sim-conductorlisted

# sim-conductor — Meta-Simulation Automation Orchestrator > Places deep-insight personas (fe-marketplace) in an isolated environment to validate AI tools from the external user's perspective, classifies findings into M/S/R tiers, and completes the pipeline through to PR automatically. ## Core Principle — Beyond Self-Inspection The structural trap in AI tool quality validation: when the builder tests, they are always confined to an internal perspective. sim-conductor addresses this limitation with **physical isolation + AI personas**. ``` Development environment (harness root) ↕ physical isolation Isolated environment (~/sim/observer/) ← new user reproduction space (zero development context) ``` The devil-advocate persona captures that self-inspection is cleaning, not a vaccine — clarifying the need for a real external mirror (direct external user validation). In Path B (environments without `~/sim/`), logical isolation (agent prompt directives) substitutes, and only Area B is recommended. Runs autonomously through to PR or report commit. User involvement = 1 trigger + 1 PR review. ## Invocation Triggers | Trigger pattern | Suggested Area | |---|---| | "Look at this from an external user's perspective", "How would someone else see this?" | Area A | | "Check the harness", "asset audit", "internal audit" | Area B | | "Any new ideas?", "ideation scan", "naming candidates" | Area C | | "Review this code" (pre-PR), "review this prompt" | Area D (code) | | "Check