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.Covers a four-project layout with Domain, Application, Infrastructure, and Api layers. Explains use case handlers, domain entities with behavior, and infrastructure as a plugin.
Export approved checkpoints as merged safetensors, LoRA-only weights, GGUF with imatrix, or FP8. Covers quantization format selection and troubleshooting failed export smoke tests.
Designs the team's ongoing operating rhythm. Establishes task management practices, collaboration rituals, and tooling to structure daily work.
Produces Excel workbooks, including multi-sheet files, formulas, formatting, financial models, and tabular cleanup. Also handles CSV and TSV inputs when the intended deliverable is a spreadsheet.
Evaluates CodeGraph retrieval quality on a real codebase through comparative agent runs. Supports testing, auditing, or validating local development builds and published npm versions against repositories in a target language.
Uses Firecrawl's paper index for semantic search, related-paper expansion, and in-body verification. Produces literature reviews, systematic reviews, summaries, and sourced syntheses across biomedical and life sciences, computer science, physics, mathematics, and industry publications.
Scans seven GMGN-supported chains and filters tokens by liquidity, real volume, concentration, and rug and developer risk. Scores survivors on a shared 0–100 scale and returns up to ten that meet the score floor. Supports narrowing chains, token age, result count, and minimum score.
Apply GRPO and reinforcement learning from verifiable rewards to math, code, tool calls, and structured output. Covers reward function design and troubleshooting divergence or reward hacking.
Covers n8n workflows from creation through publishing, including visual layout, sticky notes, meaningful descriptions, and node names. Supports validation, testing, archiving, and folder or project organization.
Addresses irrelevant matches, missing results, and low precision or recall in Qdrant. Covers embedding selection, hybrid search, fusion, reranking, relevance feedback, ground truth datasets, and recall@k evaluation.
Create task scenarios for an existing usability study. Include realistic tasks, success criteria, and notes for the facilitator.
Uses ADS-B and AIS sources to trace flights, ships, identifiers, ownership, and port-call histories. Analyzes tracking gaps and dark-fleet behavior for sanctions research, supply-chain compliance, asset tracing, and journalism.
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