Skip to content
Agentmart
Submit a tool

modao-demo

墨刀 Demo 生成:基于 PRD 调用墨刀 MCP 生成可交互原型。

Skill by xgl1103

IndexedMIT
Write a review

Chalk Labs

Need help deploying modao-demo?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/xgl1103-modao-demo

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

墨刀 Demo 生成:基于 PRD 调用墨刀 MCP 生成可交互原型。

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/modao-demo

What's inside

Skill name
modao-demo
Description
墨刀 Demo 生成:基于 PRD 调用墨刀 MCP 生成可交互原型。
License
MIT
Instructions
124 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# 墨刀 Demo 生成(Modao Demo)

工作流 B 第四阶段,将 PRD 转化为可交互的原型演示。

## 输入

- PRD 文档(`prd_mvp.md`)
- 用户确认(PRD_MVP_GATE 通过)

## 输出

产物文件:`runtime/evidence_ledger/{opportunity_id}/workflow_b/demo/demo_manifest.json`

JSON 结构:

```json
{
  "opportunity_id": "xxx",
  "stage": "MODAO_DEMO",
  "completed_at": "2026-10-15T10:00:00Z",
  "modao_task_id": "task_xxx",
  "modao_task_url": "https://modao.cc/proto/xxx",
  "modao_preview_url": "https://modao.cc/preview/xxx",
  "pages": [
    {
      "page_name": "首页",
      "page_description": "产品首页,展示核心功能入口",
      "components": ["导航栏", "功能卡片", "底部菜单"]
    },
    {
      "page_name": "功能页",
      "page_description": "核心功能页面",
      "components": ["表单", "列表", "操作按钮"]
    }
  ],
  "interaction_flows": [
    {
      "flow_name": "主流程",
      "steps": ["首页 → 功能页 → 结果页"]
    }
  ],
  "demo_status": "completed"
}
```

## 执行步骤

1. **读取 PRD**:加载 `prd_mvp.md`,提取核心页面和交互
2. **页面规划**:定义 3-5 个核心页面
3. **调用墨刀 MCP**:使用 `modao-generator` Skill 生成原型
4. **等待生成**:轮询任务状态直到完成
5. **记录结果**:保存 task_id、预览链接到 manifest

## 子 Agent 任务书

```markdown
## 任务
基于 PRD 生成墨刀原型。

## 输入
- 机会 ID:{opportunity_id}
- PRD 路径:`runtime/evidence_ledger/{opportunity_id}/workflow_b/prd/prd_mvp.md`

## 输出要求
1. 产物路径:`runtime/evidence_ledger/{opportunity_id}/workflow_b/demo/demo_manifest.json`
2. 必须包含 modao_task_id、modao_task_url、modao_preview_url
3. 至少 3 个核心页面
4. 完成后调用:`python scripts/ops.py innovation:workflow-b:demo --id {opportunity_id} --proto-url <预览链接>`

## 执行流程
1. 读取 PRD,提取核心页面和交互
2. 读取 `skills/modao-generator/SKILL.md`
3. 调用墨刀 MCP 生成原型
4. 等待生成完成(最多 100 秒)
5. 保存结果到 manifest

## 禁止
- 不得修改 PRD
- 不得执行 Gate 检查
- 不得跳过墨刀 MCP 直接编造链接
```

## 墨刀 MCP 调用

使用 `modao__generate_html` 或 `modao__generate_react`:

```python
# 示例:生成 HTML 原型
modao__generate_html(
    query="基于以下 PRD 生成可交互原型:\n\n{prd_content}",
    user_input="产品名:{product_name}\n核心功能:{core_features}"
)
```

等待任务完成:

```python
modao__get_task_result(task_id="task_xxx")
```

## 质量检查

- modao_task_id 非空
- modao_preview_url 可访问
- 至少 3 个核心页面
- 交互流程完整

## 命令

```bash
python scripts/ops.py innovation:workflow-b:demo --id ID --status COMPLETED --artifacts '["path/to/demo_manifest.json"]'
```

参数说明:
- `--id`:机会 ID(必填)
- `--status`:阶段状态,可选 RUNNING/COMPLETED/FAILED/SKIPPED(默认 RUNNING)
- `--artifacts`:产物路径列表,JSON 数组格式(可选)

## 依赖

From xgl1103/ai-product-manager-employee, MIT.

More from xgl1103/ai-product-manager-employee

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 21, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from xgl1103

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get modao-demo running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying modao-demo?

CallGet help
Cite this page

modao-demo skill. Agent Mart. https://agentmart.dev/skills/xgl1103-modao-demo (last updated 2026-10-24)