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."..." for exact phrases · Try typography, debugging or spreadsheetOpens the hosted context-mode Insight analytics dashboard in the default browser. Provides AI-assisted engineering teams with per-engineer productive rates, retry waste, blocker detection, and role-specific views.
Deletes all indexed content from the context-mode knowledge base and resets session statistics. The purge is destructive and cannot be undone.
Displays how much context window context-mode saved during the session, including token consumption, savings ratio, and a per-tool breakdown. It is read-only and cannot reset statistics or clear the knowledge base.
Pulls the latest context-mode code, builds and installs it, and updates the global npm installation. Also configures hooks and fixes settings.
Computer Use Agent — autonomous browser control via Steel, Browser Use, and Browserbase cloud providers. Supports headful CDP sessions, CAPTCHA solving, proxy rotation, live view, session recording/replay, Playwright/Puppeteer integration, and LLM-driven visual browsing. Use when asked about computer use, browser automation, web scraping, Steel sessions, cloud browsers, headful browsing, CAPTCHA s…
Extract Gherkin scenarios from story markdown files into runnable .feature files and generate step definition stubs. Use when syncing stories to test suites.
Provides guidance on setting up CUDA-Q, selecting simulation targets, and accessing QPUs. Covers authoring kernels with @cudaq.kernel.
Scaffolds and defines resource kinds with spec and status schemas, reusable named types, and field constraints. Registers versions in the app manifest, configures custom routes and code generation, and handles generation errors.
Supports modifying and contributing to NVIDIA cuOpt, including solver internals, C++/CUDA, Python, server components, and CI. Covers builds, tests, debugging, pull requests, DCO, and code conventions.
Installs cuOpt for Python, C, or server use through pip, conda, or Docker and verifies the installation. Building from source is outside its scope.
Traces, completes, and interprets Pareto frontiers across competing objectives. Uses repeated single-objective cuOpt solves with weighted-sum and ε-constraint methods.
Explains LP, MILP, and QP concepts and parses problem descriptions into parameters, decisions, constraints, and objectives. Focuses on mathematical formulation rather than API usage.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
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