Loading…
docker-agent-run
Cursor Skill
Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make
Skills across Dockerfiles, Compose, Docker Agent, Docker Sandboxes, and safe Docker workflows.
Created by DockerView Source
Skills11
docker-agent-configUse 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
docker-agent-deployUse this skill when exposing a Docker Agent as a server (MCP, HTTP API, A2A, ACP, or OpenAI-compatible chat), distributing an agent via an OCI registry with `docker agent share`, or measuring agent quality with `docker agent eval`. Even if the user just says they want to "turn my
docker-agent-runUse this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make
docker-build-strategiesUse this skill when writing, reviewing, or optimizing Dockerfiles, even if the user just says their image is too large, their build is slow, or they need to harden a container for production. Covers multi-stage builds, layer caching, .dockerignore, non-root users, and image size
docker-compose-patternsUse this skill when creating, modifying, or debugging Docker Compose configurations, even if the user just says they need to wire services together, add a database to their stack, or set up a local development environment with multiple containers. Covers service definitions, heal
Related plugins
Floot
Build and host full-stack apps.
Lightrun
Lightrun live-runtime debugging skills with deterministic preflight and evidence-first diagnosis.
Browserless
Browser automation tool for AI agents: web scraping, crawling, and web search, with built-in stealth features by running headless browsers in the Browserless cloud
Turso
Manage Turso Cloud (organizations, databases, groups) and run SQL from Cursor via the hosted Turso MCP server — OAuth login, no API token to copy.
incident.io
Makes your agent fluent in incident.io: responding to and investigating incidents, working with on-call schedules and escalations, and authoring the operational content — runbooks, skills, and plugins — that incident.io investigations draw on. Bundles the official incident.io MCP server.
GoDaddy
Brainstorm domain names and check availability.