DDC_Skills_for_AI_Agents_in_Construction MCP — 使用场景, 安装 & 实时演示

为什么要用

核心特性

Breadth: 221 sub-skills across the construction lifecycle
BIM data handling (IFC parsing, Revit exports, model audits)
Cost estimation templates and WBS conventions
Scheduling helpers (P6/MS Project-adjacent)
Document control: submittals, RFIs, change orders

实时演示

实际使用效果

ddc-skills-for-ai-agents-in-construction-skill.replay ▶ 就绪

0/0

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "ddc-skills-for-ai-agents-in-construction-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
        "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "ddc-skills-for-ai-agents-in-construction-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction",
          "~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add ddc-skills-for-ai-agents-in-construction-skill -- git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction ~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： DDC_Skills_for_AI_Agents_in_Construction

How to audit a BIM IFC model for basic data quality

👤 BIM coordinators and VDC teams ⏱ ~60 min advanced

何时使用： You receive an IFC file from a consultant and need a quality check.

前置条件

Python with ifcopenshell — pip install ifcopenshell
Skill cloned — git clone https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction ~/.claude/skills/DDC_Skills_for_AI_Agents_in_Construction

步骤

Parse the IFC

Audit model.ifc — count entities by class, find missing Psets, flag orphan geometry.✓ 已复制

→ Entity counts + quality flags
Check naming and classification

Verify wall and room naming against our company standard.✓ 已复制

→ Per-element conformance report
Produce a coordinator-ready report

Generate an issue list the consultant can act on.✓ 已复制

→ Ordered issue list

结果： A model audit report you can send back in under an hour.

注意事项

Huge IFC files exceed memory — Stream-parse rather than load full tree; or pre-filter by spatial structure

搭配使用： filesystem

Produce a quick order-of-magnitude cost estimate

👤 Estimators, PMs, bid teams ⏱ ~30 min intermediate

何时使用： Early-phase numbers for a concept before you commit to a detailed estimate.

步骤

Describe the project

Concrete frame office, ~12,000 sqm, Tier-1 city, shell-only. Give me a per-sqm cost range.✓ 已复制

→ Range with the assumptions stated
Break into WBS

Break the estimate into WBS sections with % allocations.✓ 已复制

→ Top-level WBS with line items
Flag risks

List the top 5 cost risks for this concept.✓ 已复制

→ Risks with impact

结果： A defensible concept estimate ready for internal review.

注意事项

Using global averages without local adjustment — Always override with local benchmarks when you have them

Review a construction schedule for common issues

👤 Schedulers and PMs ⏱ ~30 min intermediate

何时使用： You got a schedule from a subcontractor and need to check for the obvious red flags.

步骤

Feed the schedule

Review schedule.xlsx — flag missing logic, negative float, open ends, and unrealistic durations.✓ 已复制

→ Categorized findings
Prioritize

Rank by impact on completion date.✓ 已复制

→ Sorted list

结果： Quick surface-level schedule review that catches 80% of common problems.

注意事项

Missing CPM-level analysis — For real float analysis, export from P6 rather than relying on Excel

组合

与其他 MCP 搭配，撬动十倍杠杆

ddc-skills-for-ai-agents-in-construction-skill + filesystem

Process a whole project folder of IFCs, schedules, and docs

Walk project/ and produce a weekly coordination packet.✓ 已复制

工具

此 MCP 暴露的能力

工具	输入参数	何时调用	成本
bim-audit	IFC path	On any incoming IFC	ifcopenshell compute
cost-estimation	project concept	Early phase	0
schedule-review	schedule export	Sub-submittal review	0
document-control	RFIs/submittals/COs	Project admin	0

成本与限制

运行它的成本

API 配额: none
每次调用 Token 数: 5–30k per task
费用: free at skill level
提示: Use only the sub-skills relevant to your role — this bundle is wide

安全

权限、密钥、影响范围

凭据存储： none

数据出站： none

Construction estimates and schedules are often confidential — handle like other sensitive project data

故障排查

常见错误与修复

ifcopenshell install fails

Use Python 3.10 or 3.11 and pip install ifcopenshell from a wheel matching your platform.

验证： python -c 'import ifcopenshell; print(ifcopenshell.version)'

Estimates are wildly off

Override unit costs with your regional database; the skill uses generic benchmarks only

替代方案

DDC_Skills_for_AI_Agents_in_Construction 对比其他方案

替代方案	何时用它替代	权衡
generic csv-data-summarizer-claude-skill	Your construction data is CSV and you don't need BIM semantics	No domain knowledge

DDC_Skills_for_AI_Agents_in_Construction

为什么要用

核心特性

实时演示

实际使用效果

安装

选择你的客户端

使用场景

实战用法： DDC_Skills_for_AI_Agents_in_Construction

How to audit a BIM IFC model for basic data quality

前置条件

步骤

注意事项

Produce a quick order-of-magnitude cost estimate

步骤

注意事项

Review a construction schedule for common issues

步骤

注意事项

组合

与其他 MCP 搭配，撬动十倍杠杆

工具

此 MCP 暴露的能力

成本与限制

运行它的成本

安全

权限、密钥、影响范围

故障排查

常见错误与修复

替代方案

DDC_Skills_for_AI_Agents_in_Construction 对比其他方案

更多

资源