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.Covers aggregates, aggregate roots, value objects, domain events, domain services, and strongly typed IDs. Includes repository patterns for aggregate persistence and pairing DDD with Clean Architecture.
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining an…
Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, aut…
Runs multi-perspective deliberation on questions, plans, and complex choices. Supports expert-style panel discussion, devil's advocate analysis, and examination of dilemmas and trade-offs from several angles.
Analyzes PayPal and QuickBooks sales to identify top performers and slow movers, then incorporates seasonality. Produces a strategic brief covering products to promote, offers to run, and items to hold, without creating calendars or assets.
Runs a multi-step annotation pipeline using VLM and LLM distillation. Produces multi-level captions and multiple-choice, binary, or open-ended question-answer pairs with reasoning traces.
Provides access to Cournot probability queries and management of prepaid calls, account balances, and API keys. Intended for explicit Cournot requests or the /cournot command.
Provides guidance and local audit tools for workflows using GeoSeries and GeoDataFrame. Covers spatial operations and vector-data input and output.
Supports text, image, and reference-based video generation plus natural-language editing. Covers character preservation and clips up to 15 seconds at 720p or 1080p for demos and social content.
Diagnoses and safely reclaims macOS disk space: caches, logs, app remnants, large/duplicate files, Docker/OrbStack, Chromium code-sign clones, developer caches. Use when a Mac is low on storage, shows “Caching needs more space”, or before deleting anything to avoid data loss. Not for Windows/Linux or permission issues (use macos-permissions).
Runs format conversion for datasets supported by NVIDIA TAO DAFT. Applies specifically to DAFT data rather than general dataset conversion.
Selects the appropriate prompts for gh-aw workflow requests. Covers workflow design, creation, debugging, and upgrades.
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