Token导航 LogoToken导航

Agent Skill · 研究检索

bim-clash-detection(bim 冲突检测)

bim-clash-detection 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

bim-clash-detection 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为权限未标注;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 50,189。

总安装 624周安装 25GitHub Stars 113下载 202核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:bim-clash-detection(bim 冲突检测)
来源仓库:https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction
仓库路径:skills/bim-clash-detection
安装命令:
npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction --skill bim-clash-detection
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction --skill bim-clash-detection

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

bim-clash-detection 自动识别建筑模型中 MEP 与结构等专业间的冲突。提供优先级分类与解决建议,减少现场返工与协调成本。通过 npx skills add 安装,输入模型文件与规则集即可运行检测。支持多种 IFC 格式,需确保模型版本兼容。输出报告含冲突位置与严重等级,供团队评审与修正。

来源仓库内路径:skills/bim-clash-detection

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agent…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    权限没有明确标注,第一次使用时只给一个无关紧要的任务,观察它到底读了哪些文件和网络。

常见问题

6 条

bim-clash-detection 怎么安装?

在终端执行 npx skills add https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_const…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

bim-clash-detection 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

bim-clash-detection 需要什么权限?

权限级别没有明确标注。第一次使用时建议只给无关紧要的任务,观察它实际读写了哪些内容。

bim-clash-detection 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

bim-clash-detection 用的人多吗?

公开数据是累计安装 624 次,近一周安装 25 次,下载 202 次,GitHub 113 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

bim-clash-detection 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
bim-clash-detection

bim 冲突检测 · 本页

624113权限未标注未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

BIM Clash Detection

Business Case

Problem Statement

Coordination issues cause significant rework:

  • MEP vs structural conflicts discovered on site
  • Late design changes increase costs
  • Manual clash review is time-consuming
  • No standardized clash categorization

Solution

Automated clash detection and analysis system that identifies conflicts between building systems and provides prioritized resolution recommendations.

Business Value

  • Cost savings - Detect issues before construction
  • Time reduction - Automated clash identification
  • Better coordination - Systematic conflict resolution
  • Quality improvement - Fewer field issues

Technical Implementation

import pandas as pd
from datetime import datetime
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from enum import Enum
import math

class ClashType(Enum):
    """Types of clashes."""
    HARD = "hard"           # Physical intersection
    SOFT = "soft"           # Clearance violation
    WORKFLOW = "workflow"   # Sequencing conflict
    DUPLICATE = "duplicate" # Duplicated elements

class ClashStatus(Enum):
    """Clash resolution status."""
    NEW = "new"
    ACTIVE = "active"
    RESOLVED = "resolved"
    APPROVED = "approved"
    IGNORED = "ignored"

class ClashSeverity(Enum):
    """Clash severity level."""
    CRITICAL = "critical"
    MAJOR = "major"
    MINOR = "minor"
    INFO = "info"

class Discipline(Enum):
    """BIM disciplines."""
    ARCHITECTURAL = "architectural"
    STRUCTURAL = "structural"
    MECHANICAL = "mechanical"
    ELECTRICAL = "electrical"
    PLUMBING = "plumbing"
    FIRE_PROTECTION = "fire_protection"
    CIVIL = "civil"

@dataclass
class BoundingBox:
    """3D bounding box."""
    min_x: float
    min_y: float
    min_z: float
    max_x: float
    max_y: float
    max_z: float

    def intersects(self, other: 'BoundingBox') -> bool:
        """Check if boxes intersect."""
        return (self.min_x <= other.max_x and self.max_x >= other.min_x and
                self.min_y <= other.max_y and self.max_y >= other.min_y and
                self.min_z <= other.max_z and self.max_z >= other.min_z)

    def volume(self) -> float:
        """Calculate bounding box volume."""
        return ((self.max_x - self.min_x) *
                (self.max_y - self.min_y) *
                (self.max_z - self.min_z))

    def center(self) -> Tuple[float, float, float]:
        """Get center point."""
        return (
            (self.min_x + self.max_x) / 2,
            (self.min_y + self.max_y) / 2,
            (self.min_z + self.max_z) / 2
        )

@dataclass
class BIMElement:
    """BIM element representation."""
    element_id: str
    name: str
    discipline: Discipline
    category: str  # e.g., "Duct", "Beam", "Pipe"
    level: str
    bounding_box: BoundingBox
    properties: Dict[str, Any] = field(default_factory=dict)

    def distance_to(self, other: 'BIMElement') -> float:
        """Calculate distance between element centers."""
        c1 = self.bounding_box.center()
        c2 = other.bounding_box.center()
        return math.sqrt(
            (c2[0] - c1[0])**2 +
            (c2[1] - c1[1])**2 +
            (c2[2] - c1[2])**2
        )

@dataclass
class Clash:
    """Clash between two elements."""
    clash_id: str
    element_a: BIMElement
    element_b: BIMElement
    clash_type: ClashType
    severity: ClashSeverity
    status: ClashStatus
    distance: float  # Penetration depth (negative) or clearance gap
    location: Tuple[float, float, float]
    detected_at: datetime
    resolved_at: Optional[datetime] = None
    assigned_to: Optional[str] = None
    notes: str = ""

    def to_dict(self) -> Dict[str, Any]:
        return {
            'clash_id': self.clash_id,
            'element_a_id': self.element_a.element_id,
            'element_a_name': self.element_a.name,
            'element_a_discipline': self.element_a.discipline.value,
            'element_b_id': self.element_b.element_id,
            'element_b_name': self.element_b.name,
            'element_b_discipline': self.element_b.discipline.value,
            'clash_type': self.clash_type.value,
            'severity': self.severity.value,
            'status': self.status.value,
            'distance': round(self.distance, 3),
            'location_x': self.location[0],
            'location_y': self.location[1],
            'location_z': self.location[2],
            'level': self.element_a.level,
            'detected_at': self.detected_at.isoformat(),
            'assigned_to': self.assigned_to,
            'notes': self.notes
        }

@dataclass
class ClashTest:
    """Clash test configuration."""
    name: str
    discipline_a: Discipline
    discipline_b: Discipline
    clash_type: ClashType
    tolerance: float = 0.0  # Clearance tolerance in meters
    enabled: bool = True

class BIMClashDetector:
    """Detect and manage BIM clashes."""

    def __init__(self):
        self.elements: List[BIMElement] = []
        self.clashes: List[Clash] = []
        self.clash_tests: List[ClashTest] = []
        self._clash_counter = 0

    def load_elements(self, elements_df: pd.DataFrame) -> int:
        """Load BIM elements from DataFrame."""
        loaded = 0
        for _, row in elements_df.iterrows():
            element = BIMElement(
                element_id=str(row.get('element_id', '')),
                name=str(row.get('name', '')),
                discipline=Discipline(row.get('discipline', 'architectural')),
                category=str(row.get('category', '')),
                level=str(row.get('level', '')),
                bounding_box=BoundingBox(
                    min_x=float(row.get('min_x', 0)),
                    min_y=float(row.get('min_y', 0)),
                    min_z=float(row.get('min_z', 0)),
                    max_x=float(row.get('max_x', 0)),
                    max_y=float(row.get('max_y', 0)),
                    max_z=float(row.get('max_z', 0))
                )
            )
            self.elements.append(element)
            loaded += 1
        return loaded

    def add_clash_test(self, test: ClashTest):
        """Add clash test configuration."""
        self.clash_tests.append(test)

    def setup_standard_tests(self):
        """Setup standard MEP coordination tests."""
        standard_tests = [
            ClashTest("MEP vs Structure", Discipline.MECHANICAL, Discipline.STRUCTURAL, ClashType.HARD),
            ClashTest("Electrical vs Structure", Discipline.ELECTRICAL, Discipline.STRUCTURAL, ClashType.HARD),
            ClashTest("Plumbing vs Structure", Discipline.PLUMBING, Discipline.STRUCTURAL, ClashType.HARD),
            ClashTest("MEP vs MEP", Discipline.MECHANICAL, Discipline.ELECTRICAL, ClashType.HARD),
            ClashTest("Duct Clearance", Discipline.MECHANICAL, Discipline.MECHANICAL, ClashType.SOFT, tolerance=0.05),
            ClashTest("Fire Protection", Discipline.FIRE_PROTECTION, Discipline.STRUCTURAL, ClashType.HARD),
        ]
        for test in standard_tests:
            self.add_clash_test(test)

    def run_clash_detection(self) -> List[Clash]:
        """Run all clash tests."""
        new_clashes = []

        for test in self.clash_tests:
            if not test.enabled:
                continue

            # Filter elements by discipline
            elements_a = [e for e in self.elements if e.discipline == test.discipline_a]
            elements_b = [e for e in self.elements if e.discipline == test.discipline_b]

            # Check all pairs
            for elem_a in elements_a:
                for elem_b in elements_b:
                    if elem_a.element_id == elem_b.element_id:
                        continue

                    clash = self._check_clash(elem_a, elem_b, test)
                    if clash:
                        new_clashes.append(clash)

        self.clashes.extend(new_clashes)
        return new_clashes

    def _check_clash(self, elem_a: BIMElement, elem_b: BIMElement,
                     test: ClashTest) -> Optional[Clash]:
        """Check if two elements clash."""

        # Expand bounding box by tolerance for soft clashes
        box_a = elem_a.bounding_box
        box_b = elem_b.bounding_box

        if test.clash_type == ClashType.SOFT:
            # Add clearance tolerance
            expanded_a = BoundingBox(
                box_a.min_x - test.tolerance, box_a.min_y - test.tolerance, box_a.min_z - test.tolerance,
                box_a.max_x + test.tolerance, box_a.max_y + test.tolerance, box_a.max_z + test.tolerance
            )
            intersects = expanded_a.intersects(box_b)
        else:
            intersects = box_a.intersects(box_b)

        if not intersects:
            return None

        # Calculate clash point and severity
        self._clash_counter += 1
        clash_id = f"CLH-{self._clash_counter:05d}"

        # Clash location (center of intersection)
        location = (
            (max(box_a.min_x, box_b.min_x) + min(box_a.max_x, box_b.max_x)) / 2,
            (max(box_a.min_y, box_b.min_y) + min(box_a.max_y, box_b.max_y)) / 2,
            (max(box_a.min_z, box_b.min_z) + min(box_a.max_z, box_b.max_z)) / 2
        )

        # Calculate penetration depth
        distance = elem_a.distance_to(elem_b)

        # Determine severity
        if test.clash_type == ClashType.HARD:
            severity = ClashSeverity.CRITICAL if distance < 0.1 else ClashSeverity.MAJOR
        else:
            severity = ClashSeverity.MINOR if distance > test.tolerance else ClashSeverity.MAJOR

        return Clash(
            clash_id=clash_id,
            element_a=elem_a,
            element_b=elem_b,
            clash_type=test.clash_type,
            severity=severity,
            status=ClashStatus.NEW,
            distance=distance,
            location=location,
            detected_at=datetime.now()
        )

    def get_summary(self) -> Dict[str, Any]:
        """Get clash detection summary."""
        by_severity = {}
        by_discipline = {}
        by_status = {}

        for clash in self.clashes:
            # By severity
            sev = clash.severity.value
            by_severity[sev] = by_severity.get(sev, 0) + 1

            # By discipline pair
            pair = f"{clash.element_a.discipline.value} vs {clash.element_b.discipline.value}"
            by_discipline[pair] = by_discipline.get(pair, 0) + 1

            # By status
            stat = clash.status.value
            by_status[stat] = by_status.get(stat, 0) + 1

        return {
            'total_clashes': len(self.clashes),
            'by_severity': by_severity,
            'by_discipline': by_discipline,
            'by_status': by_status,
            'elements_checked': len(self.elements),
            'tests_run': len([t for t in self.clash_tests if t.enabled])
        }

    def export_to_dataframe(self) -> pd.DataFrame:
        """Export clashes to DataFrame."""
        return pd.DataFrame([c.to_dict() for c in self.clashes])

    def resolve_clash(self, clash_id: str, resolution_note: str):
        """Mark clash as resolved."""
        for clash in self.clashes:
            if clash.clash_id == clash_id:
                clash.status = ClashStatus.RESOLVED
                clash.resolved_at = datetime.now()
                clash.notes = resolution_note
                break

    def assign_clash(self, clash_id: str, assignee: str):
        """Assign clash to team member."""
        for clash in self.clashes:
            if clash.clash_id == clash_id:
                clash.assigned_to = assignee
                clash.status = ClashStatus.ACTIVE
                break

Quick Start

# Initialize detector
detector = BIMClashDetector()

# Setup standard MEP tests
detector.setup_standard_tests()

# Load elements from DataFrame
elements_df = pd.read_excel("bim_elements.xlsx")
detector.load_elements(elements_df)

# Run detection
clashes = detector.run_clash_detection()
print(f"Found {len(clashes)} clashes")

# Get summary
summary = detector.get_summary()
print(f"Critical: {summary['by_severity'].get('critical', 0)}")

Common Use Cases

1. MEP Coordination

# Focus on MEP vs Structure
mep_clashes = [c for c in detector.clashes
               if c.element_a.discipline in [Discipline.MECHANICAL, Discipline.ELECTRICAL]]

2. Export for Review

df = detector.export_to_dataframe()
df.to_excel("clash_report.xlsx", index=False)

3. Assign to Teams

for clash in detector.clashes:
    if clash.element_a.discipline == Discipline.MECHANICAL:
        detector.assign_clash(clash.clash_id, "MEP Team")

Resources

  • DDC Book: Chapter 2.4 - BIM Coordination
  • Reference: ISO 19650 BIM Standards

平台分布

Codex

36.89%
按下载量换算75

Claude

26.79%
按下载量换算54

Cursor

17.36%
按下载量换算35

Gemini CLI

9.43%
按下载量换算19

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限未标注

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills