Results for “pr”

Provides storage and environment conventions for NeMo-RL agents on Brev instances, ensuring large experiment outputs go to /ephemeral and secrets are loaded from .env.

Trains, evaluates, exports, and runs inference for NVPanoptix3D models that perform panoptic 3D scene reconstruction from posed RGB images, producing 3D panoptic segmentation with occupancy completion.

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

Analyze Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Provides summaries, breakdowns by model, session, or date, and CSV export.

Produces an evidence-backed inventory of live automations (jobs, hooks, connectors, MCP servers, wrappers) and recommends keep/merge/cut/fix-next actions before rewriting anything.

Evaluates Power BI data model architecture, relationships, storage modes, and performance to identify optimization opportunities and ensure adherence to best practices.

Creates detailed technical implementation plans for features based on a Feature PRD, including system architecture, database schema, API design, and frontend component hierarchy.

Query NFT and token data, trade NFTs on Seaport, swap ERC20 tokens via DEX aggregator, configure wallet signing providers, and build/register/gate AI agent tools on Base.

Deploys and configures CrowdStrike Falcon EDR sensors across Windows, macOS, and Linux endpoints, sets prevention and response policies, validates deployment, and integrates with SIEM platforms.

Transcribe audio with high accuracy using ElevenLabs Scribe models, supporting speaker diarization, audio event tagging, forced alignment, and subtitle generation via the inference.sh CLI.

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

Build production RAG and semantic search systems with a high-performance vector database written in Rust, supporting hybrid search, filtering, and horizontal scaling.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.

Generate a single continuous cinematic shot video with no cuts, using text or image prompts and configurable style, duration, and aspect ratio.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Generate or edit Xiaohongshu (RedNote) cover images using GPT Image 2 / Codex, with a Gemini CLI fallback, supporting 18 preset styles and custom style learning.

Loads and processes whole-slide pathology images, builds spatial graphs, trains deep learning models, and analyzes multiplexed immunofluorescence data across 160+ slide formats.

Operates AI infrastructure as a production dependency: manages GPU utilization, MCP servers, LLM gateways, inference pipelines, token costs, semantic caching, and model observability.

Manage vector database operations across Pinecone, Weaviate, Qdrant, and ChromaDB, including embedding generation, index creation, metadata filtering, hybrid search, and production deployment for RAG and similarity search.

Evaluates speaker verification models by computing true positive rate at fixed false positive rate thresholds, probing embedding space separation of same-speaker versus different-speaker pairs.

Access ATXP's paid API tools for web search, AI image generation, music creation, video generation, and X/Twitter search via CLI or programmatic client.

Search external documentation (web pages, API docs, papers) and generate useful summaries for development. Use when investigating new technologies, understanding third-party APIs, researching best practices, or gathering information for technical decisions. Reduces hallucinations and expands agent knowledge.

Task tracking for async/multi-step work. Use dex to create, track, and complete tasks that span multiple sessions or require coordination (e.g., coding agent dispatches, PR reviews, background jobs). Tasks stored as JSON files in .dex/tasks/.

This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or requests 3-5 year financial planning for a startup.

Agent profile for review Android Compose code, lifecycle, permissions, navigation, Material behavior, performance, and Play release risks. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

Professional US stock analysis with financial data, news, social sentiment, and multi-model AI. Comprehensive reports at $0.02-0.10 per analysis. Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

Turn a weak/cheap "Flash" model into a "Pro" performer by wrapping HKUDS UpSkill — captures agent session failures, has a strong Teacher model analyze them and draft a skill, then validates it against the weak Student model in a closed Ralph Loop (up to 3 rounds) before storing it for automatic reuse. Use when the user wants to install UpSkill, run `/upskill-init`, `/upskill-configure`, `/upskill-build`, `/upskill-run`, `/upskill-list`, `/upskill-status`, `/upskill-mode`, `/upskill-model`, `/upskill-remove`, or `/upskill-uninstall`, wants a cheap model to perform closer to a Pro model without switching, or wants a good session (success or failure) distilled into a validated skill. Triggers on: upskill, up-skill, flash to pro, teacher student distillation, ralph loop skill validation, distill agent failures into skills. Routes skill-quality ratcheting to `skill-autoresearch`, scaffolding to `write-a-skill`, and spec-compliance rewrites to `skill-standardization`.

Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead. Calls `runcomfy run happyhorse/happyhorse-1-0/text-to-video` through the local RunComfy CLI. Triggers on "happyhorse", "happy horse", "happyhorse 1.0", "happyhorse video", or any explicit ask to generate video with this model.

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Flux Kontext / Nano Banana 2 t2i instead. Calls `runcomfy run google/nano-banana-2/edit` through the local RunComfy CLI. Triggers on "nano banana edit", "edit with nano banana", "image edit nano banana", or any explicit ask to edit with this model.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for TAO OCRNet models for scene text recognition from cropped text-region images, supporting CTC and attention-based decoders.

Run TAO SDK jobs as Docker containers on a local or remote Docker daemon with NVIDIA GPU support, including preflight checks and credential handling.

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.

Enables AI agents to make policy-gated payments using the x402 HTTP payment protocol with per-task budgets, spending controls, and non-custodial wallets.

Injects up to 1 million tokens of external context into AI agent memory, auto-summarizes conversations with tone and intent preservation, and compresses multi-turn history into dense token sequences.