发现 Skills

Authoritative rules and patterns for production-quality Kotlin Coroutines on Android. Covers structured concurrency, lifecycle integration, and reactive streams.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

End-to-end verification and self-evidence for a delivery in any repository, with or without a preconfigured verify plan. Discover an existing plan when one was handed to this run; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), drive the real product, capture visually confirmed evidence, and publish a round with the lh CLI. Triggers on 'verify the task', 'collect evidence', 'prove it works', 'upload evidence', 'verify plan', 'requiredEvidence', 'local test', 'manual test', 'test report', 'test with cli', 'test in electron', 'test desktop', or any local end-to-end verification task. Needs no ambient ids, and never depends on running inside a LobeHub conversation.

Automated CI/CD pipeline setup with GitHub Actions, deployment strategies, and automation workflows. Use for build automation, testing, and deployment.

GraphQL schema design, resolvers, and client integration. Use for building GraphQL APIs and front-end queries.

Use when the design phase is complete and needs to be handed off to the development team. The development handoff summary is generated automatically, consolidating page lists, route structure, functional requirements, and items pending confirmation to produce a developer-facing handoff document. Keywords: design handoff, design delivery, handoff, developer onboarding, delivery documentation.

Generates structured experimental designs (factorial, response surface, Taguchi) to systematically discover how multiple factors affect outcomes while minimizing experimental runs. Use when optimizing multi-factor systems with limited experimental budget, screening many variables to find the vital few, discovering interactions between parameters, mapping response surfaces for peak performance, validating robustness to noise factors, or when users mention factorial designs, A/B/n testing, parameter tuning, or process optimization.

Polymarket sports prediction markets — live odds, prices, order books, events, series, and market search. No auth required. Covers NFL, NBA, MLB, soccer, tennis, cricket, MMA, esports. Supports moneyline, spreads, totals, and player props. Use when: user asks about sports betting odds, prediction markets, win probabilities, market sentiment, or "who is favored to win" questions. Don't use when: user asks about actual match results, scores, or statistics — use football-data or fastf1 instead. Don't use for historical match data. Don't use for news — use sports-news instead. Don't confuse with Kalshi — Polymarket focuses on crypto-native prediction markets with deeper sports coverage; Kalshi is a US-regulated exchange with different market structure.

Generate structured landing page copy OR audit existing pages for conversion optimization. Framework-agnostic - adapts approach based on awareness level and offer type.

Complete guide for Apache Spark data processing including RDDs, DataFrames, Spark SQL, streaming, MLlib, and production deployment

Expert data analysis and manipulation for customer support operations using pandas

Comprehensive Pydantic data validation skill for customer support tech enablement - covering BaseModel, Field validation, custom validators, FastAPI integration, BaseSettings, serialization, and Pydantic V2 features

UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.

Guide for saving a web page for offline use using the monolith CLI. Use this when instructed to save a web page.

Godot game engine automation and documentation

Implementing UI/UX features in sidecar including modals (internal/modal library), keyboard shortcuts, mouse support, scrolling, pill/tab rendering, and pane resizing. Use when implementing UI features, handling user input, adding keyboard shortcuts, building modals, or working on UX improvements.

Materialize documentation for SQL syntax, data ingestion, concepts, and best practices. Use when users ask about Materialize queries, sources, sinks, views, or clusters.

Resolve common penetration testing issues in Ark. Use when fixing security vulnerabilities from pentest reports, security audits, or OWASP Top 10 issues.

LinkedIn Ads deep analysis for B2B advertising. Evaluates 25 checks across technical setup, audience targeting, creative quality, lead gen forms, and bidding strategy. Includes Thought Leader Ads, ABM, and predictive audiences. Use when user says "LinkedIn Ads", "B2B ads", "sponsored content", "lead gen forms", "InMail", or "LinkedIn campaign".

Builds AI-native products using OpenAI's development philosophy and modern AI UX patterns. Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences. Based on Kevin Weil (OpenAI CPO) on building for future models, hybrid approaches, and cost optimization.

Structures presentations and verbal pitches using Matt Abrahams' WHAT-SO WHAT-NOW WHAT framework and impromptu speaking techniques. Use when preparing presentations, creating talking points, or practicing difficult conversations.

Builds feedback collection systems using Superhuman's PMF framework and YC's "talk to users" methodology. Use when implementing NPS surveys, scheduling user interviews, or measuring product-market fit.

Claude Code CLI orchestrator: dispatch Anthropic's Claude Code from external AI assistants for code, review, deep reasoning.

Chrome DevTools orchestrator: routes between bdg CLI (fast, token-efficient) and Code Mode MCP (multi-tool integration).