Agent Skills by founderphantom
Showing 118 vetted skills indexed across 1 GitHub repositories.
founderphantomparallel-cli
Orchestrate Parallel CLI workflows for web search and JSON output.
founderphantomqmd
Index text-based files locally for hybrid keyword and semantic search.
founderphantomduckduckgo-search
Search the web via DuckDuckGo without an API key.
founderphantomscrapling
Automate web scraping with HTTP, JS rendering, and stealth fetching.
founderphantombioinformatics
Index and fetch bioinformatics skills and pipelines from bioSkills and ClawBio.
founderphantomdomain-intel
Gather passive domain intelligence using Python's standard library.
founderphantomdocker-management
Manage Docker container, image, and network lifecycles via CLI and Compose.
founderphantominference-sh-cli
Orchestrate 150+ AI apps through a unified CLI interface.
founderphantomsherlock
Search social media accounts by username across 400+ networks.
founderphantomoss-forensics
Correlate git history, GitHub API, archive data, and IOC enrichment to document supply-chain compromise evidence.
founderphantom1password
Manage secrets with the 1Password CLI in Hermes Agent workflows.
founderphantomneuroskill-bci
Integrate real-time NeuroSkill brain and body metrics into Hermes responses.
founderphantomnemo-curator
Automates GPU-accelerated cleaning and deduplication of multimodal LLM training data with fuzzy/semantic dedup, PII redaction, NSFW detection via Nemo Curator and optional RAPIDS stack.
founderphantomhuggingface-accelerate
Automates distributed PyTorch training across DDP, DeepSpeed, FSDP, and Megatron-LM with unified commands and automatic device placement.
founderphantomchroma
Store embeddings and metadata in a local vector database with filtering.
founderphantomsimpo-training
Optimize language-model preferences without a reference model.
founderphantomslime-rl-training
Orchestrate end-to-end reinforcement learning post-training for large language models with slime.
founderphantomlambda-labs-gpu-cloud
Provision Lambda Labs GPU clusters and deploy ML workloads.
founderphantomhuggingface-tokenizers
Train BPE, WordPiece, and Unigram tokenizers with HuggingFace Transformers integration.
founderphantompinecone
Index and retrieve high-dimensional embeddings with low latency using Pinecone.
founderphantomtensorrt-llm
Optimize LLM inference on NVIDIA GPUs with TensorRT and FP8/INT4 quantization.
founderphantomqdrant-vector-search
Enable vector similarity search with Qdrant for RAG and semantic retrieval.
founderphantomfaiss
Index and search large dense vector collections with Flat, IVF, and HNSW.
founderphantompytorch-lightning
Transform raw PyTorch code into structured training pipelines with PyTorch Lightning.