Total 46,631 skills
Showing 12 of 46631 skills
Maxxton integration. Manage data, records, and automate workflows. Use when the user wants to interact with Maxxton data.
LoRA, full fine-tuning, DPO preference tuning, VLM training, function-calling tuning, reasoning tuning, and BYOM uploads on Together AI. Reach for it whenever the user wants to adapt a model on custom data rather than only run inference, evaluate outputs, or host an existing model.
Use when creating git worktrees for Maven projects - prevents SNAPSHOT artifact clashes and corporate plugin resolution failures through isolated local repositories
Golioth integration. Manage data, records, and automate workflows. Use when the user wants to interact with Golioth data.
API.Bible integration. Manage data, records, and automate workflows. Use when the user wants to interact with API.Bible data.
Use when about to use jq, curl, sed, awk, or bash for JSON/XML processing, API calls, data transformation, or file processing - before writing any bash commands for data manipulation
Chatlayer integration. Manage data, records, and automate workflows. Use when the user wants to interact with Chatlayer data.
On-demand and reserved GPU clusters (H100, H200, B200) on Together AI with Kubernetes or Slurm orchestration, shared storage, credential management, and cluster scaling for ML and HPC jobs. Reach for it when the user needs multi-node compute or infrastructure control rather than a managed model endpoint.
Dope.security integration. Manage data, records, and automate workflows. Use when the user wants to interact with Dope.security data.
Blend integration. Manage data, records, and automate workflows. Use when the user wants to interact with Blend data.
Linqs integration. Manage Persons, Organizations, Deals, Leads, Activities, Notes and more. Use when the user wants to interact with Linqs data.
Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.