mixer-policy-safety
SkillDev toolsReview, harden, and test the safety policy for AI-Controlled Party mixer/Soundcraft Ui24R scene arming. Use for approval gates, blocked mixer operations, hazardous request handling, venue validation, bypass attempts, QA, risk review, or follow-up safety changes.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the mixer-policy-safety skill
What this skill tells your AI
The instructions your AI receives, as published by pantani/tdmcp in .claude/skills/mixer-policy-safety/SKILL.md and read by ahel’s review.
Review the design from the viewpoint of a live-show safety gate.
Context to read
_workspace/ai-party-mixer/01_contract.md_workspace/ai-party-mixer/02_adapter.md- current
show-directorschema/runtime - AI-Controlled Party docs/spec
Review rules
- AI can arm; human operator approves.
- Scene/cue execution must be predeclared and auditable.
mixer_gain,pa_mute,audio_routing, channel edits, and routing changes stay blocked/operator-only.- Live execution requires dry-run tests, adapter health, rollback/fallback notes, and a venue rehearsal.
- Low-confidence voice/STT input cannot execute or approve anything.
Output
Write _workspace/ai-party-mixer/03_policy_qa.md with pass/fail findings,
bypass attempts, required tests, validation gates, and residual risks.
Quality bar
Prefer a clear block over a clever risky shortcut. If a claim depends on venue hardware, mark it venue-validated-only.
Signals
- GitHub stars
- 41
- Forks
- 9
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
mixer-policy-safety- Source
- github.com/pantani/tdmcp