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."..." for exact phrases · Try typography, debugging or spreadsheetUses ctx7 to retrieve current library documentation and search, install, or generate AI coding skills. Also configures Context7 MCP for coding agents.
Enables direct use of external apps through the Composio CLI. Also supports building AI agents and applications with the SDK, with access to more than 1,000 apps.
Run a full-site SEO audit and return a scored, prioritized report. Use only for site-wide checks; use seo-page for one URL or seo-technical for a technical-only review.
Covers Angular v20+ nested routing, protected routes, route-based data loading, and signal-based route parameter access. The skill is deprecated and unmaintained; its description directs users to the official Angular skills.
Frames a topic and develops successive debate rounds, each with an ASCII structure diagram. Lets the user control pacing, deepen a section, or introduce participants, then saves the full discussion as an Org note.
Supports new skill creation and revisions to existing skills. Runs evaluations, benchmarks performance with variance analysis, and optimizes descriptions for better triggering accuracy.
Uploads, lists, describes, updates, and deletes models and their versions in the Agent Platform Model Registry. Excludes model training, endpoint deployment, and models outside Agent Platform.
Uses observed UI state, semantic locators, and bounded waits to make browser checks reliable. Includes isolated test data and explicit outcome verification.
Creates architecture, flow, sequence, data model, journey, deployment, and many other diagrams alongside statistical and planning charts. Supports HTML, SVG, and PNG output, .drawio and .excalidraw imports, lifecycle phase maps, and onboarding guidance.
Covers adversarial examples, model extraction, prompt injection, membership inference, data poisoning, and fine-tuning manipulation. Also addresses neural network analysis, LoRA exploitation, and LLM jailbreaking in CTF contexts.
Supports evaluation datasets, metric selection and authoring, LLM-as-judge scoring, and failure analysis for models and agents. Guides dataset schemas and before-and-after comparisons to assess fixes and improve quality.
Carries out phased implementation plans through subagents. Particularly supports executing plans produced by make-plan.
A growing collection of real, public skills. Descriptions and instructions indexed 25 Sept 2026.
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