Nico
Community@objval · Chile
CS student · Full-stack dev
Agent Skills by Nico
Showing 115 vetted skills indexed across 1 GitHub repositories.
objvalparallel-cli
Orchestrate web search, extraction, and enrichment workflows via the Parallel CLI with JSON output.
objvalqmd
Index local notes, docs, and transcripts for hybrid BM25 and vector search.
objvalduckduckgo-search
Search the web via DuckDuckGo CLI or Python package without API keys.
objvalscrapling
Bypass anti-bot protections and crawl multi-page sites via CLI and Python.
objvalbioinformatics
Index and retrieve bioinformatics skills from bioSkills and ClawBio libraries.
objvaldomain-intel
Enumerate subdomains, inspect TLS certificates, query WHOIS, and resolve DNS records using Python stdlib.
objvaldocker-management
Manage Docker containers, images, volumes, networks, and Compose stacks via CLI.
objvalinference-sh-cli
Orchestrate 150+ AI apps via the inference.sh CLI with JSON outputs.
objvalsherlock
Search for social media accounts by username across 400+ networks.
objvaloss-forensics
Investigate GitHub repositories for supply-chain compromises across a 7-phase workflow.
objval1password
Manage secrets with the 1Password CLI across Hermes workflows.
objvalneuroskill-bci
Integrate real-time NeuroSkill brain and biometrics data into Hermes via CLI and WebSocket/HTTP APIs.
objvalnemo-curator
Automate GPU-accelerated curation of multimodal LLM training datasets.
objvalhuggingface-accelerate
Automates distributed training orchestration for PyTorch models using HuggingFace Accelerate.
objvalchroma
Store embeddings with metadata for similarity search and retrieval.
objvalsimpo-training
Align language models using reference-free preference optimization with YAML configs.
objvalslime-rl-training
Automate RL post-training for LLMs using slime with Megatron and SGLang.
objvallambda-labs-gpu-cloud
Provision on-demand Lambda Labs GPU instances for ML training and inference.
objvalhuggingface-tokenizers
Tokenize text with Rust-backed tokenizers for NLP pipelines.
objvalpinecone
Manage and scale vector embeddings with a fully managed serverless vector database.
objvaltensorrt-llm
Optimize LLM inference on NVIDIA GPUs with TensorRT-LLM.
objvalqdrant-vector-search
Deploy a Rust-powered vector search backend with REST and gRPC APIs.
objvalfaiss
Perform scalable vector similarity search with FAISS index types and CPU/GPU execution.
objvalpytorch-lightning
Train PyTorch Lightning models across GPUs and TPUs with distributed strategies.