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 tune-once, cache, and launch patterns, parameter space design, and configurations for sm80 through sm120. Addresses tile sizes, occupancy, num_ctas, and common correctness or performance pitfalls.
Evaluates agent security controls against OWASP ASI 2026 risks. Supports security posture reviews, control mapping, compliance reports, and comparisons of agent framework security features.
Translates brand strategy into visual direction for designers or agencies. Defines logo direction, color palettes, typography, imagery style, and design system foundations.
Builds a scratch plan within the target page and iterates on purpose, structure, and draft steps with the user. Drafts one section per approved step and removes planning material afterward.
Analyzes tasks using Vertical Slice Architecture, Clean Architecture, DDD, and Modular Monolith approaches. Produces structured implementation plans for work requiring multiple steps.
Transforms a natural-language feature description into a feature specification. Supports both creating new specifications and updating existing ones.
Perform read-only disk scans and classify space consumers by cleanup risk. Generate a collapsible HTML report with copyable commands, with an optional local service for moving items to trash or deleting them.
Uses a fresh-context subagent to verify documentation claims against source and rerun documented commands. Manually checks pages, sections, or changed claims independently of the drafting loop.
Writes or edits pages in the OpenSpec docs tree using its house style guide. Emphasizes action-first language, scannable content, and no preamble.
Writes, edits, and reviews prose to eliminate predictable AI patterns and formulaic language. Applies to scientific writing, blog posts, newsletters, memos, reports, and other substantial text.
Retrieves structured stock sentiment, social activity, and Polymarket coverage through the Adanos Finance API. Compares tickers and agreement across sources in a read-only workflow.
Compares documented intent with implementation evidence to find meaningful behavioral mismatches. Supports audits of AI-built code, checks of access control against documented permissions, and verification that a codebase follows its own documentation.
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