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.Organizes PyTorch code into LightningModules and configures Trainers, data pipelines, callbacks, and experiment logging. Supports multi-GPU and TPU training and distributed strategies including DDP, FSDP, and DeepSpeed.
Adapt vision-language models to visual domains or tasks through supervised learning. Covers frozen-vision-tower LoRA configuration and troubleshooting runs that train without learning.
Supports time series classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Uses scikit-learn-compatible APIs for temporal and sequential data analysis.
Supports debugging failures, locating error origins, and tracing bugs through code.
Manages matrix enablement, impact and urgency mappings, manual overrides, and fallback priority through the sf CLI. Reads existing values before changes and requires explicit confirmation for mutations.
Supports symbolic algebra, calculus, equation solving, and linear algebra in Python. Includes code generation through lambdify and LaTeX output, with a focus on exact symbolic computation.
Manages persistent knowledge through facts, daily notes, entity records, weekly synthesis, and recall. Supports memory of user patterns and plans across sessions.
Uses the Zotero Web API v3 to retrieve, create, update, and delete library items and associated resources. Supports citation exports, library searches, PDF uploads, and research automation integrations.
Shannon is an autonomous AI pentester for web applications and APIs. It combines white-box source code analysis with live exploit execution.
Guide implementation of Effect workflows, services, layers, schemas, and configuration. Covers schedules, caches, streams, HTTP clients, and tests.
Provides FigJam-specific guidance for agents using the use_figma MCP tool. Complements the foundational tool guidance in figma-use.
Creates images through the OpenRouter Image API using multiple AI models. Supports artwork, concept art, logos, reference-based editing, and compositing; technical diagrams are handled by a separate skill.
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