Results for “proto-loader”

Load 3D models, textures, and HDR environments in Three.js with GLTF, OBJ, FBX, STL, PLY, and Draco/KTX2 compression support.

Imported skill loading from langchain

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Land and deploy workflow. Merges the PR, waits for CI and deploy, verifies production health via canary checks. Takes over after /ship creates the PR. Use when: "merge", "land", "deploy", "merge and verify", "land it", "ship it to production". (gstack)

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Provides guidance on enabling and optimizing GKE Cluster Autoscaler, including Node Auto Provisioning, troubleshooting scale-up/down issues, and best practices for capacity management.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Pull and verify the official Holoscan SDK container from NGC, selecting the correct CUDA/arch tag for the host GPU and validating with bundled Python and C++ examples.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Implement and debug network requests, API calls, and data fetching in Expo apps using fetch, React Query, SWR, and Expo Router loaders.

Sets up Microsoft Testing Platform hot reload to iterate fixes on failing tests without rebuilding, covering package installation, environment configuration, and the iterative workflow.

Selects Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes based on Orin SM 8.7 vs Thor SM 11.0 and JetPack version.

Scaffolds a Spring Boot Kotlin project with Gradle, WebFlux, R2DBC, Redis, MongoDB, and Testcontainers, including Docker Compose setup.

Preview and verify imported content in a local AEM Edge Delivery Services development server, validating rendering and comparing with the original page.

Imported skill load from langchain

Create polished HTML technical reports and multi-page documents for consulting deliverables. Includes a customizable design system with dark cover page, warm cream content pages (8.5x11 portrait), professional typography, and a curated component library (KPI cards, data tables with severity coloring, callout boxes, recommendation cards, priority banners). Trigger on report, audit report, technical document, written report, assessment, or multi-page document. Outputs standalone HTML files exported to PDF via Chrome headless.

Author or debug Kubernetes manifests with distinct probes, right-sized resources, autoscaling, and safe reversible rollouts.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

PR Fleet

Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.

Create polished HTML slide decks and PDF-ready documents for consulting deliverables. Uses the RRBC design system with warm light mode, dark mode cover pages, Lora/Inter/Roboto Mono typography, and data visualization palette. Trigger on 'deck', 'slides', 'presentation', 'pitch deck', 'keynote', 'report', or 'PDF'.

Build creative browser demos with DOM-free text layout.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Prepare the demo video for a freelance bid — captures a clean screenshot of the gig's published n8n workflow via Claude in Chrome, builds a shot-by-shot recording script pairing the VSL narration with on-screen actions, and hands the founder tool-agnostic recording instructions (Loom/Tella/any recorder). The Demo phase of the Inbound Gig Engine. The founder records the video themselves.

Deploy applications to Heroku with safe, read-only inspection first. Use when the agent needs to assess Heroku readiness, choose between Heroku Git and container deployment, create or target an app, wire a Heroku remote, or perform a controlled Heroku deployment.

Guides building Expo Router navigation with file-based routing, layouts, tabs, protected routes, and deep linking.

Detects the project stack and generates production-ready multi-stage Dockerfiles with compose services, .dockerignore, non-root users, health checks, layer caching, and optional dev hot-reload profiles.

Generates and runs load tests for API endpoints using k6, Locust, or Artillery. Detects the API framework, creates realistic user behavior flows, executes ramp-up, sustained, spike, and stress profiles, and produces a bottleneck analysis with optimization recommendations.

Prepare safe production launches — pre-launch checklist, monitoring, staged rollout, and rollback. Load when deploying to production, releasing a major change, opening beta access, or the user asks for a launch checklist, go-live plan, rollout strategy, or rollback plan. Not for local-only prototypes. Pairs with ci-cd-and-automation and app-security-hardening.

Designs and executes load tests, covering scenario design, baseline capture, execution configuration, results analysis, and reporting for k6, Locust, Gatling, and JMeter.

Imports external plan files into a GSD-structured project, detecting conflicts against existing roadmap, requirements, and locked decisions before writing a validated PLAN.md.

Builds a throwaway prototype to answer a design question, choosing between a runnable terminal app for logic/state questions or multiple UI variations switchable from one route.

Delegates a bounded repository task to an allowlisted external coding CLI through a guarded runner, with provider selection, timeout handling, and independent local review.