thisismynewfmail-ui
Community@thisismynewfmail-ui
Agent Skills by thisismynewfmail-ui
Showing 122 vetted skills indexed across 1 GitHub repositories.
parallel-cli
Run parallel web search and extraction workflows with JSON output.
gitnexus-explorer
Index a codebase into a knowledge graph and serve an interactive UI.
qmd
Search local markdown notes and transcripts with hybrid retrieval.
duckduckgo-search
Search DuckDuckGo for text, news, image, and video results with titles, URLs, and snippets.
scrapling
Extract data from static and JavaScript-rendered web pages via scrapling.
bioinformatics
Fetch curated bioinformatics skills and pipelines for genomics workflows.
domain-intel
Identify subdomains, SSL certificates, WHOIS data, DNS records, and domain availability.
docker-management
Manage Docker containers, images, volumes, networks, and Compose stacks via CLI.
inference-sh-cli
Run AI media generation apps through the inference.sh CLI.
sherlock
Search 400+ social networks for a username and list found profiles.
oss-forensics
Coordinate multi-source OSS forensics investigations to document supply-chain risks in GitHub repositories.
1password
Inject encrypted 1Password secrets into shells and applications via the op CLI.
neuroskill-bci
Stream real-time brain and biometrics data from NeuroSkill into Hermes conversations.
nemo-curator
Curate multimodal datasets with quality filtering, deduplication, and PII redaction.
huggingface-accelerate
Scale PyTorch training across DDP, DeepSpeed, FSDP, and Megatron backends.
chroma
Store and query vector embeddings with metadata filtering for semantic retrieval.
simpo-training
Optimize LLMs on paired preference datasets without a reference model.
slime-rl-training
Coordinate RL-based post-training for LLMs using slime's Megatron-LM and SGLang integration.
lambda-labs-gpu-cloud
Provision on-demand GPU cloud instances for machine learning training and inference.
huggingface-tokenizers
Train BPE, WordPiece, and Unigram tokenizers with alignment tracking for transformers.
pinecone
Create, upsert, and query Pinecone indexes for similarity search.
tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT-LLM on A100/H100 GPUs.
qdrant-vector-search
Perform low-latency vector similarity search with metadata filtering for RAG systems.
faiss
Enable fast, scalable vector similarity search and clustering on billion-scale embeddings.