Skip to content

prompt-hierarchy

Domain: prompt · Model class: cheap

Use this skill when the user wants to work on Calibrating AI agent autonomy levels and control surfaces for tasks. Triggers include “calibrate agent autonomy”, “how much autonomy should my agent have”, “set up agent control surfaces”. Do NOT use when design a multi-step pipeline (use core-workflow-orchestrator).

Calibrating AI agent autonomy levels and control surfaces for tasks. This skill provides structured guidance, references, and worked examples to help produce high-quality, actionable outputs.

  • “calibrate agent autonomy”
  • “how much autonomy should my agent have”
  • “set up agent control surfaces”
  • “choose between guided and autonomous mode”
  • design a multi-step pipeline (use core-workflow-orchestrator)
  • write a prompt template (use core-prompt-engineering)
  1. What is the user’s goal and current state?
  2. What constraints (time, team, compliance) apply?
  3. Are there existing artifacts (specs, code, benchmarks) to reference?
  • prompt asset
  • explicit output contract
  • failure handling
  • worked example or usage guidance

flow-orchestrator · gov-workflow-compliance