Agent Skills by Khyro
Showing 116 vetted skills indexed across 1 GitHub repositories.
JKhyroparallel-cli
Run Parallel CLI web search, extraction, research, and monitoring tasks with JSON output.
JKhyroqmd
Search local knowledge bases with hybrid keyword, vector, and reranked retrieval.
JKhyroduckduckgo-search
Search DuckDuckGo for text, news, images, and videos without an API key.
JKhyroscrapling
Extract web page content from static, dynamic, and protected sites.
JKhyrobioinformatics
Index bioinformatics reference skills for genomics and transcriptomics tasks.
JKhyrodomain-intel
Map passive domain intelligence via subdomain, SSL, WHOIS, and DNS lookups.
JKhyrodocker-management
Manage Docker containers, images, volumes, networks, and Compose stacks.
JKhyroinference-sh-cli
Manage inference.sh CLI app discovery and execution workflows.
JKhyrosherlock
Search a username across 400+ social networks for matching accounts.
JKhyrooss-forensics
Reconstruct GitHub repository compromise timelines from git, API, and archive sources.
JKhyro1password
Configure 1Password CLI for secure secret retrieval and injection.
JKhyroneuroskill-bci
Incorporate real-time NeuroSkill biometrics into assistant responses for cognitive state awareness.
JKhyronemo-curator
Filter, deduplicate, and redact multimodal training datasets with GPU acceleration.
JKhyrohuggingface-accelerate
Scale PyTorch training with a unified distributed API for multi-GPU and mixed-precision workflows.
JKhyrochroma
Create Chroma vector collections for document retrieval and semantic search with embeddings and metadata filtering.
JKhyrosimpo-training
Optimize language model preference alignment with SimPO training.
JKhyroslime-rl-training
Configure RL post-training workflows for large language models with slime.
JKhyrolambda-labs-gpu-cloud
Provision and manage Lambda Labs GPU instances for ML training.
JKhyrohuggingface-tokenizers
Train and deploy BPE, WordPiece, and Unigram Hugging Face tokenizers.
JKhyropinecone
Manage production vector search infrastructure with Pinecone indexes and hybrid queries.
JKhyrotensorrt-llm
Optimize LLM inference and serving on NVIDIA GPUs with TensorRT-LLM.
JKhyroqdrant-vector-search
Designs and operates Qdrant-backed vector search collections for semantic retrieval.
JKhyrofaiss
Build fast similarity search over dense vector embeddings with Faiss indices.
JKhyropytorch-lightning
Train PyTorch models with Lightning Trainer and LightningModule workflows.