Simulate Agents
SkillAI & modelsLets your agent test a finished feature by role-playing a mock user and an auditor before a human reviews it.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Simulate Agents skill
About this skill
Run Mock User and Auditor agents against a feature in fresh contexts before human review. Use after verify-work, before request-review, when user wants pre-review simulation.
What this skill tells your AI
The instructions your AI receives, as published by danielvm-git/bigpowers in skills/simulate-agents/SKILL.md and read by ahel’s review.
HARD GATE — HARD GATE — Simulations are hypothetical. Do NOT use sim results to make production decisions without validation on real agents. Sims help discover gaps, not replace testing.
Two roles, isolated contexts (no shared state with BUILD agent):
- Mock User — follows Verification Script; reports UX gaps in plain language.
- Auditor — checks CONVENTIONS.md, security checklist, test coverage; structured pass/fail.
Process
- Read story Verification Script + changed files diff.
- Spawn Mock User: step through UAT script; log failures.
- Spawn Auditor: run
audit-codechecklist cold. - Write
specs/SIMULATION-<feature>.mdwith both reports. - Failed items →
respond-revieworplan-workgaps — do not skip human review.
Verify
→ verify: test -f skills/simulate-agents/SKILL.md && test -d specs/verifications
Signals
- GitHub stars
- 248
- Forks
- 19
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
simulate-agents- Source
- github.com/danielvm-git/bigpowers