Agent Skills Hub

skill-authoring-workflow

A standardized workflow for converting raw PM notes, workshops, or rough drafts into polished, validated, and repository-compliant AI skills.

ReasoningBank Intelligence

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement in AI agents.

rust

Implement robust Rust backend services using Axum, SQLx, and thiserror with production-grade patterns.

backend-rag-implementation

Build RAG systems to ground LLMs in proprietary data. Includes vector database integration, embedding strategies, hybrid search, and advanced retrieval patterns for FastAPI backends.

executing-plans

Execute implementation plans in separate sessions with review checkpoints, ensuring task-by-task verification and robust code quality.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

web-shader-extractor

Extract, deobfuscate, and port WebGL/Canvas/Shader visual effects from websites into standalone, native JavaScript projects.

debug-cuda-crash

Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.

paper-writing

Full-stack automated paper writing pipeline from research narrative to polished LaTeX/PDF.

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.

pix

An autonomous UI implementation agent that converts Figma designs into pixel-perfect code using Figma MCP and browser-based refinement.