Agent Skills by avoi-ceo
Showing 123 vetted skills indexed across 1 GitHub repositories.
parallel-cli
Execute vendor-backed web search and extraction workflows with JSON outputs.
gitnexus-explorer
Index codebases into a navigable knowledge graph with GitNexus and a web UI.
qmd
Search local knowledge bases with hybrid BM25, vector, and LLM reranking.
drug-discovery
Identify ChEMBL targets and extract active compounds with ADMET and drug-likeness checks.
duckduckgo-search
Search DuckDuckGo for text, news, images, and videos via CLI.
scrapling
Automates web scraping with HTTP fetching, stealth browser automation, and spider crawling.
domain-intel
Performs domain intelligence gathering using Python standard library and outputs structured JSON.
docker-management
Automate Docker container, image, volume, network, and Compose lifecycle management.
inference-sh-cli
Run 150+ AI apps from a single CLI with JSON outputs.
sherlock
Identify and aggregate social media accounts by username across 400+ platforms.
oss-forensics
Consolidates forensic evidence from git history, GitHub API, Wayback Machine, and BigQuery GH Archive.
1password
Manage secrets with the 1Password CLI for reading and injecting credentials.
fitness-nutrition
Plan workouts and nutrition using wger and USDA data with Python calculators.
neuroskill-bci
Integrate real-time brain and body metrics from NeuroSkill into AI responses.
nemo-curator
Deduplicate and filter large multimodal datasets for LLM training.
huggingface-accelerate
Automate distributed PyTorch training setup across GPUs and devices.
chroma
Store embeddings and metadata for fast semantic search in AI applications.
simpo-training
Train language models with reference-free SimPO preference optimization.
slime-rl-training
Automates scalable RL post-training for LLMs with Megatron-LM and SGLang.
guidance
Constrain LLM outputs with regex and grammars for structured JSON/XML generation.
lambda-labs-gpu-cloud
Launch and manage on-demand Lambda Labs GPU cloud resources for ML workloads.
huggingface-tokenizers
Train and load Rust-based HuggingFace Tokenizers for batched encoding with offsets and padding.
pinecone
Launch serverless vector search with hybrid dense and sparse matching.
tensorrt-llm
Optimize LLM inference on NVIDIA GPUs with TensorRT.