Loading...
Loading...
Found 153 Skills
Manage design systems in Stitch using MCP tools. Includes retrieval of assets, creating/updating design systems in Stitch, and applying them to screens.
Runs plugin health checks (venv packages, skill registration, and album slug collisions). Use when the user asks to check plugin health, verify setup, or troubleshoot missing skills.
Build, modify, debug, or verify Runway Model Routers: inspect live config and eligible models via MCP, manage approved settings, integrate routed SDK calls, and inspect routing results. Use with +runway-dev. Not for direct per-model endpoints or agent REST CLI.
Use this skill when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets, multi-agent teams with sub_agents. Even if the user just says they want to "build an AI agent with Docker", "make a coding agent config", "add a tool to my agent", or "set up a team of agents", this skill applies. Covers agent properties (model, instruction, toolsets, sub_agents, fallback), the models/providers sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands.
Drive Real A11y interact-then-diff loops: checkpoint the semantic tree, click or type by role + accessible name, then diff. Use for MCP checkpoint_tree / click_element / type_text / focus_element / diff_tree, or CLI interact / click / type / focus with --session.
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
Build, modify, debug, or verify Runway Characters integrations: inspect preset or custom avatars with MCP, manage live Sessions via SDK, and connect the application UI. Use with +runway-dev. UI says Characters; MCP/API use avatars. Not for avatar video generation endpoints.
Work with KubeSense alerts — survey what is firing, inspect a rule's breaching condition and history, and create rules either via the create-alert MCP tool or as import JSON over metrics, logs, and traces. Includes validate-alert-json for checking hand-built rule JSON, the alert engine's own field allow-lists, which differ from the query engine's, and translating Datadog monitors. Also covers multi-query formula rules, the Alert. placeholder namespace, manual resolve, and maintenance windows.
Work with Google Drive through its MCP tools - search, read, create, organize, share, comment, and export files. Use when creating files in specific folders, moving or renaming, converting Markdown/CSV into Docs/Sheets, managing comments, or exporting a rendered PDF.