跳到正文
cccskills
免费在 GitHub 公开

mixer-scene-contract

Design the MixerSceneIntent, approval state, JSON schema, CLI examples, audit entries, and tests for AI-Controlled Party mixer/Soundcraft Ui24R scene arming. Use whenever a task mentions mixer scenes, Ui24R snapshots/cues, operator-approved mixer control, show-director contract updates, schema updates, dry-run CLI shape, or follow-ups that revise this contract.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos
查看安装方法

包含的文件（1）

  • SKILL.md1.6 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

mixer-scene-contract

Design the structured contract for approved mixer scene changes. This skill is for design/spec work, not implementation.

Context to read

  • src/automation/showDirectorSchema.ts
  • src/automation/showDirectorRuntime.ts
  • src/cli/agent.ts around show-director
  • tests/unit/showDirector.test.ts
  • tests/unit/cliAgent.test.ts

Design rules

  • Keep mixer scene changes separate from generic arm_effect.
  • The MVP operation is "arm scene/cue for approval", not autonomous execution.
  • Require explicit names or IDs: show_name, snapshot_name, cue_name, scene_id, or setlist_ref. Do not design fuzzy live lookup as execution.
  • Preserve blocked/operator-only semantics for mixer_gain, pa_mute, and audio_routing.
  • Every accepted request needs an audit entry with request, intent, decision, approval ID, operator, and adapter target.

Output

Write _workspace/ai-party-mixer/01_contract.md with:

  1. proposed schema fields and examples;
  2. approval and audit model;
  3. CLI dry-run examples;
  4. mapping to action plans;
  5. compatibility notes;
  6. unit-test checklist.

Quality bar

The result should be specific enough that a builder can implement it without asking what fields exist or how approval flows.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

agent-manager-skill

免费

Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agent-memory-mcp

免费

Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agent-pipeline

免费

Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agent-tool-builder

免费

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agentic-harness-patterns

免费

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

agenttrail

免费

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

中文简介正在准备中。当前显示原文说明。

hybridlabor-api/aos62026年10月16日 更新

查看 hybridlabor-api 的全部技能

报告此技能的问题