Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Localizes existing video or audio into one or more languages while preserving the presenter's identity and cloning their voice. Supports synchronized lip movement and subtitle review before rendering, returning an output for each target language.
Guides use of Microsoft's MarkItDown Python utility to convert documents, spreadsheets, presentations, images, audio, structured data, archives, and web sources to Markdown. Supports document processing pipelines, text extraction, and LLM preprocessing.
Supports bounded process-based simulations involving events, resources, interrupts, and monitoring. Covers replications, warm-up periods, and reproducible output analysis.
Takes a list of projects and their supporting documentation and arranges them in the SRED format for submission.
Analyzes what-if questions using four to six scenario branches, including best, likely, worst, wild card, contrarian, and second-order outcomes. Supports strategic decisions, contingency planning, and exploration of uncertain futures.
Implements Paddle webhook handling in a Next.js Route Handler. Covers signature verification, idempotency, retry behavior, and local testing.
Supports multi-objective optimization using NSGA-II, NSGA-III, and MOEA/D. Covers Pareto fronts, constraint handling, and benchmark problems such as ZDT and DTLZ.
Supports backbones including FAN, EfficientNet, and ResNet. Covers training, evaluation, distillation, quantization, export, and inference.
Supports training, evaluation, export, pruning, quantization, retraining, and inference for OCRNet. Recognizes text from cropped text-region images with CTC or attention-based decoders.
Synthesise the current conversation into a specification and publish it to the project tracker. Uses what has already been discussed without conducting another interview.
Runs a two-step pipeline that extracts referring expressions from image-caption pairs and grounds them to pixel-space bounding boxes with a VLM. Supports automatic labeling for image grounding datasets.
Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for multi-node distributed training. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator installed, or when integrating TAO into an existing k8s-native ML platform.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name