Results for “grounding”

Builds or debugs Google Gemini features using @google/generative-ai, covering generateContent, function calling, grounding, multimodal input, and streaming, with guidance for editing src/lib/ai/clients/google.ts.

Create and manage persistent AI agents with threads, messages, runs, and tools using the Azure AI Agents SDK for .NET.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Generates phrase-grounded bounding box annotations from image-caption pairs using a VLM, producing cleaned captions, referring expressions, and pixel-space bounding boxes.

Use this skill for context gathering, file triage, source maps, assumptions, task framing, prompt hygiene. Trigger when the task involves programming work related to Context Engineering, production implementation, audits, debugging, strategy, or validation.

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.

Run a bounded cross-platform landscape scan before planning or implementation. Use when the real job is researching what exists, how people work around it, which solutions repeat, or how platform/tooling patterns map before deciding what to build. Produce reusable `.survey/{slug}/` artifacts, validate the artifact contract, and route planning or execution outward only after the survey is done.

Design a SEEDS regenerative inquiry cycle connecting place-based learning to ecological awareness for young learners. Use when building early childhood or primary inquiry around ecosystems and community.

Generate images using Google Gemini 3.1 Flash Image Preview via the inference.sh CLI, with support for text-to-image, image editing, multi-image input, and Google Search grounding.

Evaluates text-to-image generation models by decomposing assessment into five specialized skills (object presence, count, spatial relations, scale, and text rendering) and open-ended prompts, producing interpretable binary scores with visual and textual explanations.

Run a PDCA quality audit on LLM/AI features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", "audit prompts", "check AI quality", "audit AI costs", "check traces". Jailbreak/OWASP LLM → audit-llm-security. Token caps → plan-llm-cost-guardrails.