數據與 AI

Answers questions about the cgl-consulting plugin including commands, agents, and methodology. Auto-activates on plugin help requests like "what commands", "how do I use", "where do I start", or "explain the methodology". Provides quick reference or spawns guide agent for complex questions.

AI video pipeline validator for Veo 3 feasibility, 8-second scene chunking, and shot continuity.USE WHEN: Validating screenplays for AI video generation, chunking scenes into 8-second segments, generating continuation prompts, scoring feasibility risk, or adding editing metadata.PIPELINE POSITION: screenwriter → **production-validator** → imagine/arch-vINPUT: XML from screenwriter skill (scene tags with duration, action, key_visuals) OUTPUT: Enhanced XML with validation, chunks, continuity tags, and Veo 3 promptsKEY FUNCTIONS: - Veo 3 feasibility validation with risk scoring (LOW/MEDIUM/HIGH/CRITICAL) - 8-second scene chunking with continuation prompts - Shot continuity tagging for editors - Technical optimization for AI-friendly alternatives

Class interfaces present one cohesive abstraction - don't mix domain logic with serialization, persistence, or unrelated concerns

Conduct comprehensive news research and generate professional newsletters. Use when user submits topics for news analysis, sentiment tracking, or competitive media coverage research.

Detect and fix memory leaks in Python and PyTorch code, especially matplotlib figures and unreleased tensors. This skill should be used during Phase 4 performance optimization when memory usage grows over time.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Biome - Fast all-in-one toolchain for web projects (linter + formatter in Rust, 100x faster than ESLint)

Use this skill after code changes are made, when reviewing implementations, checking code quality, or ensuring constitutional compliance. Apply when user mentions reviewing, analyzing, or checking code quality. Also use proactively after significant code implementations to verify they follow mini_agent framework principles.

[Extends solution-architect] GraphQL API specialist. Use for GraphQL schemas, Apollo Server/Federation, DataLoader, resolvers, subscriptions. Invoke alongside solution-architect for GraphQL API design.

Generate unit tests, integration tests, and test cases for code. Use when you see TEST comments, when asked to add test coverage, or when writing tests for new functionality.

Post-training model validation workflow: gating, backtesting, walk-forward validation, deployment decisions. Trigger after GPU training completes.

Enterprise interactive survey orchestrator with AskUserQuestion tool integration, multi-select support, conditional branching, error recovery, and production-grade decision automation across all Alfred workflows; activates for requirement clarification, architectural decisions, risky operations, feature selection, and complex multi-step user interactions

Transforms app ideas into shippable MVPs using Next.js + Supabase. Enforces ship-fast philosophy, prevents feature creep, generates PRDs and Claude Code starter prompts. Maximum 1-week builds focused on core user loop only.

Configure data tables in drizzle-cube dashboards for displaying detailed records with sorting. Use when creating data tables, sortable lists, detailed views, or tabular data displays.

AI-powered GitHub issue automation

Local speech-to-text with the Whisper CLI (no API key).

Comprehensive guide for building Computer Use Agents with the CUA framework. This skill should be used when automating desktop applications, building vision-based agents, controlling virtual machines (Linux/Windows/macOS), or integrating computer-use models from Anthropic, OpenAI, or other providers. Covers Computer SDK (click, type, scroll, screenshot), Agent SDK (model configuration, composition), supported models, provider setup, and MCP integration.

MCP (Model Context Protocol) server evaluation guide for creating comprehensive test suites with read-only, independent questions. Use when building MCP servers, creating evaluation frameworks, or testing LLM tool usage patterns.

Implement autonomous KB query functionality with SQL and ChromaDB tools for financial data analysis

Generate detailed explanations of code, algorithms, patterns, and architecture. Use when you see EXPLAIN comments, when asked to document code, or when explaining how something works.