clash-resolution-analyzer

clash-resolution-analyzer is a skill for Claude Code, Codex from jdmorag97-rgb/DDC_Skills_for_AI_Agents_in_Construction. It costs 30 tokens per session (3,875 once invoked), scanned A, a copy of clash-resolution-analyzer, MIT.

A tool for analyzing BIM clash-detection results, where a clash means that building elements or systems occupy conflicting spaces. It prioritizes clashes, identifies patterns, suggests resolutions and tracks progress.

In plain words
What is it for?
Use it to rank clashes by impact, assign responsibility by trade, monitor resolution status and support coordination.
Why use it?
It helps teams focus on the most important conflicts and identify repeated causes instead of handling every clash equally.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to rank clashes by impact, assign responsibility by trade, monitor resolution status and support coordination.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add jdmorag97-rgb/DDC_Skills_for_AI_Agents_in_Construction --skill clash-resolution-analyzer
Clone the repo
git clone --depth 1 https://github.com/jdmorag97-rgb/DDC_Skills_for_AI_Agents_in_Construction

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for clash-resolution-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer/github.svg)](https://agentmods.dev/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer)
Your own site
<a href="https://agentmods.dev/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer"><img src="https://agentmods.dev/badge/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for clash-resolution-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer"><img src="https://agentmods.dev/badge/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/clash-resolution-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.03875
Opus 5 $0.00015 $0.01937
Sonnet 5 $0.00006 $0.00775
Haiku 4.5 $0.00003 $0.00387

Measured 8d ago against content hash 773729ac2877, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

clash-resolution-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to clash-resolution-analyzer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

2_DDC_Book/4.3-BIM-Validation-Pipeline/clash-resolution-analyzer/SKILL.md · 476 lines

How it starts

The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clash Resolution Analyzer for Construction

Overview

Analyze clash detection results from BIM coordination. Prioritize clashes by impact, identify patterns, suggest resolutions, assign responsibility, and track resolution progress.

Business Case

Clash resolution analysis enables:

  • Efficient Coordination: Focus on critical clashes first
  • Pattern Recognition: Fix root causes, not symptoms
  • Clear Accountability: Assign responsibility by trade
  • Progress Tracking: Monitor resolution status

Technical Implementation

from dataclasses import dataclass, field
from typing import List, Dict, Any, Optional, Tuple
from enum import Enum
from datetime import datetime
from collections import defaultdict

class ClashPriority(Enum):
    CRITICAL = 1  # Must resolve before construction
    HIGH = 2      # Resolve in next coordination cycle
    MEDIUM = 3    # Resolve before trade starts
    LOW = 4       # Minor, can resolve in field

class ClashStatus(Enum):
    NEW = "new"
    ASSIGNED = "assigned"
    IN_PROGRESS = "in_progress"
    RESOLVED = "resolved"
    APPROVED = "approved"
    VOID = "void"  # Not a real clash

class ResolutionType(Enum):
    ROUTE_AROUND = "Route around obstruction"
    RAISE_LOWER = "Raise or lower element"
    RESIZE = "Resize element"
    RELOCATE = "Relocate element"
    STRUCTURAL_MOD = "Structural modification required"
    DESIGN_CHANGE = "Design change required"
    NO_CLASH = "Not a real clash (tolerance)"
    SEQUENCE = "Resolve by construction sequence"

@dataclass
class ClashElement:
    id: str
    name: str
    category: str
    discipline: str
    level: str
    system: str

@dataclass
class Clash:
    id: str
    name: str
    element1: ClashElement
    element2: ClashElement
    location: Tuple[float, float, float]
    distance: float  # Negative = hard clash, positive = clearance violation
    clash_type: str  # hard, clearance, duplicate
    priority: ClashPriority = ClashPriority.MEDIUM
    status: ClashStatus = ClashStatus.NEW
    assigned_to: str = ""
    resolution_type: Optional[ResolutionType] = None
    resolution_notes: str = ""
    created_date: datetime = field(default_factory=datetime.now)
    resolved_date: Optional[datetime] = None

@dataclass
class ClashPattern:
    pattern_type: str
    disciplines: Tuple[str, str]
    systems: Tuple[str, str]
    clash_count: int
    example_clashes: List[str]
    suggested_resolution: str
    root_cause: str

@dataclass
class ClashReport:
    report_name: str
    total_clashes: int
    new_clashes: int
    resolved_clashes: int
    clashes_by_priority: Dict[str, int]
    clashes_by_discipline: Dict[str, int]
    clashes_by_status: Dict[str, int]
    patterns: List[ClashPattern]
    resolution_rate: float

class ClashResolutionAnalyzer:
    """Analyze and manage BIM clash detection results."""

    # Discipline priority for resolution responsibility
    DISCIPLINE_PRIORITY = {
        'Structural': 1,
        'Architectural': 2,
        'Mechanical': 3,
        'Plumbing': 4,
        'Electrical': 5,
        'Fire Protection': 6,
    }

    # Common resolution strategies by clash type
    RESOLUTION_STRATEGIES = {
        ('Mechanical', 'Structural'): {
            'strategy': ResolutionType.ROUTE_AROUND,
            'responsible': 'Mechanical',
            'notes': 'MEP typically routes around structure'
        },
        ('Plumbing', 'Structural'): {
            'strategy': ResolutionType.ROUTE_AROUND,
            'responsible': 'Plumbing',
            'notes': 'Coordinate sleeves/penetrations with SE'
        },
        ('Electrical', 'Mechanical'): {
            'strategy': ResolutionType.RAISE_LOWER,
            'responsible': 'Electrical',
            'notes': 'Conduit typically more flexible than ductwork'
        },
        ('Mechanical', 'Mechanical'): {
            'strategy': ResolutionType.RESIZE,
            'responsible': 'Mechanical',
            'notes': 'Review duct sizing and routing options'
        },
        ('Fire Protection', 'Mechanical'): {
            'strategy': ResolutionType.ROUTE_AROUND,
            'responsible': 'Fire Protection',
            'notes': 'Sprinkler typically routes around major duct'
        },
    }

    def __init__(self):
        self.clashes: Dict[str, Clash] = {}
        self.patterns: List[ClashPattern] = []
        self.history: List[Dict] = []

    def import_clashes(self, clash_data: List[Dict]) -> int:
        """Import clashes from Navisworks or other clash detection software."""
        count = 0

        for data in clash_data:
            clash = Clash(
                id=data.get('id', f'CLH-{count}'),
                name=data.get('name', ''),
                element1=ClashElement(
                    id=data.get('element1_id', ''),
                    name=data.get('element1_name', ''),
                    category=data.get('element1_category', ''),
                    discipline=data.get('element1_discipline', ''),
                    level=data.get('element1_level', ''),
                    system=data.get('element1_system', '')
                ),
                element2=ClashElement(
                    id=data.get('element2_id', ''),
                    name=data.get('element2_name', ''),
                    category=data.get('element2_category', ''),
                    discipline=data.get('element2_discipline', ''),
                    level=data.get('element2_level', ''),
                    system=data.get('element2_system', '')
                ),
                location=(
                    data.get('x', 0),
                    data.get('y', 0),
                    data.get('z', 0)
                ),
                distance=data.get('distance', 0),
                clash_type=data.get('clash_type', 'hard')
            )

            # Auto-prioritize
            clash.priority = self._auto_prioritize(clash)

            # Auto-assign
            clash.assigned_to = self._auto_assign(clash)

            self.clashes[clash.id] = clash
            count += 1

        return count

    def _auto_prioritize(self, clash: Clash) -> ClashPriority:
        """Automatically prioritize clash based on characteristics."""
        # Hard clashes with structure are critical
        if clash.element1.discipline == 'Structural' or clash.element2.discipline == 'Structural':
            if clash.clash_type == 'hard':
                return ClashPriority.CRITICAL

        # Large penetration clashes
        if abs(clash.distance) > 0.1:  # More than 100mm overlap
            return ClashPriority.HIGH

        # MEP-MEP clashes
        mep_disciplines = ['Mechanical', 'Electrical', 'Plumbing', 'Fire Protection']
        if clash.element1.discipline in mep_disciplines and clash.element2.discipline in mep_disciplines:
            return ClashPriority.MEDIUM

        # Clearance violations
        if clash.clash_type == 'clearance':
            return ClashPriority.LOW

        return ClashPriority.MEDIUM

    def _auto_assign(self, clash: Clash) -> str:
        """Automatically assign responsibility based on discipline priority."""
        d1 = clash.element1.discipline
        d2 = clash.element2.discipline

        # Check for known resolution strategy
        key = (d1, d2) if (d1, d2) in self.RESOLUTION_STRATEGIES else (d2, d1)
        if key in self.RESOLUTION_STRATEGIES:
            return self.RESOLUTION_STRATEGIES[key]['responsible']

        # Default to lower priority discipline (typically more flexible)
        p1 = self.DISCIPLINE_PRIORITY.get(d1, 10)
        p2 = self.DISCIPLINE_PRIORITY.get(d2, 10)

        return d2 if p2 > p1 else d1

    def analyze_patterns(self) -> List[ClashPattern]:
        """Identify patterns in clashes."""
        patterns = []

        # Group by discipline pair
        discipline_pairs = defaultdict(list)
        for clash in self.clashes.values():
            pair = tuple(sorted([clash.element1.discipline, clash.element2.discipline]))
            discipline_pairs[pair].append(clash)

        for (d1, d2), clashes in discipline_pairs.items():
            if len(clashes) >= 3:  # Pattern threshold
                # Further group by system
                system_pairs = defaultdict(list)
                for clash in clashes:
                    sys_pair = tuple(sorted([clash.element1.system, clash.element2.system]))
                    system_pairs[sys_pair].append(clash)

                for (s1, s2), sys_clashes in system_pairs.items():
                    if len(sys_clashes) >= 2:
                        # Get resolution strategy
                        key = (d1, d2) if (d1, d2) in self.RESOLUTION_STRATEGIES else (d2, d1)
                        strategy = self.RESOLUTION_STRATEGIES.get(key, {})

                        patterns.append(ClashPattern(
                            pattern_type=f"{d1} vs {d2}",
                            disciplines=(d1, d2),
                            systems=(s1, s2),
                            clash_count=len(sys_clashes),
                            example_clashes=[c.id for c in sys_clashes[:3]],
                            suggested_resolution=strategy.get('strategy', ResolutionType.ROUTE_AROUND).value,
                            root_cause=f"Coordination needed between {s1} and {s2} systems"
                        ))

        self.patterns = sorted(patterns, key=lambda p: -p.clash_count)
        return self.patterns

    def suggest_resolution(self, clash_id: str) -> Dict:
        """Suggest resolution for a specific clash."""
        if clash_id not in self.clashes:
            return {'error': 'Clash not found'}

        clash = self.clashes[clash_id]
        d1, d2 = clash.element1.discipline, clash.element2.discipline

        # Get strategy
        key = (d1, d2) if (d1, d2) in self.RESOLUTION_STRATEGIES else (d2, d1)
        strategy = self.RESOLUTION_STRATEGIES.get(key, {})

        suggestion = {
            'clash_id': clash_id,
            'resolution_type': strategy.get('strategy', ResolutionType.ROUTE_AROUND),
            'responsible_discipline': strategy.get('responsible', self._auto_assign(clash)),
            'notes': strategy.get('notes', 'Review and coordinate'),
            'similar_clashes': [],
        }

        # Find similar clashes
        for pattern in self.patterns:
            if d1 in pattern.disciplines and d2 in pattern.disciplines:
                suggestion['similar_clashes'] = pattern.example_clashes
                suggestion['pattern_root_cause'] = pattern.root_cause
                break

        return suggestion

    def update_clash_status(self, clash_id: str, status: ClashStatus,
                            resolution_type: ResolutionType = None,
                            notes: str = "") -> bool:
        """Update clash status."""
        if clash_id not in self.clashes:
            return False

        clash = self.clashes[clash_id]
        old_status = clash.status

        clash.status = status
        if resolution_type:
            clash.resolution_type = resolution_type
        if notes:
            clash.resolution_notes = notes
        if status in [ClashStatus.RESOLVED, ClashStatus.APPROVED]:
            clash.resolved_date = datetime.now()

        # Track history
        self.history.append({
            'clash_id': clash_id,
            'timestamp': datetime.now(),
            'old_status': old_status.value,
            'new_status': status.value,
            'notes': notes
        })

        return True

    def get_clashes_by_discipline(self, discipline: str) -> List[Clash]:
        """Get all clashes assigned to a discipline."""
        return [c for c in self.clashes.values() if c.assigned_to == discipline]

    def get_clashes_by_level(self, level: str) -> List[Clash]:
        """Get all clashes on a specific level."""
        return [c for c in self.clashes.values()
                if c.element1.level == level or c.element2.level == level]

    def generate_coordination_matrix(self) -> Dict[str, Dict[str, int]]:
        """Generate matrix showing clashes between disciplines."""
        matrix = defaultdict(lambda: defaultdict(int))

        for clash in self.clashes.values():
            d1 = clash.element1.discipline
            d2 = clash.element2.discipline
            matrix[d1][d2] += 1
            if d1 != d2:
                matrix[d2][d1] += 1

        return dict(matrix)

    def generate_report(self) -> ConsistencyReport:
        """Generate comprehensive clash analysis report."""
        clashes_by_priority = defaultdict(int)
        clashes_by_discipline = defaultdict(int)
        clashes_by_status = defaultdict(int)

        for clash in self.clashes.values():
            clashes_by_priority[clash.priority.name] += 1
            clashes_by_discipline[clash.assigned_to] += 1
            clashes_by_status[clash.status.value] += 1

        resolved = clashes_by_status.get('resolved', 0) + clashes_by_status.get('approved', 0)
        resolution_rate = resolved / len(self.clashes) * 100 if self.clashes else 0

        return ClashReport(
            report_name=f"Clash Report {datetime.now().strftime('%Y-%m-%d')}",
            total_clashes=len(self.clashes),
            new_clashes=clashes_by_status.get('new', 0),
            resolved_clashes=resolved,
            clashes_by_priority=dict(clashes_by_priority),
            clashes_by_discipline=dict(clashes_by_discipline),
            clashes_by_status=dict(clashes_by_status),
            patterns=self.patterns,
            resolution_rate=resolution_rate
        )

    def generate_report_markdown(self) -> str:
        """Generate markdown report."""
        report = self.generate_report()

        lines = ["# Clash Resolution Report", ""]
        lines.append(f"**Date:** {datetime.now().strftime('%Y-%m-%d')}")
        lines.append(f"**Total Clashes:** {report.total_clashes}")
        lines.append(f"**Resolution Rate:** {report.resolution_rate:.1f}%")
        lines.append("")

        # By status
        lines.append("## Status Summary")
        for status, count in report.clashes_by_status.items():
            lines.append(f"- {status}: {count}")
        lines.append("")

        # By priority
        lines.append("## Priority Breakdown")
        for priority, count in sorted(report.clashes_by_priority.items()):
            lines.append(f"- {priority}: {count}")
        lines.append("")

        # By discipline
        lines.append("## By Responsible Discipline")
        for disc, count in sorted(report.clashes_by_discipline.items(), key=lambda x: -x[1]):
            lines.append(f"- {disc}: {count}")
        lines.append("")

        # Patterns
        if report.patterns:
            lines.append("## Clash Patterns Identified")
            for pattern in report.patterns[:5]:
                lines.append(f"\n### {pattern.pattern_type}")
                lines.append(f"- **Count:** {pattern.clash_count} clashes")
                lines.append(f"- **Systems:** {pattern.systems[0]} vs {pattern.systems[1]}")
                lines.append(f"- **Root Cause:** {pattern.root_cause}")
                lines.append(f"- **Suggested Resolution:** {pattern.suggested_resolution}")

        # Critical clashes
        critical = [c for c in self.clashes.values() if c.priority == ClashPriority.CRITICAL and c.status == ClashStatus.NEW]
        if critical:
            lines.append("\n## Critical Unresolved Clashes")
            for clash in critical[:10]:
                lines.append(f"- **{clash.id}**: {clash.element1.name} vs {clash.element2.name}")
                lines.append(f"  - Location: Level {clash.element1.level}")
                lines.append(f"  - Assigned: {clash.assigned_to}")

        return "\n".join(lines)

Read the full file on GitHub · 476 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 476 lines · 30 tokens per session scan A 773729ac2877

Subscribe to this mod's changes

clash-resolution-analyzer is a skill published in the GitHub repository jdmorag97-rgb/DDC_Skills_for_AI_Agents_in_Construction (2 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 3,875 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to clash-resolution-analyzer, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systemic-issue-triage

Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.

Gentleman-Programming/gentle-ai · 57 tokens

triage-issue

Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…

atlassian/atlassian-mcp-server · 116 tokens

bug-triage

Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

Donchitos/Claude-Code-Game-Studios · 59 tokens

browse-flows

Browse Power Automate environments and flows interactively. Use when the user wants to browse, list, or explore their flows and environments.

microsoft/power-platform-skills · 31 tokens

operating-cadence

Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…

cbrock84/headcount · 95 tokens

status

Display current FIRE project status and validate integrity of intents, work items, and runs.

fabriqaai/specs.md · 19 tokens