Agent Skills Hub

nvidia-resiliency-ext

Provides resiliency, health monitoring, and fault tolerance utilities for NVIDIA GPU-accelerated distributed applications, including process management and API key handling.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

pytdc

Access AI-ready datasets, benchmarks, and molecular oracles for drug discovery, including ADME, toxicity, DTI, and molecular generation tasks.

git-ship

Automate your entire Git lifecycle from commit and PR creation to CI monitoring and branch merging, enforcing conventional commits throughout.

semgrep-rule-variant-creator

Port Semgrep rules to new languages using a strict, test-driven methodology. Includes applicability analysis, AST-based translation, and automated validation for each target language.

MLOps Industrialization

A framework to transform experimental ML prototypes into robust, production-ready Python packages using src layout, hybrid architecture, and strict configuration management.

taide-botrun

A RAG-based AI solver for high school Chinese GSAT exams, featuring structured knowledge retrieval, reasoning templates, and explainable AI outputs.

submodule-push

Pushes local changes in git submodules (hive or core-geth) to their respective remote forks, ensuring repository synchronization.

ai-multimodal

Process and generate multimedia with Google Gemini. Analyze audio, images, videos, and PDFs with high-context windows. Supports transcription, visual QA, OCR, and AI-driven image creation.

rag-engineer

Architect and optimize production-grade RAG systems. Master embedding models, vector databases, chunking strategies, and retrieval pipelines for high-accuracy LLM applications.

debug-distributed

Debugging guide for AReaL distributed training issues, including hangs, NCCL errors, OOM, and numerical consistency in FSDP2/TP/CP/EP.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.