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.Uses authoritative evidence when framework, library, runtime, platform, or API decisions depend on current documented behavior. Covers version-specific conventions and official best practices rather than framework-independent logic.
Ground framework-specific implementation in official documentation — detect stack versions, fetch authoritative docs, implement cited patterns, cite sources. Load when building with a library or framework where API correctness matters, when the user wants verified or documented code, or before writing framework code from memory. Also triggers on "source driven development", "cite the docs", "check…
Detect and manage connected MCP sources used for enterprise search. Guide users in connecting new sources, order source priorities, and account for rate limits.
Plan quarterly or annual SOX 404 testing and select samples for revenue, purchasing, IT general controls, and close controls. Build workpaper templates and evaluate and classify control deficiencies.
Define a spacing scale from a base unit and specify when each step applies. Standardises padding and margins while leaving page-level columns and gutters to grid design.
Defines clean, readable interfaces through generous whitespace. Uses consistent padding and grid-based layouts to give content room to breathe.
Assists in provisioning instances and databases, designing performant schemas, and querying data in Cloud Spanner on Google Cloud. Use when designing primary keys, writing SQL queries or client library code, or diagnosing performance issues.
Defines the SPARC workflow for planning complex implementations before coding. Applies to new features, architectural changes, redesigns, integrations, and unclear requirements.
Places, deduplicates, migrates, and validates Spark engineering knowledge across AGENTS, Notes, Roles, Skills, and Workflows.
Writes DataFrame transformations, Spark SQL queries, RDD pipelines, and structured streaming analytics. Optimizes shuffles, partitioning, executor memory, and Parquet processing for distributed workloads.
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.
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.
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