The library

flox-environments · Setting up project dependencies (Python, Node, Rust, system libs) once and sharing a lock file so all devs get identical environments.

baoyu-url-to-markdown · Saving web articles, tweets, YouTube transcripts, or HN threads as markdown when you need structured content extraction with login support.

k8s-troubleshoot · Quickly diagnosing why a pod won't start or a container keeps crashing without ssh-ing into nodes.

flutter-dart-code-review · Auditing Flutter code for state management anti-patterns and widget best practices regardless of which state library is used.

baoyu-wechat-summary · Creating weekly WeChat group digests to surface key discussion points when you have active group chats.

k8s-vind · Creating lightweight isolated Kubernetes clusters for CI/CD, testing, or multi-tenant development without spinning up full clusters.

form-cro · Reducing form friction (fewer fields, clearer CTAs) to increase lead capture when you have actual drop-off data or completion rates.

baoyu-xhs-images · user mentions "小红书图片", "小红书种草", "小绿书", "微信图文", "微信贴图", "image cards", "图片卡片", baoyu-xhs-images, or wants social media infographic series.

foundation-models-on-device · building privacy-preserving or offline AI features, extracting structured data, or streaming model output in a native iOS app.

baoyu-youtube-transcript · user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面", "视频封面", "video thumbnail", "video cover image", or provides a YouTube URL and wants the transcrip

ai-model-nodejs · Only SDK supporting image generation (ai.createImageModel + generateImage). Text models via ai.createModel with groups cloudbase, hunyuan-exp, or custom-*. Model IDs (deepseek-v4-flash, deepseek-v3.2,

fp-ts-errors · you want type-safe explicit error handling in TS APIs or services.

ai-model-web · Default routing for page/页面/Web/前端/frontend/网页/H5 AI — call directly from browser, do NOT propose a Node.js proxy. Covers generateText and streamText. Models via ai.createModel with groups cloudbase,

fp-ts-pragmatic · writing or refactoring TypeScript with fp-ts (Option/Either/TaskEither).

ai-model-wechat · Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Mod

fp-ts-react · building React apps with functional, type-safe state and fetch handling.

auth-nodejs-cloudbase · This skill should be used when Node.js code must read caller identity, inspect end users, or bridge an existing user system into CloudBase; not when configuring providers or building client login UI.

senior-devops · setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.

auth-tool-cloudbase · This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readine

frontend-a11y · building any interactive UI component or form.

auth-web-cloudbase · Provides concise and practical Web authentication solutions with multiple login methods and complete user management.

frontend-design-direction · building or improving websites, dashboards, applications, components, landing pages, visual tools, or any web UI that needs stronger product-specific design judgment.

frontend-slides · the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choic

cloud-functions · This skill should be used when users need application runtime code on CloudBase, not when they are merely calling CloudBase official platform APIs.

frontend-web-core · choosing a framework, wiring SSR-sensitive or motion code, or planning accessibility — the interlocking rules every frontend-web spoke depends on.

cloud-storage-web · Complete guide for CloudBase cloud storage using Web SDK (@cloudbase/js-sdk) - upload, download, temporary URLs, file management, and best practices.

invariant-review-skill · When using invariant-review-skill

frontend-web-orchestrator · When building a UI but the framework choice hasn't been locked in yet

cloudbase-agent · When deploying CloudBase agents and need language-specific instructions

gateguard · When agents tend to guess instead of investigating before edits

cloudbase-agent-python · When deploying Python agents that need AG-UI protocol, persistent memory, and observability

mcp-diagnoser · When MCP servers fail to connect or authenticate unexpectedly

gcp-cloud-run · When building stateless, cold-start-optimized services on Cloud Run

cloudbase-agent · When serving TypeScript agents with client-state annotation and browser/mini-program UIs

cloudbase-cli · When deploying functions, apps, storage in CI/CD pipelines or batch operations

gh-issues · When auto-fixing many issues at once with sub-agents opening PRs in parallel

cloudbase-platform · When deciding which CloudBase service (functions, storage, auth, database) to use

tool-skill · When troubleshooting command-line tool configuration and behavior

a11y-audit · When verifying WCAG 2.2 compliance on web interfaces

cloudbase-wechat-integration · When CloudBase APIs return errors or auth fails unexpectedly

chat_agent_skill · When MCP resource discovery or configuration is unclear

git-pr-ops-core · When choosing between PR, branch, merge, or CI/CD patterns

ab-test-setup · When quantifying feature impact before full rollout

cloudrun-development · When agent deployment fails and root cause is unclear

git-pr-ops-orchestrator · When the choice of bundler, runtime, or framework needs alignment

data-model-creation · When defining schemas for NoSQL or relational storage

git-workflow · When coordinating multi-developer repos with automated checks

adversarial-reviewer · Catching production-breaking bugs and maintainability issues that self-review and agreeable LLMs miss

http-api-cloudbase · Non-Node backends and integration tests calling CloudBase features (database, functions, storage) without SDKs

spectral-data-skill · Harmonizing spectral libraries across USGS, ASTER, EMIT, and ECOSTRESS for machine learning or geophysics