Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when editing AgentHTML artifacts, agent-html files, Gallery Preview DSL, blocks, components, sections, prompt schema, or runtime-rendered artifact content. Before editing AgentHTML content, read `.agents/skills/agent-html/references/prompt-schema.md` for the current DSL contract and enabled component grammar.
Build DAG-based AI pipelines connecting Gradio Spaces, HuggingFace models, and Python functions into visual workflows. Use when asked to create a workflow, build a pipeline, connect AI models, chain Gradio Spaces, create a daggr app, build multi-step AI applications, or orchestrate ML models. Triggers on: "build a workflow", "create a pipeline", "connect models", "daggr", "chain Spaces", "AI pipeline".
Set up an MCP server target for Opfor red-teaming.
Set up an agent or chatbot target for Opfor red-teaming.
MANDATORY before editing ACPClient, ACPTransport, AgentInstance, ACP provider flow, tool-call parsing, permission requests, provider switch, reconnect, or ACP subprocess lifecycle in agentic.nvim.
MANDATORY before editing MessageWriter, PermissionManager, tool-call block rendering, sender headers, thinking blocks, auto-scroll, folds, status rows, permission buttons, or chat-buffer tool-call tests.
Create or modify OpenCowork Custom Extensions. Use when the user asks to build a custom extension/plugin for OpenCowork that adds Agent tools, declarative HTTP tools, sandboxed JavaScript handlers, extension configuration fields, network allowlists, or custom response UI renderers, or to bundle skills, sub-agents, slash commands, MCP servers, or persistent state into one installable extension.
Create or update a reusable personal OpenCowork artifact-template skill. Use when the user invokes $template-creator or asks in natural language to create a template using, from, or based on an attached Word document, PowerPoint presentation, or Excel workbook, or explicitly asks to edit or update a passed artifact-template skill. Do not use for one-off artifact creation from an existing template.
Design and implement ADK-Rust agent workflow patterns including LLM, sequential, parallel, loop, and multi-agent orchestration. Use when building or refactoring agent topology.
Bootstrap new ADK-Rust applications with correct crate/features, provider setup, and verification steps. Use when starting a new agent app or converting an existing Rust app to ADK-Rust.