Loading...
Loading...
Found 3,140 Skills
Handles commit flows by detecting changes, optionally running validator validation, and completing commits for requests such as "commit with validator", "run checks before commit", "run validator then commit", or "skip validator and commit".
Quantitative strategy generation and optimisation framework via Longbridge — create, modify, and backtest quant strategies: parameter grid search, walk-forward validation, overfitting detection (in-sample vs. out-of-sample), strategy combination (multi-strategy correlation diversification), Sharpe / Calmar ratio optimisation. Generates Python code frameworks for local execution. Triggers: "策略优化", "策略生成", "参数优化", "网格搜索", "回测优化", "过拟合", "walk-forward", "策略回测优化", "策略組合", "策略優化", "策略生成", "參數優化", "網格搜索", "回測優化", "strategy optimization", "strategy generation", "parameter optimization", "grid search", "overfitting", "walk-forward validation", "strategy backtest", "Sharpe ratio", "Calmar ratio".
Build typed LLM applications with PydanticAI: schema-constrained outputs, tool integration, validation, retries, and deterministic downstream handoffs. Use when users need reliable structured outputs instead of free-form text generation.
Comprehensive Blazor development expertise covering Blazor Server, WebAssembly, and Hybrid apps. Use when building Blazor components, implementing state management, handling routing, JavaScript interop, forms and validation, authentication, or optimizing Blazor applications. Includes best practices, architecture patterns, and troubleshooting guidance.
Expert skill for prompt engineering and task routing/orchestration. Covers secure prompt construction, injection prevention, multi-step task orchestration, and LLM output validation for JARVIS AI assistant.
Design ETL workflows with data validation using tools like Pandas, Dask, or PySpark. Use when building robust data processing systems in Python.
Detect the divergence phenomenon where commodity prices rise but the holdings of corresponding physical ETFs/trusts decline, and use multi-indicator cross-validation to assess the risk of physical supply tightness/delivery pressure.
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-v INPUT: XML from screenwriter skill (scene tags with duration, action, key_visuals) OUTPUT: Enhanced XML with validation, chunks, continuity tags, and Veo 3 prompts KEY 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
Use when building AdonisJS v6 applications, implementing features in AdonisJS, or reviewing AdonisJS code. Covers routing, controllers, validation, authentication, database patterns, testing, and error handling.
Expert knowledge for Formedible - A React form library built on TanStack Form with 22+ field types, multi-page forms, analytics, and type-safe validation
Validate code changes by intelligently selecting and running the appropriate test suites. Use this when editing code to verify changes work correctly, run tests, validate functionality, or check for regressions. Automatically discovers affected test suites, selects the minimal set of venvs needed for validation, and handles test execution with Docker services as needed.
Use when writing tests for serialization, validation, normalization, or pure functions - provides property catalog, pattern detection, and library reference for property-based testing