Total 58,125 skills, AI & Machine Learning has 9659 skills
Showing 12 of 9659 skills
Route low-risk coding tasks to cheaper LLMs while keeping Codex for high-risk decisions, using MCP tools for cost-aware delegation
Sign in to OpenAnt. Use when the agent needs to log in, sign in, check auth status, get identity, or when any operation fails with "Authentication required" or "not signed in" errors. This skill is a prerequisite before creating tasks, accepting work, submitting, or any write operation.
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone with a Mask2Former-style head and 3D frustum reconstruction. Use when training, evaluating, exporting, or running inference for a TAO NVPanoptix3D model. Trigger phrases include "train NVPanoptix3D", "panoptic 3D reconstruction", "3D scene segmentation", "occupancy completion".
Reference for writing and editing excellent skills: Vocabulary and principles to make skills predictable.
assign a task to an external coding agent and monitor it. Pipes the prompt via stdin to dodge quoting failures and auto-approves permissions to avoid silent hangs. Triggers: run a task with an external agent, hand off to OpenCode, Claude Code, or similar, execute a plan non-interactively. Flags: --agent <name> (default opencode), --model <model>, and --dir <path>.
Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent (Codex or Claude).
Interprets authoritative specs and helps design a new implementation collaboratively, preserving required business, API, and database contracts while exploring architecture, stack, and delivery options with the user. Use when the user wants to start a new project from frozen specs, discuss implementation approaches, or plan an incremental rebuild without depending on the legacy codebase.
No Polling for Background Agents
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.
Session mode: act as orchestrator brain only. Research and implementation go to cheaper-model subagents; the orchestrator scopes, briefs, verifies, and judges. User-invoked with the task as the argument.
The agentmemory HTTP REST API surface, the primary protocol for talking to the memory server. Use when calling agentmemory over HTTP, when MCP is unavailable and you need a fallback, or when integrating a host that does not speak MCP.
Use this skill when a Legal or HR matter must be classified and routed to the right specialist agent, when a matter crosses both domains and needs parallel review, or when Legal and HR agents disagree and the conflict must be resolved. It defines routing rules, the overlap handoff matrix, the controlled-handoff communication principles, and the conflict-resolution protocol. It does not give legal or HR advice and never makes a final routing decision binding on a human.