and user expectations into docs/skills/think.md. ALWAYS trigger this skill when: a user raises a second-round correction, points out a bug or ambiguity that was missed in the previous agent turn, disagrees with an implementation decision, or explicitly says something like "you missed X", "this is wrong", "you didn't handle Y", "I already said Z". The goal is to capture the gap so it can later be refined into a reusable skill or rule — not just silently fix it in one conversation and forget it. Do not skip this skill just because the fix itself is trivial; the value is in the recorded pattern, not the fix.
ui-design-ref
Source:SkillHub
Project:citado
v1.0.0
前端 UI 设计规范参考与决策辅助。当 agent 需要为 Citado 实现或审查 UI 组件时，使用本 skill 核对 token 选择、状态定义、对比度与语义色规则。适用场景包括：新增交互组件、调整颜色/状态样式、选择 Tailwind 工具类、审查 hover/active/selected 实现是否合规。ALWAYS use this skill when implementing or reviewing UI components in packages/fe.
ui-test
Source:Browserbase
v0.4.0
AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness, accessibility, responsive layout, and UX heuristics. Use when the user asks to test UI changes, QA a pull request, audit accessibility, or run exploratory testing. Supports local browser (localhost) and remote Browserbase (deployed sites).
unused-package-deps
Source:SkillHub
Project:citado
v1.0.0
Check whether dependencies declared in package.json are actually used in this Citado monorepo. Use whenever the task is to audit unused dependencies, clean up package manifests, decide whether a package belongs in dependencies or devDependencies, confirm Knip results, or explain why a dependency should stay, move, or be removed. Also use for prompts like “检查未使用依赖”, “哪些依赖可以删”, “package.json 里有没有没用到的包”, or “为什么 Knip 报这个依赖没用”.
viewer-review
Source:SkillHub
Project:citado
v1.0.0
Review or implement Citado viewer host/runtime changes. Use when a task touches packages/fe viewer code, viewer-core, viewer-pdf, or viewer-image, especially overlays, panels, drag interactions, external stores, or render-engine lifecycles.
webapp-testing
Source:SkillHub
v1.0.0
Browser-based testing and debugging toolkit for web applications using Playwright. Use when verifying frontend behavior, capturing screenshots, inspecting browser logs, or debugging UI issues in local or deployed web apps. Triggers: web app test, UI test, screenshot capture, browser debugging, frontend verification.
what-antibot
Source:Browserbase
v0.0.0
Detect antibot vendors on one or more URLs without opening a browser session. Use when the user asks what antibot, bot protection, WAF, captcha, or challenge provider a site uses, or asks to check sites for Cloudflare, Akamai, DataDome, PerimeterX, Imperva/Incapsula, Kasada, reCAPTCHA, hCaptcha, Anubis, or Shape Security markers.
yjs-crdt
Source:SkillHub
Project:citado
v1.0.0
Domain-enhanced guidance for building collaborative features with Yjs CRDT, including architecture patterns, provider choices, and operational troubleshooting.
ylapp-local-bootstrap
Source:SkillHub
v1.1.0
Use for: 新电脑拉取 ylapp 后一键完成本地部署与启动。Triggers: 本地部署, 本地启动, 新电脑环境初始化, 启动 ylapp, local bootstrap, run ylapp locally.