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.Run a quarter-boundary workflow that updates quarter-scoped folders and archives finished projects. Grade the closing quarter's goals or OKRs and draft the next quarter's goals behind an approval gate.
Guided first-run that produces a real verified win in under five minutes using the skill library on a seeded offline fixture. Load when a new user asks how to start, run the demo, try agent-loom, or get a quick win. Also triggers on "quickstart", "first run", "demo agent-loom", "try the skills", or onboarding to the library. Zero external credentials required. Idempotent — safe to run multiple tim…
Tone down overly bold or visually aggressive designs. Reduces intensity while maintaining design quality and impact.
Identifies a World R skill without describing its functionality.
Exploit Time-of-Check to Time-of-Use (TOCTOU) race conditions in web applications and APIs. Use this skill when testing transactional operations (e.g., applying coupons, transferring funds, redeeming rewards, or purchasing items) to bypass business logic and duplicate actions before the server updates its database state.
Guides the development of Retrieval-Augmented Generation systems for LLM applications. Covers embedding models, vector databases, chunking strategies, semantic search, and retrieval optimization.
Covers Retrieval-Augmented Generation implementation patterns, including document chunking, embeddings, and vector stores. Supports vector and semantic search with retrieval optimization.
Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external document retrieval. Covers document injection, embedding manipulation, knowledge…
Looks up up-to-date Railway documentation to provide accurate answers. Supports questions about platform features, how Railway works, and supplied docs.railway.com URLs.
Supports substantial or tedious tasks whose completion can be verified by tests, linters, or builds. Examples include implementing a specification, fixing all lint errors, and making all tests pass; excludes work needing human judgment during execution.
Supports plugin development for Ghidra and IDA. Focuses on converting scripts into engineered plugin projects.
Provides React development rules focused on asynchronous behavior, rendering, and bundle performance.
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