Agent skill
babysitter
Orchestrate complex multi-step workflows using babysitter SDK
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/babysitter
SKILL.md
Babysitter Orchestration
Use this skill to orchestrate complex, multi-step coding workflows through babysitter's process-driven execution engine.
How It Works
- Babysitter creates a run from a process definition (JavaScript file with tasks)
- Each iteration produces effects (tasks to execute)
- You execute the effects and post results back
- The loop continues until the run completes
Starting a Run
Use the SDK bridge directly (imported from the extension):
createNewRun()to create a runiterate()to advance the orchestrationpostResult()to report effect outcomes
Effect Types
| Kind | Action |
|---|---|
| agent | Execute as sub-agent task |
| node | Run Node.js script |
| shell | Run shell command |
| breakpoint | Ask user for approval |
| sleep | Wait until timestamp |
| skill | Expand and execute skill |
Completion
When the run completes, the SDK returns a completion proof. Output it wrapped in <promise>PROOF_VALUE</promise> tags.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?