design-human-ai-workflow

Installation
SKILL.md

Design Human AI Workflow

Contract

Design the joint system, not an AI feature in isolation. Autonomy must match uncertainty, reversibility, user expertise, and consequence. A human approval step is not a control when the reviewer lacks context, time, or a meaningful alternative.

Workflow

  1. Map the current job, actors, information, tools, decisions, handoffs, exceptions, incentives, and failure recovery.
  2. Identify where AI could retrieve, transform, recommend, generate, decide, or act. Compare it with simpler automation and unchanged human work.
  3. Assign responsibility for each step: human only, AI proposes, AI acts with confirmation, AI acts within limits, or AI acts with retrospective review.
  4. Define context sources, freshness, permissions, provenance, uncertainty, and what the system must never infer or retain.
  5. Design previews, explanations, confidence or evidence cues, editing, approval, cancellation, undo, escalation, and safe defaults appropriate to the risk.
  6. Handle ambiguity, tool failure, partial completion, conflicting instructions, stale state, unavailable reviewers, and repeated failure without silent continuation.
  7. Define learning and feedback loops without making users responsible for endless correction or turning unreviewed feedback into truth.
  8. Measure task success, effort, time, quality, override, recovery, trust calibration, distributional effects, and automation-induced errors.

BuildBetter Acceleration

Installs
1
GitHub Stars
4
First Seen
Oct 27, 2026