Agent Skills by Yang Fang
Showing 64 vetted skills indexed across 1 GitHub repositories.
parallel-cli
Orchestrate vendor web search, extraction, and research tasks for Hermes agents.
gitnexus-explorer
Index codebases into an interactive knowledge graph with a Node.js backend and web UI.
qmd
Search local knowledge stores with hybrid BM25, vector, and LLM reranking.
duckduckgo-search
Search DuckDuckGo for text, news, images, and videos without an API key.
scrapling
Automate web data extraction with HTTP fetching, dynamic rendering, and spider crawling.
bioinformatics
Index and fetch bioinformatics skills and pipelines from open-source libraries.
domain-intel
Collect passive domain intelligence using Python's standard library and output structured JSON.
inference-sh-cli
Orchestrate 150+ AI apps from the inference.sh CLI with JSON inputs.
sherlock
Identify and aggregate social media profiles by username across 400+ networks.
oss-forensics
Correlate evidence from GitHub, web archives, and CI/CD data to investigate supply chain security incidents.
1password
Manage application secrets via the 1Password CLI (op) with op:// paths.
fitness-nutrition
Plans gym workouts and tracks nutrition using wger and USDA FoodData Central APIs with offline calculators for BMI, TDEE, one-rep max, macro splits, and body fat.
neuroskill-bci
Stream real-time brain and biometric metrics from NeuroSkill to Hermes.
nemo-curator
Automate GPU-accelerated deduplication and quality filtering for multimodal LLM training data.
huggingface-accelerate
Automate distributed training setup across CPU, GPU, and TPU environments.
chroma
Store embeddings and metadata in an open-source vector database for semantic search.
simpo-training
Optimize LLM preferences with SimPO using chosen versus rejected responses.
slime-rl-training
Guide RL post-training of large language models with Megatron-LM and SGLang.
guidance
Constrain LLM outputs with regex patterns and grammars for structured formats.
clip
Map images and text into a shared embedding space with PyTorch.
lambda-labs-gpu-cloud
Provision on-demand GPU instances and clusters via the Lambda Cloud API.
huggingface-tokenizers
Train and run Rust-based HuggingFace tokenizers with BPE, WordPiece, and Unigram models.
peft-fine-tuning
Fine-tune large language models with LoRA and QLoRA adapters.
stable-diffusion-image-generation
Generate images from text prompts using Hugging Face Diffusers.