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.Validates compatible NVIDIA driver, CUDA Toolkit, and Container Toolkit versions. Supports checks on Linux distributions and approval-based automated installation on Debian, RHEL, and SUSE families, with manual instructions elsewhere.
Addresses broken and unreliable Playwright tests. Supports debugging failures, intermittent errors, and tests that only pass sometimes.
Supports code refactoring operations such as renaming functions, extracting modules, restructuring classes, and moving code between files.
Brainstorms research directions through iterative refinement and literature-based novelty checks. Scores ideas on interestingness, feasibility, and novelty.
Completes outcome-focused business, marketing, product, and creative workflows with Firecrawl. Produces deliverables such as research reports, literature reviews, SEO and QA reports, lead lists, knowledge bases, and website design systems.
Classifies pull request changes, performs surface-level checks, and determines required reference material. Writes results to .pr-triage.json for downstream code review and CI cost optimization.
Addresses ten known training failure modes on NVIDIA DGX Spark. Supports checks before long GB10 jobs and diagnosis of startup failures, out-of-memory errors below 128GB, and mid-run slowdowns.
Uses official corporate registries, filings, and offshore datasets to trace ownership and control. Supports KYB and UBO verification, sanctions screening, shell-company detection, procurement integrity, and acquisition diligence.
Writes posts for LinkedIn, Twitter/X, Threads, Bluesky, Facebook, Instagram, TikTok, Pinterest, and YouTube. Turns supplied topics or ideas into platform-specific social content.
Supports memory headroom planning and diagnosis of unified-memory out-of-memory failures on GB10. Covers temperature and power monitoring during long-running training jobs.
Compares storage services by cost, performance, configuration, and security. Covers migration, archival, replication, recovery, shared file systems, and storage for specialized workloads, excluding managed databases and query engines.
Covers PyTorch, Unsloth, TRL, and vLLM installation on NVIDIA DGX Spark with GB10, aarch64, and CUDA 13. Addresses libcudart and wheel ABI errors and choosing between NGC containers and pip installations.
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