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.Handles academic papers, web articles, reports, and documentation for non-developer users. Extracts key findings, compares multiple sources, and produces structured research summaries with formatted citations.
Requires writing a test before implementation and observing its failure. Then guides writing minimal code to pass, ensuring the test checks behavior.
Sets up vLLM or SGLang serving on Jetson. Uses upstream vLLM on Thor and Orin with JetPack 7.2 or later, and NVIDIA-AI-IOT vLLM on older Orin systems.
Generates Product Requirements Documents for feature planning and task orchestration in ralph-tui. Includes user stories that can be converted into beads issues or prd.json for automated execution.
Selects a serving stack and memory configuration for LLM or VLM workloads on NVIDIA Jetson. Covers vLLM, SGLang, llama.cpp, and TensorRT Edge-LLM runtime flags.
Provides browser automation and web testing guidance using Selenium WebDriver. Covers element location, waits, and test organization.
Provides a performance optimization agent skill. The description does not specify the target systems or optimization techniques.
Organizes a company's brand portfolio through parent-brand relationships, hierarchies, and naming systems. Supports decisions about branded houses, houses of brands, and extensions under existing brands.
Applies a typed 80-item CORE-EEAT profile to assess content quality and publishing readiness. Examines evidence coverage and veto checks, then produces a plan for improvements.
Structures planning before implementation through explicit requirements, technical design, and task breakdowns. Suits work spanning multiple modules, unclear acceptance criteria, or substantial architectural decisions.
Determines which pages a new or existing website needs and prioritizes their creation. Supports sitemap planning, page organization, and website hierarchy.
Maps codebase boundaries and builds a defensive security review roadmap in workspace/plan.json using the active threat model and historical learnings. It supports campaign planning rather than code review execution or patching.
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