发现 Skills

Arize Phoenix observability platform setup for LLM debugging and evaluation

Protocol Buffers and gRPC service definition with backward compatibility checks

Internal quality audit skill with planning, execution, findings documentation, and corrective action tracking

TypeScript SDK development with Node.js and browser support. Design SDK architecture, implement type-safe API clients, support ESM and CommonJS modules, and configure bundling for browsers.

A Linux system troubleshooting workflow for diagnosing and resolving system issues, performance problems, and service failures.

Automatic payment tracking and follow-up

Backend service development expert (generalist). Proficient in multiple backend technology stacks and able to choose the most suitable technical solution based on requirements. Use this skill when the user needs API development, database design, microservice architecture, or backend business logic. Automatically switch to the corresponding language expert mode according to the user's required tech stack: - Python → see python/SKILL.md - Node.js → see nodejs/SKILL.md - Go → see go/SKILL.md - Java → see java/SKILL.md

Manually trigger the cdd-code-simplifier agent to review and simplify code

Use this skill when asked about "hooks", "PreToolUse", "PostToolUse", "SessionStart", "hook events", "validate tool use", "block commands", "add context on session start", or implementing event-driven automation.

Trace bugs backward to their origin, not just symptoms

Readiness checklist for homelab VLAN segmentation, local DNS filtering, and WireGuard-style remote access before changing router, firewall, DHCP, or VPN configuration.

Generate production-ready API endpoints from natural language descriptions. Supports Next.js App Router, tRPC, and Express. Includes authentication, validation, error handling, and best practices. Use when building REST or tRPC APIs.

Automate the initial setup of a new skill. Use when you want to create a new skill from scratch.

Guide users through App Store Connect actions that require manual browser interaction. Use when agreements, tax/banking, privacy policies, or other dashboard-only tasks need attention.

Generates comprehensive chapter outlines for books, including key topics, subtopics, learning objectives, and estimated word counts. Use this when the user needs help structuring a book chapter or creating a table of contents.

Connecting to MCP servers, tool invocation, session management. Use when the orchestrator or any agent needs to call tools on an MCP server (bridge, cowork-mcp).

Build clean, scalable UIs with Tailwind CSS using modern utilities and variants

Automated webapp explorer that crawls a local web application using Playwright BFS, mapping all screens, interactive elements, navigation flows, and user workflows into a structured JSON sitemap with per-screen screenshots. Computes UX metrics: min clicks per destination, average depth, deepest screens. Supports authenticated SPAs with session persistence and mobile viewport. Use when: analyzing webapp structure, documenting UI flows, preparing for visual analysis, mapping user workflows, auditing navigation complexity. Triggers: /app-explorer, "explore my app", "map the webapp", "analyze app structure", "crawl my frontend", "mappa la webapp", "esplora l'app".

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Strategic knowledge base for SaaS business planning and GTM strategy (2025-2026). Market sizing, audience/persona frameworks, competitive analysis, pricing models, positioning (April Dunford, Blue Ocean, Crossing the Chasm), GTM motions (PLG/SLG/hybrid), advertising benchmarks, and KPI targets. Used by the business-planner agent.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Firecrawl SDK for scraping bot-protected websites with proxy auto-escalation and structured data extraction. Use when sites have heavy bot protection (Queue-it, Akamai, Cloudflare) or when you need clean markdown/structured output from complex pages.

Analyze sleep data, identify sleep patterns, assess sleep quality, and provide personalized recommendations for sleep improvement. Supports correlation analysis with other health data.

Analyze content sequences within a section and provide neutral descriptions for AEM Edge Delivery Services. Invoked per section during page import to identify breaking points between default content and blocks.