Skip to content

yzsp-studio/mediakit-shared-suite / creative-drama

creative-drama

Verified

完整制作短剧、微电影、剧情短片、动画短片、动态漫、剧情视频和长篇剧本。用户明确需要角色驱动、冲突因果、剧情弧线、角色与道具资产、分段视频、抽帧连续性和成片交付时调用。当用户提出短剧、动画短片、微电影、短片、电影、剧情视频、AI视频、影视化短片、动态漫、宣传片、预告片等影视剧制作需求,或包含"做个短剧"、"拍个微电影"、"弄个动画短片"、"做个长视频"、"宣传片"等表达时调用。只有宣传片、预告片或广告片被明确要求做成完整剧情链、角色行动链或影视剧式叙事时才调用本 skill;普通品牌宣传、企业宣传、产品广告、UGC、活动预告、信息流广告和通用创意视频使用 creative-video。

references/cli/get-workspace.md

View on GitHub
# `design-cli design-workspace +get-workspace`

查当前会话上挂的画布。复用 Alice IDL 的 `GetCanvasWorkspace`(按会话查)。

## 用途

回答一个问题:**这个会话上有没有画布**。

- **有** → 返回 `canvas_workspace_id` 与 `version`,用于显式恢复或核对目标 Workspace
- **没有** → 返回 `exists=false`

本命令只用于显式查询、恢复和排障,不是创作任务的默认初始化入口。执行创作 Skill 时先读取当前对话:已有唯一有效 Workspace ID 就直接使用;对话没有 ID 就按 Skill 规则调用 [`+workspace-create`](workspace-create.md),不要先用本命令查询。

这是每轮创作的**第一条命令**:手上没有画布 ID 时先查,别直接建 —— 会话上已有画布时重复建会拿回同一张(服务端按会话幂等),白绕一圈。

## 命令

```bash
design-cli design-workspace +get-workspace
```

零参数。会话 ID 由 CLI 从环境变量读取(沙箱注入):优先 `MCP_VM_CONVERSATION_ID`,未设或纯空白时回退 `SESSION_ID`。不能用命令行指定。

## 请求

```text
POST /creativity/canvas_workspace/cli/get_workspace
Content-Type: application/json
```

```json
{"conversation_id":"7788"}
```

## 输出

**会话上有画布:**

```json
{"code":0,"msg":"ok","xml_data":"<canvas_workspace><exists>true</exists><canvas_workspace_id>cws_10001</canvas_workspace_id><version>1</version></canvas_workspace>"}
```

**会话上还没有画布:**

```json
{"code":0,"msg":"ok","xml_data":"<canvas_workspace><exists>false</exists></canvas_workspace>"}
```

⚠️ **「没有画布」是正常答案,不是错误** —— `code` 仍是 `0`,退出码仍是 `0`。**按 `<exists>` 分支,不要按退出码判断有没有画布**。查不到时不返回 `canvas_workspace_id` 与 `version` 两格,不要把空串当成画布 ID 往下调。

真正的错误(参数错、内部错)照旧 `code != 0` + 退出码 `1`。

## 典型动线

```bash
design-cli design-workspace +get-workspace
# exists=false → 建一张
design-cli design-workspace +workspace-create --title "雨夜便利店短剧"
# 记下返回的 canvas_workspace_id,后续命令都用它
design-cli design-workspace +ls --canvas-workspace-id cws_10001
```

退出码与错误处理见 [`README.md`](README.md)。
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall