Loading...
Loading...
Found 4,981 Skills
Analyze videos, screen recordings, and screenshots to generate structured, actionable notes for coding agents. Supports Loom, YouTube, and local files. Extracts visual context, on-screen text, and audio narration. Use when someone shares a video and you need to understand what it shows.
Set up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.
Event-sourced task system for agent collaboration. Use when managing tasks, tracking work, handing off between agents, checking task queues, or reporting progress. Provides both MCP tools and a CLI (ql).
Vercel Agent guidance — AI-powered code review, incident investigation, and SDK installation. Automates PR analysis and anomaly debugging. Use when configuring or understanding Vercel's AI development tools.
Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
Extracts the full design soul, system, and agent rules from reference UI images. Use this skill when the user provides screenshots, Figma exports, or any UI reference images and wants the agent to design with the same soul, taste, feeling, and personality — not just copy colors and spacing. Marrow reads beneath the surface: it extracts the living core of a design — the decisions, proportions, restraint, and emotional intent that make a UI feel the way it does. Triggers on: /marrow, /extract-ui, /design-from-ref, /read-design, or any prompt like "extract the design system from these images", "make it look and feel like this", "get the rules from this UI", "build with the same soul", "match this design". Always use this skill when images are provided alongside a request to replicate, match, or be inspired by a design.
Use a persistent Codex sidecar thread from the local `codex-sidecar` CLI for design review, implementation advice, debugging, and context-preserving follow-up questions while keeping the current agent as the primary executor.
Core patterns for AI coding agents based on analysis of Claude Code, Codex, Cline, Aider, OpenCode. Triggers when: Building an AI coding agent or assistant, implementing tool-calling loops, managing context windows for LLMs, setting up agent memory or skill systems, or designing multi-provider LLM abstraction. Capabilities: Core agent loop with while(true) and tool execution, context management with pruning and compression and repo maps, tool safety with sandboxing and approval flows and doom loop detection, multi-provider abstraction with unified API for different LLMs, memory systems with project rules and auto-memory and skill loading, session persistence with SQLite vs JSONL patterns.
Top-tier software architect agent for complex multi-stage project development. This skill embodies the role of a senior software architect who decomposes complex tasks into structured sub-modules, iterates each component until excellence is achieved, enforces strict quality gates between phases, and produces documentation compliant with all skill standards. Core Philosophy: "Design once, iterate until perfect, then move forward." Triggers when: You need to design architecture for a complex multi-stage project, decompose requirements into modules, or establish quality gates for development phases. Commands: - /architect design <task> - Full architecture design for a task - /architect phase <n> - Execute specific phase - /architect iterate <module> - Iterate on a specific module - /architect status - Show current architecture status - /architect review - Review and validate architecture Six phases: Requirement Analysis, Architecture Design, Task Decomposition, Iterative Development, Integration & Validation, Documentation Generation. Each phase has strict exit criteria.
Guide for conducting thorough, multi-source research and producing comprehensive, well-sourced reports. Powered by AnyCap -- the capability runtime that equips AI agents with web search (including AI Grounded citations), web crawl, image generation, cloud storage, and one-click web publishing through a single CLI. Use when the user asks for deep research, competitive analysis, market research, technical deep dive, literature review, technology comparison, or any task requiring multi-source information gathering and synthesis. Also use when users say "investigate", "survey the landscape", "compare X vs Y", "state of the art", "write a report on", "look into", "find out about", "analyze the market", or any inquiry that needs more than a single search. Trigger on mentions of research, analysis, investigation, comparison, report, survey, or deep dive.
OMC agent catalog, available tools, team pipeline routing, commit protocol, and skills registry. Auto-loads when delegating to agents, using OMC tools, orchestrating teams, making commits, or invoking skills.