Blender best practices and Python code snippets for the Blender MCP server. Use when creating 3D models, manipulating geometry, applying materials, or performing operations like bisecting, boolean...
Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions...
Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates
Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates
Generate database migration scripts for Liquibase, Flyway, Alembic with rollback safety, data preservation, and zero-downtime patterns
Guidelines for developing with Sequelize, a promise-based Node.js ORM supporting PostgreSQL, MySQL, MariaDB, SQLite, and SQL Server
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Advanced memory operations reference. Basic patterns (profile loading, simple recall/remember) are in project instructions. Consult this skill for background writes, memory versioning, complex...
Create safe, reversible database migration scripts with rollback capabilities, data validation, and zero-downtime deployments. Use when changing database schemas, migrating data between systems,...
Use to convert probabilities into decisions (bet/pass/hedge) and optimize scoring. Invoke when need to calculate edge, size bets optimally (Kelly Criterion), extremize aggregated forecasts, or...
Advanced memory operations reference. Basic patterns (profile loading, simple recall/remember) are in project instructions. Consult this skill for background writes, memory versioning, complex...
Use when defining stopping rules for projects, avoiding sunk cost fallacy, setting objective exit criteria, deciding whether to continue/pivot/kill initiatives, or when users mention kill...
Framework for developing, testing, and deploying trading strategies for prediction markets. Use when creating new strategies, implementing signals, or building backtesting logic.
|
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
|
Build real-time collaborative editing with WebSockets, OT/CRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative...
Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API....
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention