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.Collects preferences for script type, tone, audience, length, hooks, humor, and storytelling. Generates complete YouTube scripts and stores preferences and past scripts to maintain a consistent style.
Refines code to improve clarity, consistency, and maintainability without changing functionality. Focuses on recently modified code unless directed otherwise.
Handles Conda installation of Holoscan SDK v4.3 and later on CUDA 13. Directs CUDA 12 hosts to container or wheel installation methods.
Covers sbatch scripts, torch.distributed.run environment variables, hardware-specific CUDA connection rules, and container conventions. Includes monitoring and diagnosing failures by rank.
Uses structured research instructions to coordinate parallel agents and produce cited investment due diligence. Covers company facts, industry cycles, business segments, financial quality, ownership and governance, market disagreements, valuation and moats, and a consolidated report.
Collects user preferences and generates plan.md and todo.md to start a complete modeling workflow. Invokes skills for problem analysis, modeling, code, charts, diagrams, paper writing, and final validation in stages.
Handles Python installation of Holoscan SDK through pip in a virtual environment. Native C++ installations, apt, and Conda are outside its scope.
Investigates a failing GitHub Actions run or job. Creates a GitHub issue for the identified failure.
Explains context management, verification strategies, explore-plan-implement workflows, prompting, and session management in Claude Code. Addresses parallel sessions, automation, and failure patterns such as repeated mistakes or lost instructions.
Provides a command reference and terminal workflows for GitLab operations. Routes to specialized skills for authentication, pipelines, merge requests, issues, releases, repositories, Artifact Registry token exchange, and other glab commands.
Explains Megatron-LM test layout, recipe YAML structure, and adding and running unit and functional tests. Covers golden values, marker filters, and consistency with CI.
Supports synthetic T1, T2, FLAIR, SWI, and MRA brain MRI volumes. The workflow is not intended for production training data.
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