ontology
Creates and queries entities such as people, projects, tasks, events, and documents in a typed knowledge graph. Supports relationships, constraints, graph-based action planning, and shared state across skills.
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.Creates and queries entities such as people, projects, tasks, events, and documents in a typed knowledge graph. Supports relationships, constraints, graph-based action planning, and shared state across skills.
Produces object-oriented component documentation using a shared template. Provides separate guidance for creating new documentation and updating existing documentation.
Apply Boyd's OODA loop to navigate fast-moving, uncertain, or competitive situations — Observe what is actually happening, Orient through mental models and context, Decide on the clearest path, Act quickly, then loop again. Load when the situation is changing faster than the current plan, when a competitive response is needed, when the user is stuck in analysis paralysis in a dynamic environment, …
Provides expertise in Open-AutoGLM, an AI phone agent framework powered by the AutoGLM vision-language model. It enables natural-language control of Android, HarmonyOS, and iOS devices.
Uses the OCR CLI to review pull requests, staged or unstaged changes, commits, and branch comparisons. Produces line-level comments and can apply requested fixes. Review rules can cover bugs, security vulnerabilities, performance, and code quality.
Delegates code review reasoning to the host agent's own model capabilities. OCR provides deterministic file selection and rule resolution instead of calling an LLM endpoint.
Provides platform-neutral guidance for the Open Computer Use MCP server and CLI. Covers installation, verification, configuration, troubleshooting, and operation through the native CLI, stdio MCP server, or direct tool calls.
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
Defines the agent runtime contract for reading, searching, editing, and linting markdown in an OpenKnowledge project. Covers MCP tools, grounding, links, folders, templates, and live preview, with in-scope markdown handled through OpenKnowledge tools.
Guides discovery and setup of OpenKnowledge using ok init, ok cowork, and OK Desktop. Covers repository installation, previewing standalone markdown files, sharing projects, and capability questions; project editing is covered by a separate runtime skill.
Guides turning reusable agent workflows into installable skills. Covers project versus global scope, repository layout, SKILL.md frontmatter, progressive disclosure, trigger refinement, evaluation, and installation into editors.
Ingests documents, web pages, video, and audio into research notebooks. Supports AI notes, summaries, document chat, full-text and vector search, custom transformations, and multi-speaker podcasts across multiple AI providers.
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