Total 50,537 skills, AI & Machine Learning has 8483 skills
Showing 12 of 8483 skills
Two-layer autonomous conductor — design loop produces decision packets, dispatch loop routes to bounded issues with dedupe/cooldown/archive controls. Replaces v1's single-agent persistence with a durable control loop that stops only at real blockers.
Ground responses in paper excerpts with citations. Use when user wants cited claims, quotes, or needs to avoid hallucination about paper content.
When the user wants to build or improve a sales bot's ability to monitor sentiment over time. Also use when the user mentions "sentiment trends," "tone tracking," "campaign sentiment," "aggregate sentiment," or "sentiment monitoring."
When the user wants to build or improve a sales bot's ability to enrich prospect data from multiple sources. Also use when the user mentions "prospect research," "data enrichment," "lead enrichment," "prospect intelligence," or "contact enrichment."
When the user wants to build or improve a sales bot's ability to recognize over-contacted prospects. Also use when the user mentions "prospect fatigue," "over-contact detection," "outreach fatigue," "contact frequency," or "backing off."
Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap
Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.
Use when a Luma / 拾光 / 拾光智能体 / 拾光工具 agent needs content research, topic discovery, keyword tables, persona-based search, or Excel-friendly research outputs for short-video planning.
ELFA AI — real-time crypto social intelligence and automated condition-engine skills for AI agents. Track trending tokens, surface narratives, search mentions, run market analysis, and build automated trigger-based workflows.
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TAO OneFormer model. Trigger phrases include "train OneFormer", "universal segmentation", "task-conditioned segmentation", "panoptic / instance / semantic in one model".
RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO RT-DETR model. Trigger phrases include "train RT-DETR", "real-time DETR", "low-latency object detection", "RT-DETR distillation / quantization".