Agent Skills by eddielueng
Showing 128 vetted skills indexed across 1 GitHub repositories.
eddieluengparallel-cli
Run Parallel CLI web research workflows with JSON output and async jobs.
eddieluenggitnexus-explorer
Index a source code repository into a navigable knowledge graph with an interactive web UI.
eddieluengqmd
Search local markdown and text collections with hybrid retrieval and reranking.
eddieluengdrug-discovery
Search ChEMBL for targets and bioactivities, estimate drug-likeness via PubChem, and check safety signals via OpenFDA.
eddieluengduckduckgo-search
Retrieve free web search results for text, news, images, and videos via DuckDuckGo.
eddieluengbioinformatics
Fetch domain-specific bioinformatics reference guidance and runnable pipelines from indexed skill libraries.
eddieluengdomain-intel
Collect subdomains, DNS records, TLS metadata, and WHOIS signals for a domain.
eddieluengdocker-management
Manages Docker containers, images, volumes, networks, and Compose stacks via CLI.
eddieluenginference-sh-cli
Discover and run inference.sh apps from a terminal CLI with JSON output.
eddieluengsherlock
Search 400+ social networks for accounts matching a target username.
eddieluengoss-forensics
Investigate GitHub repositories for supply chain compromise using multi-source evidence and IOC extraction.
eddielueng1password
Retrieve and inject application secrets from 1Password using the op CLI.
eddieluengfitness-nutrition
Integrates nutrition and exercise-management toolsUTE for meal planning and workout tracking.
eddieluengneuroskill-bci
Connect Hermes to a NeuroSkill BCI instance and translate cognitive metrics into guidance.
eddieluengnemo-curator
Filter, deduplicate, and redact large-scale multimodal datasets with GPU acceleration.
eddieluenghuggingface-accelerate
Abstract multi-GPU orchestration, mixed precision, and sharding for PyTorch training scripts.
eddieluengchroma
Indexes document vectors with metadata for semantic similarity search and retrieval.
eddieluengsimpo-training
Train LLMs with reference-free SimPO using chosen versus rejected preference pairs.
eddieluengslime-rl-training
Run GRPO RL post-training for LLMs with Megatron-LM and SGLang rollouts.
eddieluengguidance
Enforce regex and grammar constraints for valid JSON, XML, and code outputs.
eddieluengclip
Compute image and text embeddings for zero-shot classification and retrieval.
eddieluenglambda-labs-gpu-cloud
Provision reserved Lambda Labs GPU instances with persistent filesystems and SSH access.
eddieluenghuggingface-tokenizers
Train and apply BPE, WordPiece, and Unigram tokenizers with offset mapping.
eddieluengpeft-fine-tuning
Train low-rank LoRA/QLoRA adapters for parameter-efficient fine-tuning of large language models.