Agent Progression Designer

Design evidence-based progression systems for AI agents, multi-agent swarms, creator ranks, capability levels, trust gates, eval trials, autonomy unlocks, and non-vanity XP. Use when work involves gamifying agent performance, ranking coding agents, mapping swarm roles, or turning completed work into durable progression.

frankxai Updated

File contents

Agent Progression Designer

Use this skill to design agent progression that proves capability rather than rewarding noise.

Workflow

  1. Identify the agent role and task domain.
  2. Define progression axes: knowledge, craft, judgment, stewardship, throughput, collaboration, productization.
  3. Define evidence events that count toward XP.
  4. Define trials that prove rank-up readiness.
  5. Define autonomy unlocks and renewal requirements.
  6. Add anti-abuse rules.
  7. Output Markdown cards and ledger event examples.

Quality Gates

  • No XP without evidence.
  • No global rank that hides actual strengths and weaknesses.
  • Advanced autonomy requires recent accepted work.
  • Failed trials create repair tasks.
  • Stewardship and risk-catching must count as real progress.

Output Shape

  • Agent role card.
  • Progression axes.
  • Rank table.
  • Trial definitions.
  • Ledger event examples.
  • Autonomy unlock policy.

frankxai/awesome-gamification-agent-skills/tree/main/skills/agent-progression-designer commit 6aaa8e9a45

Frequently asked questions

npx skillmds@latest add frankxai/agent-progression-designer