Agent skill
docker-compose-launch
Launch worktree-scoped local services for issue implementation when a monorepo skill requires database dependencies.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/docker-compose-launch
SKILL.md
Docker Compose Launch
Overview
Use this skill only when the selected implementation workflow explicitly needs local services before app startup, migrations, or tests can run. Keep all service startup scoped to the assigned worktree and treat Docker Compose as a reusable helper for local implementation and test dependencies only.
Invocation Contract
The parent implementation skill should pass or infer this contract before acting:
required:trueorfalseworktree_path: absolute path to the assigned worktreeservice_types: one or more ofmysql,mariadb,postgres, ormongodbreason: short explanation of which app, package, migration, or test command needs the servicespreferred_mechanism: repository-native compose file, repo script, or fallback compose generation
If required is false, return status: not_needed and do nothing else.
Execution Rules
- Prefer repository-owned
docker-compose.yml,docker-compose.yaml,compose.yml, orcompose.yamlfiles before generating new files. - Prefer repository scripts or task-runner commands that already wrap Compose when they are documented and usable.
- Namespace any generated project name, file, network, volume, or container identifiers to the assigned worktree.
- Wait for service readiness before reporting success.
- Surface the exact startup and teardown commands that were used.
Structured Result
Return a concise structured summary using these fields:
status:ready,not_needed, orfailedservices: services that were started or detectedmechanism:repo_compose,repo_script, orgenerated_fallbackcommands: startup, readiness, and teardown commandsconnection: host, port, database, username, URL, or env hints when availablecleanup: explicit stop command, ornoneartifacts: compose files or env files created or reusednotes: concise caveats or follow-up steps
Guardrails
- Do not launch services outside the assigned worktree scope.
- Do not assume every repository needs Docker Compose.
- Do not replace a documented repository-native startup flow with a generated one unless the native path is unusable.
- Do not claim success until the requested service is accepting connections.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?