{"id":"2228c7c2-72c7-4081-95ee-394299858159","entityType":"agent","slug":"clawhub-datadrivenconstruction-bim-cost-estimation-cwicr","name":"Bim Cost Estimation Cwicr","canonicalUrl":"https://www.xpersona.co/agent/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr","canonicalPath":"/agent/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr","generatedAt":"2026-10-11T04:35:39.934Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T02:18:00.692Z","emptyReason":null},"description":"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing. Skill: Bim Cost Estimation Cwicr Owner: datadrivenconstruction Summary: Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing. Tags: latest:2.1.0 Version history: v2.1.0 | 2026-02-13T21:08:30.955Z | auto - Added \"homepage\" and \"metadata\" fields to the skill manifest with relevant information. - Specified platform compatibility","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s1774mv3t1cm8r1kgs9hccdnmn8852nb:bim-cost-estimation-cwicr","sourceUrl":"https://clawhub.ai/datadrivenconstruction/bim-cost-estimation-cwicr","homepage":"https://clawhub.ai/datadrivenconstruction/skills/bim-cost-estimation-cwicr","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/datadrivenconstruction/bim-cost-estimation-cwicr","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/datadrivenconstruction/skills/bim-cost-estimation-cwicr","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing. Skill: Bim Co"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T02:18:00.692Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T02:18:00.692Z","emptyReason":null},"stars":null,"forks":null,"downloads":1192,"packageName":null,"latestVersion":"2.1.0","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T02:18:00.627Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T02:18:00.692Z","lastCrawledAt":"2026-10-11T02:18:00.627Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T02:18:00.627Z","lastVerifiedAt":null,"highlights":[{"version":"2.1.0","createdAt":"2026-02-13T21:08:30.955Z","changelog":"- Added \"homepage\" and \"metadata\" fields to the skill manifest with relevant information. - Specified platform compatibility (Darwin, Linux, Win32) and required environment variables in metadata. - No changes to Python code or estimation logic.","fileCount":4,"zipByteSize":8043},{"version":"2.0.0","createdAt":"2026-02-13T15:22:53.595Z","changelog":"**Major upgrade: Seamlessly automate BIM cost estimation using AI and an extensive construction cost database.** - Adds end-to-end pipeline for automated cost estimation from BIM models using DDC CWICR (55,719 work items, 9 global regions). - Enables AI classification of BIM elements and vector search for precise work item and rate matching. - Supports multi-language cost data and pricing from major world cities. - Provides detailed process breakdown and a clear Python implementation for real-world integration. - Delivers estimates in hours with consistent methodology, reducing manual effort by up to 80%.","fileCount":4,"zipByteSize":7895},{"version":"1.0.0","createdAt":"2026-02-07T14:34:46.541Z","changelog":"BIM Cost Estimation CWICR 1.0.0 - Initial release of automated BIM-to-cost estimation using the DDC CWICR database. - Supports AI classification and vector search for accurate mapping of BIM elements to 55,719 work items with localized pricing in 9 languages. - Pipeline includes quantity takeoff extraction, phase/trade mapping, multi-stage decomposition, and rapid cost reporting. - Integration examples provided for OpenAI embeddings and Qdrant vector search. - Outputs detailed estimates by element, trade, and phase, exportable to HTML and Excel.","fileCount":2,"zipByteSize":6267}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1774mv3t1cm8r1kgs9hccdnmn8852nb:bim-cost-estimation-cwicr","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T04:35:39.934Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-datadrivenconstruction-bim-cost-estimation-cwicr/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T02:18:00.692Z","emptyReason":null},"readme":"Skill: Bim Cost Estimation Cwicr\n\nOwner: datadrivenconstruction\n\nSummary: Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\n\nTags: latest:2.1.0\n\nVersion history:\n\nv2.1.0 | 2026-02-13T21:08:30.955Z | auto\n\n- Added \"homepage\" and \"metadata\" fields to the skill manifest with relevant information.\n- Specified platform compatibility (Darwin, Linux, Win32) and required environment variables in metadata.\n- No changes to Python code or estimation logic.\n\nv2.0.0 | 2026-02-13T15:22:53.595Z | auto\n\n**Major upgrade: Seamlessly automate BIM cost estimation using AI and an extensive construction cost database.**\n\n- Adds end-to-end pipeline for automated cost estimation from BIM models using DDC CWICR (55,719 work items, 9 global regions).\n- Enables AI classification of BIM elements and vector search for precise work item and rate matching.\n- Supports multi-language cost data and pricing from major world cities.\n- Provides detailed process breakdown and a clear Python implementation for real-world integration.\n- Delivers estimates in hours with consistent methodology, reducing manual effort by up to 80%.\n\nv1.0.0 | 2026-02-07T14:34:46.541Z | auto\n\nBIM Cost Estimation CWICR 1.0.0\n\n- Initial release of automated BIM-to-cost estimation using the DDC CWICR database.\n- Supports AI classification and vector search for accurate mapping of BIM elements to 55,719 work items with localized pricing in 9 languages.\n- Pipeline includes quantity takeoff extraction, phase/trade mapping, multi-stage decomposition, and rapid cost reporting.\n- Integration examples provided for OpenAI embeddings and Qdrant vector search.\n- Outputs detailed estimates by element, trade, and phase, exportable to HTML and Excel.\n\nArchive index:\n\nArchive v2.1.0: 4 files, 8043 bytes\n\nFiles: claw.json (531b), instructions.md (2154b), SKILL.md (21197b), _meta.json (144b)\n\nFile v2.1.0:SKILL.md\n\n---\r\nname: \"bim-cost-estimation-cwicr\"\r\ndescription: \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\"\r\nhomepage: \"https://datadrivenconstruction.io\"\r\nmetadata: {\"openclaw\":{\"emoji\":\"πŸ—οΈ\",\"os\":[\"darwin\",\"linux\",\"win32\"],\"homepage\":\"https://datadrivenconstruction.io\",\"requires\":{\"bins\":[\"python3\"],\"env\":[\"OPENAI_API_KEY\",\"QDRANT_URL\"]},\"primaryEnv\":\"OPENAI_API_KEY\"}}\r\n---\r\n\r\n# BIM Cost Estimation with DDC CWICR\r\n\r\nGenerate accurate cost estimates from BIM models using AI classification and the DDC CWICR construction cost database.\r\n\r\n## Business Case\r\n\r\n**Problem**: Traditional cost estimation:\r\n- Manual and time-consuming (weeks for detailed estimate)\r\n- Subjective and inconsistent between estimators\r\n- Requires specialized knowledge\r\n- Difficult to update with design changes\r\n\r\n**Solution**: Automated BIM-to-cost pipeline:\r\n- Extract quantities directly from model\r\n- AI classifies elements to work items\r\n- Vector search finds matching prices in CWICR\r\n- Complete estimate in hours, not weeks\r\n\r\n**ROI**: 80% reduction in estimation time, consistent methodology\r\n\r\n## System Architecture\r\n\r\n```\r\nβ”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”\r\nβ”‚ BIM TO COST ESTIMATION PIPELINE β”‚\r\nβ”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€\r\nβ”‚ β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ BIM β”‚ β”‚ DDC β”‚ β”‚ AI β”‚ β”‚ DDC CWICR β”‚ β”‚\r\nβ”‚ β”‚ Model │────►│Converter│────►│ LLM │────►│ Vector Search β”‚ β”‚\r\nβ”‚ β”‚.rvt/.ifcβ”‚ β”‚ β”‚ β”‚ β”‚ β”‚ (Qdrant) β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β–Ό β–Ό β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ .xlsx β”‚ β”‚ Work β”‚ β”‚ Matched β”‚ β”‚\r\nβ”‚ β”‚ QTO β”‚ β”‚ Items β”‚ β”‚ Rates β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ COST ESTIMATE β”‚ β”‚\r\nβ”‚ β”‚ β”‚ β”‚\r\nβ”‚ β”‚ β€’ By element β”‚ β”‚\r\nβ”‚ β”‚ β€’ By trade β”‚ β”‚\r\nβ”‚ β”‚ β€’ By phase β”‚ β”‚\r\nβ”‚ β”‚ β€’ Resources β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚\r\nβ””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜\r\n```\r\n\r\n## DDC CWICR Database\r\n\r\n```yaml\r\nDatabase Overview:\r\n work_items: 55,719\r\n resources: 27,672\r\n languages: 9 (AR, DE, EN, ES, FR, HI, PT, RU, ZH)\r\n fields_per_item: 85\r\n embedding_model: text-embedding-3-large (3072d)\r\n vector_db: Qdrant\r\n\r\nCollections:\r\n - ddc_cwicr_ar # Arabic (Dubai prices)\r\n - ddc_cwicr_de # German (Berlin prices)\r\n - ddc_cwicr_en # English (Toronto prices)\r\n - ddc_cwicr_es # Spanish (Barcelona prices)\r\n - ddc_cwicr_fr # French (Paris prices)\r\n - ddc_cwicr_hi # Hindi (Mumbai prices)\r\n - ddc_cwicr_pt # Portuguese (SΓ£o Paulo prices)\r\n - ddc_cwicr_ru # Russian (St. Petersburg prices)\r\n - ddc_cwicr_zh # Chinese (Shanghai prices)\r\n```\r\n\r\n## Pipeline Stages\r\n\r\n| Stage | Name | Description |\r\n|-------|------|-------------|\r\n| 0 | Collect BIM Data | Extract elements from Revit/IFC |\r\n| 1 | Project Detection | AI identifies project type |\r\n| 2 | Phase Generation | AI creates construction phases |\r\n| 3 | Element Assignment | AI maps types to phases |\r\n| 4 | Work Decomposition | AI breaks types into work items |\r\n| 5 | Vector Search | Find matching rates in CWICR |\r\n| 6 | Unit Mapping | Convert BIM units to rate units |\r\n| 7 | Cost Calculation | Qty Γ— Unit Price |\r\n| 7.5 | Validation | CTO review for completeness |\r\n| 8 | Aggregation | Sum by phases and categories |\r\n| 9 | Report Generation | HTML and Excel outputs |\r\n\r\n## Python Implementation\r\n\r\n```python\r\nimport pandas as pd\r\nimport numpy as np\r\nfrom qdrant_client import QdrantClient\r\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue\r\nfrom openai import OpenAI\r\nfrom typing import List, Dict, Optional\r\nfrom dataclasses import dataclass\r\nimport json\r\n\r\n@dataclass\r\nclass WorkItem:\r\n \"\"\"Matched work item from CWICR\"\"\"\r\n cwicr_code: str\r\n description: str\r\n unit: str\r\n unit_price: float\r\n labor_cost: float\r\n material_cost: float\r\n equipment_cost: float\r\n productivity: float # units per hour\r\n currency: str\r\n confidence: float\r\n\r\n@dataclass\r\nclass CostLineItem:\r\n \"\"\"Single line item in estimate\"\"\"\r\n bim_type: str\r\n work_item: WorkItem\r\n quantity: float\r\n quantity_unit: str\r\n total_cost: float\r\n labor_cost: float\r\n material_cost: float\r\n equipment_cost: float\r\n phase: str\r\n trade: str\r\n\r\n\r\nclass BIMCostEstimator:\r\n \"\"\"BIM to cost estimation using DDC CWICR\"\"\"\r\n\r\n def __init__(\r\n self,\r\n qdrant_url: str,\r\n qdrant_api_key: str = None,\r\n openai_api_key: str = None,\r\n language: str = \"EN\"\r\n ):\r\n self.qdrant = QdrantClient(url=qdrant_url, api_key=qdrant_api_key)\r\n self.openai = OpenAI(api_key=openai_api_key)\r\n self.language = language\r\n self.collection = f\"ddc_cwicr_{language.lower()}\"\r\n\r\n def get_embedding(self, text: str) -> List[float]:\r\n \"\"\"Generate embedding for text\"\"\"\r\n response = self.openai.embeddings.create(\r\n model=\"text-embedding-3-large\",\r\n input=text,\r\n dimensions=3072\r\n )\r\n return response.data[0].embedding\r\n\r\n def search_cwicr(\r\n self,\r\n query: str,\r\n limit: int = 5,\r\n category_filter: str = None\r\n ) -> List[WorkItem]:\r\n \"\"\"Search CWICR database for matching work items\"\"\"\r\n\r\n # Get embedding\r\n query_vector = self.get_embedding(query)\r\n\r\n # Build filter if category specified\r\n query_filter = None\r\n if category_filter:\r\n query_filter = Filter(\r\n must=[\r\n FieldCondition(\r\n key=\"category\",\r\n match=MatchValue(value=category_filter)\r\n )\r\n ]\r\n )\r\n\r\n # Search\r\n results = self.qdrant.search(\r\n collection_name=self.collection,\r\n query_vector=query_vector,\r\n query_filter=query_filter,\r\n limit=limit\r\n )\r\n\r\n # Parse results\r\n work_items = []\r\n for r in results:\r\n payload = r.payload\r\n work_items.append(WorkItem(\r\n cwicr_code=payload.get('code', ''),\r\n description=payload.get('description', ''),\r\n unit=payload.get('unit', ''),\r\n unit_price=float(payload.get('unit_price', 0)),\r\n labor_cost=float(payload.get('labor_cost', 0)),\r\n material_cost=float(payload.get('material_cost', 0)),\r\n equipment_cost=float(payload.get('equipment_cost', 0)),\r\n productivity=float(payload.get('productivity', 1)),\r\n currency=payload.get('currency', 'USD'),\r\n confidence=r.score\r\n ))\r\n\r\n return work_items\r\n\r\n def decompose_bim_type(\r\n self,\r\n bim_type: str,\r\n category: str\r\n ) -> List[str]:\r\n \"\"\"Use LLM to decompose BIM type into work items\"\"\"\r\n\r\n prompt = f\"\"\"\r\nDecompose this BIM element type into construction work items:\r\n\r\nBIM Type: {bim_type}\r\nCategory: {category}\r\n\r\nList the individual work activities needed to construct this element.\r\nFor example, \"Brick Wall 240mm\" decomposes into:\r\n- Masonry: Brick laying\r\n- Mortar: Cement mortar for joints\r\n- Plaster: Internal plaster finish\r\n- Paint: Wall painting\r\n\r\nReturn a JSON array of work item descriptions.\r\nExample: [\"Brick masonry laying\", \"Cement mortar for brick joints\", \"Internal cement plaster 15mm\"]\r\n\"\"\"\r\n\r\n response = self.openai.chat.completions.create(\r\n model=\"gpt-4o\",\r\n messages=[{\"role\": \"user\", \"content\": prompt}],\r\n response_format={\"type\": \"json_object\"}\r\n )\r\n\r\n try:\r\n result = json.loads(response.choices[0].message.content)\r\n return result.get('work_items', [bim_type])\r\n except:\r\n return [bim_type]\r\n\r\n def estimate_element(\r\n self,\r\n bim_type: str,\r\n category: str,\r\n quantity: float,\r\n quantity_unit: str,\r\n phase: str = \"Construction\"\r\n ) -> List[CostLineItem]:\r\n \"\"\"Estimate cost for single BIM element type\"\"\"\r\n\r\n # Decompose into work items\r\n work_descriptions = self.decompose_bim_type(bim_type, category)\r\n\r\n line_items = []\r\n\r\n for work_desc in work_descriptions:\r\n # Search CWICR for matching rate\r\n matches = self.search_cwicr(work_desc, limit=1)\r\n\r\n if not matches:\r\n continue\r\n\r\n best_match = matches[0]\r\n\r\n # Convert quantity if units don't match\r\n adjusted_qty = self._convert_units(\r\n quantity, quantity_unit, best_match.unit\r\n )\r\n\r\n # Calculate costs\r\n total = adjusted_qty * best_match.unit_price\r\n labor = adjusted_qty * best_match.labor_cost\r\n material = adjusted_qty * best_match.material_cost\r\n equipment = adjusted_qty * best_match.equipment_cost\r\n\r\n line_items.append(CostLineItem(\r\n bim_type=bim_type,\r\n work_item=best_match,\r\n quantity=adjusted_qty,\r\n quantity_unit=best_match.unit,\r\n total_cost=total,\r\n labor_cost=labor,\r\n material_cost=material,\r\n equipment_cost=equipment,\r\n phase=phase,\r\n trade=self._get_trade(category)\r\n ))\r\n\r\n return line_items\r\n\r\n def estimate_from_qto(\r\n self,\r\n qto_data: pd.DataFrame,\r\n type_column: str = \"Type Name\",\r\n category_column: str = \"Category\",\r\n quantity_column: str = \"Volume\"\r\n ) -> List[CostLineItem]:\r\n \"\"\"Generate estimate from QTO DataFrame\"\"\"\r\n\r\n all_line_items = []\r\n\r\n # Group by type\r\n grouped = qto_data.groupby([category_column, type_column]).agg({\r\n quantity_column: 'sum'\r\n }).reset_index()\r\n\r\n for _, row in grouped.iterrows():\r\n items = self.estimate_element(\r\n bim_type=row[type_column],\r\n category=row[category_column],\r\n quantity=row[quantity_column],\r\n quantity_unit=\"mΒ³\" # Assume volume, adjust based on category\r\n )\r\n all_line_items.extend(items)\r\n\r\n return all_line_items\r\n\r\n def _convert_units(\r\n self,\r\n value: float,\r\n from_unit: str,\r\n to_unit: str\r\n ) -> float:\r\n \"\"\"Convert between units\"\"\"\r\n\r\n # Simplified conversion - expand as needed\r\n conversions = {\r\n ('mΒ³', 'mΒ³'): 1.0,\r\n ('mΒ²', 'mΒ²'): 1.0,\r\n ('m', 'm'): 1.0,\r\n ('ftΒ³', 'mΒ³'): 0.0283168,\r\n ('ftΒ²', 'mΒ²'): 0.092903,\r\n ('ft', 'm'): 0.3048,\r\n }\r\n\r\n key = (from_unit.lower(), to_unit.lower())\r\n factor = conversions.get(key, 1.0)\r\n\r\n return value * factor\r\n\r\n def _get_trade(self, category: str) -> str:\r\n \"\"\"Map BIM category to trade\"\"\"\r\n trade_map = {\r\n 'Walls': 'Masonry',\r\n 'Floors': 'Concrete',\r\n 'Structural Columns': 'Concrete',\r\n 'Structural Framing': 'Steel',\r\n 'Doors': 'Carpentry',\r\n 'Windows': 'Glazing',\r\n 'Plumbing Fixtures': 'Plumbing',\r\n 'Electrical Equipment': 'Electrical',\r\n 'Mechanical Equipment': 'HVAC'\r\n }\r\n return trade_map.get(category, 'General')\r\n\r\n def generate_estimate_report(\r\n self,\r\n line_items: List[CostLineItem],\r\n project_name: str,\r\n output_path: str\r\n ) -> dict:\r\n \"\"\"Generate comprehensive estimate report\"\"\"\r\n\r\n # Convert to DataFrame\r\n records = []\r\n for item in line_items:\r\n records.append({\r\n 'BIM Type': item.bim_type,\r\n 'Work Item': item.work_item.description,\r\n 'CWICR Code': item.work_item.cwicr_code,\r\n 'Quantity': round(item.quantity, 2),\r\n 'Unit': item.quantity_unit,\r\n 'Unit Price': round(item.work_item.unit_price, 2),\r\n 'Labor': round(item.labor_cost, 2),\r\n 'Material': round(item.material_cost, 2),\r\n 'Equipment': round(item.equipment_cost, 2),\r\n 'Total': round(item.total_cost, 2),\r\n 'Phase': item.phase,\r\n 'Trade': item.trade,\r\n 'Currency': item.work_item.currency,\r\n 'Confidence': round(item.work_item.confidence, 2)\r\n })\r\n\r\n df = pd.DataFrame(records)\r\n\r\n # Calculate totals\r\n total_cost = df['Total'].sum()\r\n total_labor = df['Labor'].sum()\r\n total_material = df['Material'].sum()\r\n total_equipment = df['Equipment'].sum()\r\n\r\n # Summary by trade\r\n by_trade = df.groupby('Trade')['Total'].sum().sort_values(ascending=False)\r\n\r\n # Write Excel\r\n excel_path = f\"{output_path}/{project_name}_Estimate.xlsx\"\r\n with pd.ExcelWriter(excel_path, engine='openpyxl') as writer:\r\n # Summary sheet\r\n summary_data = {\r\n 'Metric': ['Total Cost', 'Labor Cost', 'Material Cost', 'Equipment Cost'],\r\n 'Value': [total_cost, total_labor, total_material, total_equipment]\r\n }\r\n pd.DataFrame(summary_data).to_excel(writer, sheet_name='Summary', index=False)\r\n\r\n # By Trade\r\n by_trade.to_frame().to_excel(writer, sheet_name='By Trade')\r\n\r\n # Detail\r\n df.to_excel(writer, sheet_name='Detail', index=False)\r\n\r\n return {\r\n 'excel_path': excel_path,\r\n 'total_cost': total_cost,\r\n 'total_labor': total_labor,\r\n 'total_material': total_material,\r\n 'total_equipment': total_equipment,\r\n 'by_trade': by_trade.to_dict(),\r\n 'line_items': len(df),\r\n 'currency': line_items[0].work_item.currency if line_items else 'USD'\r\n }\r\n\r\n\r\n# Usage Example\r\ndef estimate_from_bim_model(\r\n model_path: str,\r\n qdrant_url: str,\r\n language: str = \"EN\",\r\n output_dir: str = \".\"\r\n) -> dict:\r\n \"\"\"Complete BIM to cost estimation workflow\"\"\"\r\n\r\n import subprocess\r\n from pathlib import Path\r\n\r\n # Step 1: Convert BIM to Excel\r\n print(\"Converting BIM model...\")\r\n subprocess.run([\r\n r\"C:\\DDC\\RvtExporter.exe\",\r\n model_path,\r\n \"complete\", \"bbox\"\r\n ])\r\n\r\n xlsx_path = Path(model_path).with_suffix('.xlsx')\r\n\r\n # Step 2: Load QTO data\r\n print(\"Loading quantity data...\")\r\n df = pd.read_excel(xlsx_path)\r\n\r\n # Step 3: Initialize estimator\r\n estimator = BIMCostEstimator(\r\n qdrant_url=qdrant_url,\r\n language=language\r\n )\r\n\r\n # Step 4: Generate estimate\r\n print(\"Generating cost estimate...\")\r\n line_items = estimator.estimate_from_qto(df)\r\n\r\n # Step 5: Generate report\r\n project_name = Path(model_path).stem\r\n result = estimator.generate_estimate_report(\r\n line_items=line_items,\r\n project_name=project_name,\r\n output_path=output_dir\r\n )\r\n\r\n print(f\"\\nEstimate Complete!\")\r\n print(f\"Total Cost: {result['currency']} {result['total_cost']:,.2f}\")\r\n print(f\"Excel Report: {result['excel_path']}\")\r\n\r\n return result\r\n\r\n\r\nif __name__ == \"__main__\":\r\n result = estimate_from_bim_model(\r\n model_path=r\"C:\\Projects\\Building.rvt\",\r\n qdrant_url=\"https://your-qdrant-instance.io\",\r\n language=\"DE\",\r\n output_dir=r\"C:\\Projects\\Estimates\"\r\n )\r\n```\r\n\r\n## n8n Workflow\r\n\r\nSee: `n8n_4_CAD_(BIM)_Cost_Estimation_Pipeline_4D_5D_with_DDC_CWICR.json`\r\n\r\n```yaml\r\nstages:\r\n - convert: RvtExporter β†’ XLSX\r\n - detect_project: LLM identifies project type\r\n - generate_phases: LLM creates construction phases\r\n - decompose: LLM breaks types into work items\r\n - vector_search: Qdrant finds CWICR matches\r\n - calculate: Qty Γ— Unit Price\r\n - validate: CTO review\r\n - report: HTML + Excel output\r\n```\r\n\r\n## Output Example\r\n\r\n```\r\n╔══════════════════════════════════════════════════════════════╗\r\nβ•‘ COST ESTIMATE SUMMARY β•‘\r\nβ•‘ Project: Office Building Berlin β•‘\r\nβ•‘ Date: 2026-01-24 β•‘\r\n╠══════════════════════════════════════════════════════════════╣\r\n\r\nTOTAL PROJECT COST: EUR 4,523,678.00\r\n───────────────────────────────────────────────────────────────\r\n Labor: EUR 1,847,234.00 (41%)\r\n Materials: EUR 2,312,456.00 (51%)\r\n Equipment: EUR 363,988.00 ( 8%)\r\n\r\nBY TRADE\r\n───────────────────────────────────────────────────────────────\r\n Concrete: EUR 1,234,567.00 (27%)\r\n Masonry: EUR 876,543.00 (19%)\r\n Steel Structure: EUR 654,321.00 (14%)\r\n MEP: EUR 543,210.00 (12%)\r\n Finishes: EUR 432,109.00 (10%)\r\n Other: EUR 782,928.00 (18%)\r\n\r\nCONFIDENCE ANALYSIS\r\n───────────────────────────────────────────────────────────────\r\n High (>0.85): 78%\r\n Medium (0.70-0.85): 18%\r\n Low (<0.70): 4%\r\n\r\nβ•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•\r\n```\r\n\r\n## Resources\r\n\r\n- **CWICR Repository**: https://github.com/datadrivenconstruction/OpenConstructionEstimate-DDC-CWICR\r\n- **Live Demo**: https://openconstructionestimate.com\r\n- **Qdrant**: https://qdrant.tech\r\n\r\n---\r\n\r\n*\"Resource-based costing separates physical quantities from volatile prices, enabling transparent and auditable estimates.\"*\n\nFile v2.1.0:_meta.json\n\n{\n \"ownerId\": \"kn75fhjxn1jz5xbgd9ggj0nrtd80q1dz\",\n \"slug\": \"bim-cost-estimation-cwicr\",\n \"version\": \"2.1.0\",\n \"publishedAt\": 1771016910955\n}\n\nFile v2.1.0:instructions.md\n\nYou are a BIM-to-cost estimation assistant powered by the DDC CWICR database (55,719 work items across 9 languages). You automate the full pipeline from BIM model to cost estimate using AI classification and vector search.\n\nWhen the user asks to estimate costs from a BIM model:\n1. Guide them through the pipeline stages: BIM export -> QTO -> AI classification -> vector search -> cost calculation\n2. Explain the 10-stage pipeline (collect, detect project, generate phases, assign elements, decompose work, vector search, unit mapping, cost calculation, validation, aggregation)\n3. Help configure: language/region (EN, DE, RU, ES, FR, AR, HI, PT, ZH), Qdrant connection, OpenAI API for embeddings\n4. Present results by trade, phase, and element type\n\nWhen the user asks about CWICR database:\n1. Explain the database structure: 55,719 work items, 27,672 resources, 85 fields per item\n2. Help with vector search queries using text-embedding-3-large (3072 dimensions)\n3. Show matching results with confidence scores\n\n## Input Format\n- BIM model path (.rvt or .ifc) or pre-exported QTO data (.xlsx)\n- Target language/region for pricing\n- Qdrant URL and API credentials (environment variables)\n\n## Output Format\n- Cost estimate by trade (Concrete, Masonry, Steel, MEP, etc.)\n- Cost breakdown: labor, material, equipment percentages\n- Confidence analysis (high >0.85, medium 0.70-0.85, low <0.70)\n- Excel report with Summary, By Trade, and Detail sheets\n\n## Pipeline Stages\n| Stage | Description |\n|-------|-------------|\n| 0 | Collect BIM data from Revit/IFC |\n| 1-3 | AI detects project type, generates phases, assigns elements |\n| 4 | AI decomposes element types into work items |\n| 5 | Vector search matches work items to CWICR rates |\n| 6-7 | Unit mapping and cost calculation |\n| 8-9 | Aggregation and report generation |\n\n## Constraints\n- Network permission required for Qdrant vector database and OpenAI embeddings API\n- Filesystem permission required for BIM model reading and Excel export\n- subprocess.run() is used solely for invoking the DDC RvtExporter CAD conversion tool\n- All API keys must be loaded from environment variables, never hardcoded\n\nFile v2.1.0:claw.json\n\n{\n \"name\": \"bim-cost-estimation-cwicr\",\n \"version\": \"2.0.0\",\n \"description\": \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\",\n \"author\": \"datadrivenconstruction\",\n \"license\": \"MIT\",\n \"permissions\": [\"filesystem\", \"network\"],\n \"entry\": \"instructions.md\",\n \"tags\": [\"construction\", \"BIM\", \"estimation\", \"CWICR\", \"vector-search\", \"AI\", \"cost-management\"],\n \"models\": [\"claude-*\", \"gpt-*\"],\n \"minOpenClawVersion\": \"0.8.0\"\n}\n\nArchive v2.0.0: 4 files, 7895 bytes\n\nFiles: claw.json (531b), instructions.md (2154b), SKILL.md (20927b), _meta.json (144b)\n\nFile v2.0.0:SKILL.md\n\n---\r\nname: \"bim-cost-estimation-cwicr\"\r\ndescription: \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\"\r\n---\r\n\r\n# BIM Cost Estimation with DDC CWICR\r\n\r\nGenerate accurate cost estimates from BIM models using AI classification and the DDC CWICR construction cost database.\r\n\r\n## Business Case\r\n\r\n**Problem**: Traditional cost estimation:\r\n- Manual and time-consuming (weeks for detailed estimate)\r\n- Subjective and inconsistent between estimators\r\n- Requires specialized knowledge\r\n- Difficult to update with design changes\r\n\r\n**Solution**: Automated BIM-to-cost pipeline:\r\n- Extract quantities directly from model\r\n- AI classifies elements to work items\r\n- Vector search finds matching prices in CWICR\r\n- Complete estimate in hours, not weeks\r\n\r\n**ROI**: 80% reduction in estimation time, consistent methodology\r\n\r\n## System Architecture\r\n\r\n```\r\nβ”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”\r\nβ”‚ BIM TO COST ESTIMATION PIPELINE β”‚\r\nβ”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€\r\nβ”‚ β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ BIM β”‚ β”‚ DDC β”‚ β”‚ AI β”‚ β”‚ DDC CWICR β”‚ β”‚\r\nβ”‚ β”‚ Model │────►│Converter│────►│ LLM │────►│ Vector Search β”‚ β”‚\r\nβ”‚ β”‚.rvt/.ifcβ”‚ β”‚ β”‚ β”‚ β”‚ β”‚ (Qdrant) β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β–Ό β–Ό β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ .xlsx β”‚ β”‚ Work β”‚ β”‚ Matched β”‚ β”‚\r\nβ”‚ β”‚ QTO β”‚ β”‚ Items β”‚ β”‚ Rates β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ COST ESTIMATE β”‚ β”‚\r\nβ”‚ β”‚ β”‚ β”‚\r\nβ”‚ β”‚ β€’ By element β”‚ β”‚\r\nβ”‚ β”‚ β€’ By trade β”‚ β”‚\r\nβ”‚ β”‚ β€’ By phase β”‚ β”‚\r\nβ”‚ β”‚ β€’ Resources β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚\r\nβ””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜\r\n```\r\n\r\n## DDC CWICR Database\r\n\r\n```yaml\r\nDatabase Overview:\r\n work_items: 55,719\r\n resources: 27,672\r\n languages: 9 (AR, DE, EN, ES, FR, HI, PT, RU, ZH)\r\n fields_per_item: 85\r\n embedding_model: text-embedding-3-large (3072d)\r\n vector_db: Qdrant\r\n\r\nCollections:\r\n - ddc_cwicr_ar # Arabic (Dubai prices)\r\n - ddc_cwicr_de # German (Berlin prices)\r\n - ddc_cwicr_en # English (Toronto prices)\r\n - ddc_cwicr_es # Spanish (Barcelona prices)\r\n - ddc_cwicr_fr # French (Paris prices)\r\n - ddc_cwicr_hi # Hindi (Mumbai prices)\r\n - ddc_cwicr_pt # Portuguese (SΓ£o Paulo prices)\r\n - ddc_cwicr_ru # Russian (St. Petersburg prices)\r\n - ddc_cwicr_zh # Chinese (Shanghai prices)\r\n```\r\n\r\n## Pipeline Stages\r\n\r\n| Stage | Name | Description |\r\n|-------|------|-------------|\r\n| 0 | Collect BIM Data | Extract elements from Revit/IFC |\r\n| 1 | Project Detection | AI identifies project type |\r\n| 2 | Phase Generation | AI creates construction phases |\r\n| 3 | Element Assignment | AI maps types to phases |\r\n| 4 | Work Decomposition | AI breaks types into work items |\r\n| 5 | Vector Search | Find matching rates in CWICR |\r\n| 6 | Unit Mapping | Convert BIM units to rate units |\r\n| 7 | Cost Calculation | Qty Γ— Unit Price |\r\n| 7.5 | Validation | CTO review for completeness |\r\n| 8 | Aggregation | Sum by phases and categories |\r\n| 9 | Report Generation | HTML and Excel outputs |\r\n\r\n## Python Implementation\r\n\r\n```python\r\nimport pandas as pd\r\nimport numpy as np\r\nfrom qdrant_client import QdrantClient\r\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue\r\nfrom openai import OpenAI\r\nfrom typing import List, Dict, Optional\r\nfrom dataclasses import dataclass\r\nimport json\r\n\r\n@dataclass\r\nclass WorkItem:\r\n \"\"\"Matched work item from CWICR\"\"\"\r\n cwicr_code: str\r\n description: str\r\n unit: str\r\n unit_price: float\r\n labor_cost: float\r\n material_cost: float\r\n equipment_cost: float\r\n productivity: float # units per hour\r\n currency: str\r\n confidence: float\r\n\r\n@dataclass\r\nclass CostLineItem:\r\n \"\"\"Single line item in estimate\"\"\"\r\n bim_type: str\r\n work_item: WorkItem\r\n quantity: float\r\n quantity_unit: str\r\n total_cost: float\r\n labor_cost: float\r\n material_cost: float\r\n equipment_cost: float\r\n phase: str\r\n trade: str\r\n\r\n\r\nclass BIMCostEstimator:\r\n \"\"\"BIM to cost estimation using DDC CWICR\"\"\"\r\n\r\n def __init__(\r\n self,\r\n qdrant_url: str,\r\n qdrant_api_key: str = None,\r\n openai_api_key: str = None,\r\n language: str = \"EN\"\r\n ):\r\n self.qdrant = QdrantClient(url=qdrant_url, api_key=qdrant_api_key)\r\n self.openai = OpenAI(api_key=openai_api_key)\r\n self.language = language\r\n self.collection = f\"ddc_cwicr_{language.lower()}\"\r\n\r\n def get_embedding(self, text: str) -> List[float]:\r\n \"\"\"Generate embedding for text\"\"\"\r\n response = self.openai.embeddings.create(\r\n model=\"text-embedding-3-large\",\r\n input=text,\r\n dimensions=3072\r\n )\r\n return response.data[0].embedding\r\n\r\n def search_cwicr(\r\n self,\r\n query: str,\r\n limit: int = 5,\r\n category_filter: str = None\r\n ) -> List[WorkItem]:\r\n \"\"\"Search CWICR database for matching work items\"\"\"\r\n\r\n # Get embedding\r\n query_vector = self.get_embedding(query)\r\n\r\n # Build filter if category specified\r\n query_filter = None\r\n if category_filter:\r\n query_filter = Filter(\r\n must=[\r\n FieldCondition(\r\n key=\"category\",\r\n match=MatchValue(value=category_filter)\r\n )\r\n ]\r\n )\r\n\r\n # Search\r\n results = self.qdrant.search(\r\n collection_name=self.collection,\r\n query_vector=query_vector,\r\n query_filter=query_filter,\r\n limit=limit\r\n )\r\n\r\n # Parse results\r\n work_items = []\r\n for r in results:\r\n payload = r.payload\r\n work_items.append(WorkItem(\r\n cwicr_code=payload.get('code', ''),\r\n description=payload.get('description', ''),\r\n unit=payload.get('unit', ''),\r\n unit_price=float(payload.get('unit_price', 0)),\r\n labor_cost=float(payload.get('labor_cost', 0)),\r\n material_cost=float(payload.get('material_cost', 0)),\r\n equipment_cost=float(payload.get('equipment_cost', 0)),\r\n productivity=float(payload.get('productivity', 1)),\r\n currency=payload.get('currency', 'USD'),\r\n confidence=r.score\r\n ))\r\n\r\n return work_items\r\n\r\n def decompose_bim_type(\r\n self,\r\n bim_type: str,\r\n category: str\r\n ) -> List[str]:\r\n \"\"\"Use LLM to decompose BIM type into work items\"\"\"\r\n\r\n prompt = f\"\"\"\r\nDecompose this BIM element type into construction work items:\r\n\r\nBIM Type: {bim_type}\r\nCategory: {category}\r\n\r\nList the individual work activities needed to construct this element.\r\nFor example, \"Brick Wall 240mm\" decomposes into:\r\n- Masonry: Brick laying\r\n- Mortar: Cement mortar for joints\r\n- Plaster: Internal plaster finish\r\n- Paint: Wall painting\r\n\r\nReturn a JSON array of work item descriptions.\r\nExample: [\"Brick masonry laying\", \"Cement mortar for brick joints\", \"Internal cement plaster 15mm\"]\r\n\"\"\"\r\n\r\n response = self.openai.chat.completions.create(\r\n model=\"gpt-4o\",\r\n messages=[{\"role\": \"user\", \"content\": prompt}],\r\n response_format={\"type\": \"json_object\"}\r\n )\r\n\r\n try:\r\n result = json.loads(response.choices[0].message.content)\r\n return result.get('work_items', [bim_type])\r\n except:\r\n return [bim_type]\r\n\r\n def estimate_element(\r\n self,\r\n bim_type: str,\r\n category: str,\r\n quantity: float,\r\n quantity_unit: str,\r\n phase: str = \"Construction\"\r\n ) -> List[CostLineItem]:\r\n \"\"\"Estimate cost for single BIM element type\"\"\"\r\n\r\n # Decompose into work items\r\n work_descriptions = self.decompose_bim_type(bim_type, category)\r\n\r\n line_items = []\r\n\r\n for work_desc in work_descriptions:\r\n # Search CWICR for matching rate\r\n matches = self.search_cwicr(work_desc, limit=1)\r\n\r\n if not matches:\r\n continue\r\n\r\n best_match = matches[0]\r\n\r\n # Convert quantity if units don't match\r\n adjusted_qty = self._convert_units(\r\n quantity, quantity_unit, best_match.unit\r\n )\r\n\r\n # Calculate costs\r\n total = adjusted_qty * best_match.unit_price\r\n labor = adjusted_qty * best_match.labor_cost\r\n material = adjusted_qty * best_match.material_cost\r\n equipment = adjusted_qty * best_match.equipment_cost\r\n\r\n line_items.append(CostLineItem(\r\n bim_type=bim_type,\r\n work_item=best_match,\r\n quantity=adjusted_qty,\r\n quantity_unit=best_match.unit,\r\n total_cost=total,\r\n labor_cost=labor,\r\n material_cost=material,\r\n equipment_cost=equipment,\r\n phase=phase,\r\n trade=self._get_trade(category)\r\n ))\r\n\r\n return line_items\r\n\r\n def estimate_from_qto(\r\n self,\r\n qto_data: pd.DataFrame,\r\n type_column: str = \"Type Name\",\r\n category_column: str = \"Category\",\r\n quantity_column: str = \"Volume\"\r\n ) -> List[CostLineItem]:\r\n \"\"\"Generate estimate from QTO DataFrame\"\"\"\r\n\r\n all_line_items = []\r\n\r\n # Group by type\r\n grouped = qto_data.groupby([category_column, type_column]).agg({\r\n quantity_column: 'sum'\r\n }).reset_index()\r\n\r\n for _, row in grouped.iterrows():\r\n items = self.estimate_element(\r\n bim_type=row[type_column],\r\n category=row[category_column],\r\n quantity=row[quantity_column],\r\n quantity_unit=\"mΒ³\" # Assume volume, adjust based on category\r\n )\r\n all_line_items.extend(items)\r\n\r\n return all_line_items\r\n\r\n def _convert_units(\r\n self,\r\n value: float,\r\n from_unit: str,\r\n to_unit: str\r\n ) -> float:\r\n \"\"\"Convert between units\"\"\"\r\n\r\n # Simplified conversion - expand as needed\r\n conversions = {\r\n ('mΒ³', 'mΒ³'): 1.0,\r\n ('mΒ²', 'mΒ²'): 1.0,\r\n ('m', 'm'): 1.0,\r\n ('ftΒ³', 'mΒ³'): 0.0283168,\r\n ('ftΒ²', 'mΒ²'): 0.092903,\r\n ('ft', 'm'): 0.3048,\r\n }\r\n\r\n key = (from_unit.lower(), to_unit.lower())\r\n factor = conversions.get(key, 1.0)\r\n\r\n return value * factor\r\n\r\n def _get_trade(self, category: str) -> str:\r\n \"\"\"Map BIM category to trade\"\"\"\r\n trade_map = {\r\n 'Walls': 'Masonry',\r\n 'Floors': 'Concrete',\r\n 'Structural Columns': 'Concrete',\r\n 'Structural Framing': 'Steel',\r\n 'Doors': 'Carpentry',\r\n 'Windows': 'Glazing',\r\n 'Plumbing Fixtures': 'Plumbing',\r\n 'Electrical Equipment': 'Electrical',\r\n 'Mechanical Equipment': 'HVAC'\r\n }\r\n return trade_map.get(category, 'General')\r\n\r\n def generate_estimate_report(\r\n self,\r\n line_items: List[CostLineItem],\r\n project_name: str,\r\n output_path: str\r\n ) -> dict:\r\n \"\"\"Generate comprehensive estimate report\"\"\"\r\n\r\n # Convert to DataFrame\r\n records = []\r\n for item in line_items:\r\n records.append({\r\n 'BIM Type': item.bim_type,\r\n 'Work Item': item.work_item.description,\r\n 'CWICR Code': item.work_item.cwicr_code,\r\n 'Quantity': round(item.quantity, 2),\r\n 'Unit': item.quantity_unit,\r\n 'Unit Price': round(item.work_item.unit_price, 2),\r\n 'Labor': round(item.labor_cost, 2),\r\n 'Material': round(item.material_cost, 2),\r\n 'Equipment': round(item.equipment_cost, 2),\r\n 'Total': round(item.total_cost, 2),\r\n 'Phase': item.phase,\r\n 'Trade': item.trade,\r\n 'Currency': item.work_item.currency,\r\n 'Confidence': round(item.work_item.confidence, 2)\r\n })\r\n\r\n df = pd.DataFrame(records)\r\n\r\n # Calculate totals\r\n total_cost = df['Total'].sum()\r\n total_labor = df['Labor'].sum()\r\n total_material = df['Material'].sum()\r\n total_equipment = df['Equipment'].sum()\r\n\r\n # Summary by trade\r\n by_trade = df.groupby('Trade')['Total'].sum().sort_values(ascending=False)\r\n\r\n # Write Excel\r\n excel_path = f\"{output_path}/{project_name}_Estimate.xlsx\"\r\n with pd.ExcelWriter(excel_path, engine='openpyxl') as writer:\r\n # Summary sheet\r\n summary_data = {\r\n 'Metric': ['Total Cost', 'Labor Cost', 'Material Cost', 'Equipment Cost'],\r\n 'Value': [total_cost, total_labor, total_material, total_equipment]\r\n }\r\n pd.DataFrame(summary_data).to_excel(writer, sheet_name='Summary', index=False)\r\n\r\n # By Trade\r\n by_trade.to_frame().to_excel(writer, sheet_name='By Trade')\r\n\r\n # Detail\r\n df.to_excel(writer, sheet_name='Detail', index=False)\r\n\r\n return {\r\n 'excel_path': excel_path,\r\n 'total_cost': total_cost,\r\n 'total_labor': total_labor,\r\n 'total_material': total_material,\r\n 'total_equipment': total_equipment,\r\n 'by_trade': by_trade.to_dict(),\r\n 'line_items': len(df),\r\n 'currency': line_items[0].work_item.currency if line_items else 'USD'\r\n }\r\n\r\n\r\n# Usage Example\r\ndef estimate_from_bim_model(\r\n model_path: str,\r\n qdrant_url: str,\r\n language: str = \"EN\",\r\n output_dir: str = \".\"\r\n) -> dict:\r\n \"\"\"Complete BIM to cost estimation workflow\"\"\"\r\n\r\n import subprocess\r\n from pathlib import Path\r\n\r\n # Step 1: Convert BIM to Excel\r\n print(\"Converting BIM model...\")\r\n subprocess.run([\r\n r\"C:\\DDC\\RvtExporter.exe\",\r\n model_path,\r\n \"complete\", \"bbox\"\r\n ])\r\n\r\n xlsx_path = Path(model_path).with_suffix('.xlsx')\r\n\r\n # Step 2: Load QTO data\r\n print(\"Loading quantity data...\")\r\n df = pd.read_excel(xlsx_path)\r\n\r\n # Step 3: Initialize estimator\r\n estimator = BIMCostEstimator(\r\n qdrant_url=qdrant_url,\r\n language=language\r\n )\r\n\r\n # Step 4: Generate estimate\r\n print(\"Generating cost estimate...\")\r\n line_items = estimator.estimate_from_qto(df)\r\n\r\n # Step 5: Generate report\r\n project_name = Path(model_path).stem\r\n result = estimator.generate_estimate_report(\r\n line_items=line_items,\r\n project_name=project_name,\r\n output_path=output_dir\r\n )\r\n\r\n print(f\"\\nEstimate Complete!\")\r\n print(f\"Total Cost: {result['currency']} {result['total_cost']:,.2f}\")\r\n print(f\"Excel Report: {result['excel_path']}\")\r\n\r\n return result\r\n\r\n\r\nif __name__ == \"__main__\":\r\n result = estimate_from_bim_model(\r\n model_path=r\"C:\\Projects\\Building.rvt\",\r\n qdrant_url=\"https://your-qdrant-instance.io\",\r\n language=\"DE\",\r\n output_dir=r\"C:\\Projects\\Estimates\"\r\n )\r\n```\r\n\r\n## n8n Workflow\r\n\r\nSee: `n8n_4_CAD_(BIM)_Cost_Estimation_Pipeline_4D_5D_with_DDC_CWICR.json`\r\n\r\n```yaml\r\nstages:\r\n - convert: RvtExporter β†’ XLSX\r\n - detect_project: LLM identifies project type\r\n - generate_phases: LLM creates construction phases\r\n - decompose: LLM breaks types into work items\r\n - vector_search: Qdrant finds CWICR matches\r\n - calculate: Qty Γ— Unit Price\r\n - validate: CTO review\r\n - report: HTML + Excel output\r\n```\r\n\r\n## Output Example\r\n\r\n```\r\n╔══════════════════════════════════════════════════════════════╗\r\nβ•‘ COST ESTIMATE SUMMARY β•‘\r\nβ•‘ Project: Office Building Berlin β•‘\r\nβ•‘ Date: 2026-01-24 β•‘\r\n╠══════════════════════════════════════════════════════════════╣\r\n\r\nTOTAL PROJECT COST: EUR 4,523,678.00\r\n───────────────────────────────────────────────────────────────\r\n Labor: EUR 1,847,234.00 (41%)\r\n Materials: EUR 2,312,456.00 (51%)\r\n Equipment: EUR 363,988.00 ( 8%)\r\n\r\nBY TRADE\r\n───────────────────────────────────────────────────────────────\r\n Concrete: EUR 1,234,567.00 (27%)\r\n Masonry: EUR 876,543.00 (19%)\r\n Steel Structure: EUR 654,321.00 (14%)\r\n MEP: EUR 543,210.00 (12%)\r\n Finishes: EUR 432,109.00 (10%)\r\n Other: EUR 782,928.00 (18%)\r\n\r\nCONFIDENCE ANALYSIS\r\n───────────────────────────────────────────────────────────────\r\n High (>0.85): 78%\r\n Medium (0.70-0.85): 18%\r\n Low (<0.70): 4%\r\n\r\nβ•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•\r\n```\r\n\r\n## Resources\r\n\r\n- **CWICR Repository**: https://github.com/datadrivenconstruction/OpenConstructionEstimate-DDC-CWICR\r\n- **Live Demo**: https://openconstructionestimate.com\r\n- **Qdrant**: https://qdrant.tech\r\n\r\n---\r\n\r\n*\"Resource-based costing separates physical quantities from volatile prices, enabling transparent and auditable estimates.\"*\n\nFile v2.0.0:_meta.json\n\n{\n \"ownerId\": \"kn75fhjxn1jz5xbgd9ggj0nrtd80q1dz\",\n \"slug\": \"bim-cost-estimation-cwicr\",\n \"version\": \"2.0.0\",\n \"publishedAt\": 1770996173595\n}\n\nFile v2.0.0:instructions.md\n\nYou are a BIM-to-cost estimation assistant powered by the DDC CWICR database (55,719 work items across 9 languages). You automate the full pipeline from BIM model to cost estimate using AI classification and vector search.\n\nWhen the user asks to estimate costs from a BIM model:\n1. Guide them through the pipeline stages: BIM export -> QTO -> AI classification -> vector search -> cost calculation\n2. Explain the 10-stage pipeline (collect, detect project, generate phases, assign elements, decompose work, vector search, unit mapping, cost calculation, validation, aggregation)\n3. Help configure: language/region (EN, DE, RU, ES, FR, AR, HI, PT, ZH), Qdrant connection, OpenAI API for embeddings\n4. Present results by trade, phase, and element type\n\nWhen the user asks about CWICR database:\n1. Explain the database structure: 55,719 work items, 27,672 resources, 85 fields per item\n2. Help with vector search queries using text-embedding-3-large (3072 dimensions)\n3. Show matching results with confidence scores\n\n## Input Format\n- BIM model path (.rvt or .ifc) or pre-exported QTO data (.xlsx)\n- Target language/region for pricing\n- Qdrant URL and API credentials (environment variables)\n\n## Output Format\n- Cost estimate by trade (Concrete, Masonry, Steel, MEP, etc.)\n- Cost breakdown: labor, material, equipment percentages\n- Confidence analysis (high >0.85, medium 0.70-0.85, low <0.70)\n- Excel report with Summary, By Trade, and Detail sheets\n\n## Pipeline Stages\n| Stage | Description |\n|-------|-------------|\n| 0 | Collect BIM data from Revit/IFC |\n| 1-3 | AI detects project type, generates phases, assigns elements |\n| 4 | AI decomposes element types into work items |\n| 5 | Vector search matches work items to CWICR rates |\n| 6-7 | Unit mapping and cost calculation |\n| 8-9 | Aggregation and report generation |\n\n## Constraints\n- Network permission required for Qdrant vector database and OpenAI embeddings API\n- Filesystem permission required for BIM model reading and Excel export\n- subprocess.run() is used solely for invoking the DDC RvtExporter CAD conversion tool\n- All API keys must be loaded from environment variables, never hardcoded\n\nFile v2.0.0:claw.json\n\n{\n \"name\": \"bim-cost-estimation-cwicr\",\n \"version\": \"2.0.0\",\n \"description\": \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\",\n \"author\": \"datadrivenconstruction\",\n \"license\": \"MIT\",\n \"permissions\": [\"filesystem\", \"network\"],\n \"entry\": \"instructions.md\",\n \"tags\": [\"construction\", \"BIM\", \"estimation\", \"CWICR\", \"vector-search\", \"AI\", \"cost-management\"],\n \"models\": [\"claude-*\", \"gpt-*\"],\n \"minOpenClawVersion\": \"0.8.0\"\n}\n\nArchive v1.0.0: 2 files, 6267 bytes\n\nFiles: SKILL.md (20970b), _meta.json (144b)\n\nFile v1.0.0:SKILL.md\n\n---\r\nslug: \"bim-cost-estimation-cwicr\"\r\ndisplay_name: \"BIM Cost Estimation CWICR\"\r\ndescription: \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\"\r\n---\r\n\r\n# BIM Cost Estimation with DDC CWICR\r\n\r\nGenerate accurate cost estimates from BIM models using AI classification and the DDC CWICR construction cost database.\r\n\r\n## Business Case\r\n\r\n**Problem**: Traditional cost estimation:\r\n- Manual and time-consuming (weeks for detailed estimate)\r\n- Subjective and inconsistent between estimators\r\n- Requires specialized knowledge\r\n- Difficult to update with design changes\r\n\r\n**Solution**: Automated BIM-to-cost pipeline:\r\n- Extract quantities directly from model\r\n- AI classifies elements to work items\r\n- Vector search finds matching prices in CWICR\r\n- Complete estimate in hours, not weeks\r\n\r\n**ROI**: 80% reduction in estimation time, consistent methodology\r\n\r\n## System Architecture\r\n\r\n```\r\nβ”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”\r\nβ”‚ BIM TO COST ESTIMATION PIPELINE β”‚\r\nβ”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€\r\nβ”‚ β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ BIM β”‚ β”‚ DDC β”‚ β”‚ AI β”‚ β”‚ DDC CWICR β”‚ β”‚\r\nβ”‚ β”‚ Model │────►│Converter│────►│ LLM │────►│ Vector Search β”‚ β”‚\r\nβ”‚ β”‚.rvt/.ifcβ”‚ β”‚ β”‚ β”‚ β”‚ β”‚ (Qdrant) β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β–Ό β–Ό β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ .xlsx β”‚ β”‚ Work β”‚ β”‚ Matched β”‚ β”‚\r\nβ”‚ β”‚ QTO β”‚ β”‚ Items β”‚ β”‚ Rates β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ COST ESTIMATE β”‚ β”‚\r\nβ”‚ β”‚ β”‚ β”‚\r\nβ”‚ β”‚ β€’ By element β”‚ β”‚\r\nβ”‚ β”‚ β€’ By trade β”‚ β”‚\r\nβ”‚ β”‚ β€’ By phase β”‚ β”‚\r\nβ”‚ β”‚ β€’ Resources β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚\r\nβ””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜\r\n```\r\n\r\n## DDC CWICR Database\r\n\r\n```yaml\r\nDatabase Overview:\r\n work_items: 55,719\r\n resources: 27,672\r\n languages: 9 (AR, DE, EN, ES, FR, HI, PT, RU, ZH)\r\n fields_per_item: 85\r\n embedding_model: text-embedding-3-large (3072d)\r\n vector_db: Qdrant\r\n\r\nCollections:\r\n - ddc_cwicr_ar # Arabic (Dubai prices)\r\n - ddc_cwicr_de # German (Berlin prices)\r\n - ddc_cwicr_en # English (Toronto prices)\r\n - ddc_cwicr_es # Spanish (Barcelona prices)\r\n - ddc_cwicr_fr # French (Paris prices)\r\n - ddc_cwicr_hi # Hindi (Mumbai prices)\r\n - ddc_cwicr_pt # Portuguese (SΓ£o Paulo prices)\r\n - ddc_cwicr_ru # Russian (St. Petersburg prices)\r\n - ddc_cwicr_zh # Chinese (Shanghai prices)\r\n```\r\n\r\n## Pipeline Stages\r\n\r\n| Stage | Name | Description |\r\n|-------|------|-------------|\r\n| 0 | Collect BIM Data | Extract elements from Revit/IFC |\r\n| 1 | Project Detection | AI identifies project type |\r\n| 2 | Phase Generation | AI creates construction phases |\r\n| 3 | Element Assignment | AI maps types to phases |\r\n| 4 | Work Decomposition | AI breaks types into work items |\r\n| 5 | Vector Search | Find matching rates in CWICR |\r\n| 6 | Unit Mapping | Convert BIM units to rate units |\r\n| 7 | Cost Calculation | Qty Γ— Unit Price |\r\n| 7.5 | Validation | CTO review for completeness |\r\n| 8 | Aggregation | Sum by phases and categories |\r\n| 9 | Report Generation | HTML and Excel outputs |\r\n\r\n## Python Implementation\r\n\r\n```python\r\nimport pandas as pd\r\nimport numpy as np\r\nfrom qdrant_client import QdrantClient\r\nfrom qdrant_client.models import Filter, FieldCondition, MatchValue\r\nfrom openai import OpenAI\r\nfrom typing import List, Dict, Optional\r\nfrom dataclasses import dataclass\r\nimport json\r\n\r\n@dataclass\r\nclass WorkItem:\r\n \"\"\"Matched work item from CWICR\"\"\"\r\n cwicr_code: str\r\n description: str\r\n unit: str\r\n unit_price: float\r\n labor_cost: float\r\n material_cost: float\r\n equipment_cost: float\r\n productivity: float # units per hour\r\n currency: str\r\n confidence: float\r\n\r\n@dataclass\r\nclass CostLineItem:\r\n \"\"\"Single line item in estimate\"\"\"\r\n bim_type: str\r\n work_item: WorkItem\r\n quantity: float\r\n quantity_unit: str\r\n total_cost: float\r\n labor_cost: float\r\n material_cost: float\r\n equipment_cost: float\r\n phase: str\r\n trade: str\r\n\r\n\r\nclass BIMCostEstimator:\r\n \"\"\"BIM to cost estimation using DDC CWICR\"\"\"\r\n\r\n def __init__(\r\n self,\r\n qdrant_url: str,\r\n qdrant_api_key: str = None,\r\n openai_api_key: str = None,\r\n language: str = \"EN\"\r\n ):\r\n self.qdrant = QdrantClient(url=qdrant_url, api_key=qdrant_api_key)\r\n self.openai = OpenAI(api_key=openai_api_key)\r\n self.language = language\r\n self.collection = f\"ddc_cwicr_{language.lower()}\"\r\n\r\n def get_embedding(self, text: str) -> List[float]:\r\n \"\"\"Generate embedding for text\"\"\"\r\n response = self.openai.embeddings.create(\r\n model=\"text-embedding-3-large\",\r\n input=text,\r\n dimensions=3072\r\n )\r\n return response.data[0].embedding\r\n\r\n def search_cwicr(\r\n self,\r\n query: str,\r\n limit: int = 5,\r\n category_filter: str = None\r\n ) -> List[WorkItem]:\r\n \"\"\"Search CWICR database for matching work items\"\"\"\r\n\r\n # Get embedding\r\n query_vector = self.get_embedding(query)\r\n\r\n # Build filter if category specified\r\n query_filter = None\r\n if category_filter:\r\n query_filter = Filter(\r\n must=[\r\n FieldCondition(\r\n key=\"category\",\r\n match=MatchValue(value=category_filter)\r\n )\r\n ]\r\n )\r\n\r\n # Search\r\n results = self.qdrant.search(\r\n collection_name=self.collection,\r\n query_vector=query_vector,\r\n query_filter=query_filter,\r\n limit=limit\r\n )\r\n\r\n # Parse results\r\n work_items = []\r\n for r in results:\r\n payload = r.payload\r\n work_items.append(WorkItem(\r\n cwicr_code=payload.get('code', ''),\r\n description=payload.get('description', ''),\r\n unit=payload.get('unit', ''),\r\n unit_price=float(payload.get('unit_price', 0)),\r\n labor_cost=float(payload.get('labor_cost', 0)),\r\n material_cost=float(payload.get('material_cost', 0)),\r\n equipment_cost=float(payload.get('equipment_cost', 0)),\r\n productivity=float(payload.get('productivity', 1)),\r\n currency=payload.get('currency', 'USD'),\r\n confidence=r.score\r\n ))\r\n\r\n return work_items\r\n\r\n def decompose_bim_type(\r\n self,\r\n bim_type: str,\r\n category: str\r\n ) -> List[str]:\r\n \"\"\"Use LLM to decompose BIM type into work items\"\"\"\r\n\r\n prompt = f\"\"\"\r\nDecompose this BIM element type into construction work items:\r\n\r\nBIM Type: {bim_type}\r\nCategory: {category}\r\n\r\nList the individual work activities needed to construct this element.\r\nFor example, \"Brick Wall 240mm\" decomposes into:\r\n- Masonry: Brick laying\r\n- Mortar: Cement mortar for joints\r\n- Plaster: Internal plaster finish\r\n- Paint: Wall painting\r\n\r\nReturn a JSON array of work item descriptions.\r\nExample: [\"Brick masonry laying\", \"Cement mortar for brick joints\", \"Internal cement plaster 15mm\"]\r\n\"\"\"\r\n\r\n response = self.openai.chat.completions.create(\r\n model=\"gpt-4o\",\r\n messages=[{\"role\": \"user\", \"content\": prompt}],\r\n response_format={\"type\": \"json_object\"}\r\n )\r\n\r\n try:\r\n result = json.loads(response.choices[0].message.content)\r\n return result.get('work_items', [bim_type])\r\n except:\r\n return [bim_type]\r\n\r\n def estimate_element(\r\n self,\r\n bim_type: str,\r\n category: str,\r\n quantity: float,\r\n quantity_unit: str,\r\n phase: str = \"Construction\"\r\n ) -> List[CostLineItem]:\r\n \"\"\"Estimate cost for single BIM element type\"\"\"\r\n\r\n # Decompose into work items\r\n work_descriptions = self.decompose_bim_type(bim_type, category)\r\n\r\n line_items = []\r\n\r\n for work_desc in work_descriptions:\r\n # Search CWICR for matching rate\r\n matches = self.search_cwicr(work_desc, limit=1)\r\n\r\n if not matches:\r\n continue\r\n\r\n best_match = matches[0]\r\n\r\n # Convert quantity if units don't match\r\n adjusted_qty = self._convert_units(\r\n quantity, quantity_unit, best_match.unit\r\n )\r\n\r\n # Calculate costs\r\n total = adjusted_qty * best_match.unit_price\r\n labor = adjusted_qty * best_match.labor_cost\r\n material = adjusted_qty * best_match.material_cost\r\n equipment = adjusted_qty * best_match.equipment_cost\r\n\r\n line_items.append(CostLineItem(\r\n bim_type=bim_type,\r\n work_item=best_match,\r\n quantity=adjusted_qty,\r\n quantity_unit=best_match.unit,\r\n total_cost=total,\r\n labor_cost=labor,\r\n material_cost=material,\r\n equipment_cost=equipment,\r\n phase=phase,\r\n trade=self._get_trade(category)\r\n ))\r\n\r\n return line_items\r\n\r\n def estimate_from_qto(\r\n self,\r\n qto_data: pd.DataFrame,\r\n type_column: str = \"Type Name\",\r\n category_column: str = \"Category\",\r\n quantity_column: str = \"Volume\"\r\n ) -> List[CostLineItem]:\r\n \"\"\"Generate estimate from QTO DataFrame\"\"\"\r\n\r\n all_line_items = []\r\n\r\n # Group by type\r\n grouped = qto_data.groupby([category_column, type_column]).agg({\r\n quantity_column: 'sum'\r\n }).reset_index()\r\n\r\n for _, row in grouped.iterrows():\r\n items = self.estimate_element(\r\n bim_type=row[type_column],\r\n category=row[category_column],\r\n quantity=row[quantity_column],\r\n quantity_unit=\"mΒ³\" # Assume volume, adjust based on category\r\n )\r\n all_line_items.extend(items)\r\n\r\n return all_line_items\r\n\r\n def _convert_units(\r\n self,\r\n value: float,\r\n from_unit: str,\r\n to_unit: str\r\n ) -> float:\r\n \"\"\"Convert between units\"\"\"\r\n\r\n # Simplified conversion - expand as needed\r\n conversions = {\r\n ('mΒ³', 'mΒ³'): 1.0,\r\n ('mΒ²', 'mΒ²'): 1.0,\r\n ('m', 'm'): 1.0,\r\n ('ftΒ³', 'mΒ³'): 0.0283168,\r\n ('ftΒ²', 'mΒ²'): 0.092903,\r\n ('ft', 'm'): 0.3048,\r\n }\r\n\r\n key = (from_unit.lower(), to_unit.lower())\r\n factor = conversions.get(key, 1.0)\r\n\r\n return value * factor\r\n\r\n def _get_trade(self, category: str) -> str:\r\n \"\"\"Map BIM category to trade\"\"\"\r\n trade_map = {\r\n 'Walls': 'Masonry',\r\n 'Floors': 'Concrete',\r\n 'Structural Columns': 'Concrete',\r\n 'Structural Framing': 'Steel',\r\n 'Doors': 'Carpentry',\r\n 'Windows': 'Glazing',\r\n 'Plumbing Fixtures': 'Plumbing',\r\n 'Electrical Equipment': 'Electrical',\r\n 'Mechanical Equipment': 'HVAC'\r\n }\r\n return trade_map.get(category, 'General')\r\n\r\n def generate_estimate_report(\r\n self,\r\n line_items: List[CostLineItem],\r\n project_name: str,\r\n output_path: str\r\n ) -> dict:\r\n \"\"\"Generate comprehensive estimate report\"\"\"\r\n\r\n # Convert to DataFrame\r\n records = []\r\n for item in line_items:\r\n records.append({\r\n 'BIM Type': item.bim_type,\r\n 'Work Item': item.work_item.description,\r\n 'CWICR Code': item.work_item.cwicr_code,\r\n 'Quantity': round(item.quantity, 2),\r\n 'Unit': item.quantity_unit,\r\n 'Unit Price': round(item.work_item.unit_price, 2),\r\n 'Labor': round(item.labor_cost, 2),\r\n 'Material': round(item.material_cost, 2),\r\n 'Equipment': round(item.equipment_cost, 2),\r\n 'Total': round(item.total_cost, 2),\r\n 'Phase': item.phase,\r\n 'Trade': item.trade,\r\n 'Currency': item.work_item.currency,\r\n 'Confidence': round(item.work_item.confidence, 2)\r\n })\r\n\r\n df = pd.DataFrame(records)\r\n\r\n # Calculate totals\r\n total_cost = df['Total'].sum()\r\n total_labor = df['Labor'].sum()\r\n total_material = df['Material'].sum()\r\n total_equipment = df['Equipment'].sum()\r\n\r\n # Summary by trade\r\n by_trade = df.groupby('Trade')['Total'].sum().sort_values(ascending=False)\r\n\r\n # Write Excel\r\n excel_path = f\"{output_path}/{project_name}_Estimate.xlsx\"\r\n with pd.ExcelWriter(excel_path, engine='openpyxl') as writer:\r\n # Summary sheet\r\n summary_data = {\r\n 'Metric': ['Total Cost', 'Labor Cost', 'Material Cost', 'Equipment Cost'],\r\n 'Value': [total_cost, total_labor, total_material, total_equipment]\r\n }\r\n pd.DataFrame(summary_data).to_excel(writer, sheet_name='Summary', index=False)\r\n\r\n # By Trade\r\n by_trade.to_frame().to_excel(writer, sheet_name='By Trade')\r\n\r\n # Detail\r\n df.to_excel(writer, sheet_name='Detail', index=False)\r\n\r\n return {\r\n 'excel_path': excel_path,\r\n 'total_cost': total_cost,\r\n 'total_labor': total_labor,\r\n 'total_material': total_material,\r\n 'total_equipment': total_equipment,\r\n 'by_trade': by_trade.to_dict(),\r\n 'line_items': len(df),\r\n 'currency': line_items[0].work_item.currency if line_items else 'USD'\r\n }\r\n\r\n\r\n# Usage Example\r\ndef estimate_from_bim_model(\r\n model_path: str,\r\n qdrant_url: str,\r\n language: str = \"EN\",\r\n output_dir: str = \".\"\r\n) -> dict:\r\n \"\"\"Complete BIM to cost estimation workflow\"\"\"\r\n\r\n import subprocess\r\n from pathlib import Path\r\n\r\n # Step 1: Convert BIM to Excel\r\n print(\"Converting BIM model...\")\r\n subprocess.run([\r\n r\"C:\\DDC\\RvtExporter.exe\",\r\n model_path,\r\n \"complete\", \"bbox\"\r\n ])\r\n\r\n xlsx_path = Path(model_path).with_suffix('.xlsx')\r\n\r\n # Step 2: Load QTO data\r\n print(\"Loading quantity data...\")\r\n df = pd.read_excel(xlsx_path)\r\n\r\n # Step 3: Initialize estimator\r\n estimator = BIMCostEstimator(\r\n qdrant_url=qdrant_url,\r\n language=language\r\n )\r\n\r\n # Step 4: Generate estimate\r\n print(\"Generating cost estimate...\")\r\n line_items = estimator.estimate_from_qto(df)\r\n\r\n # Step 5: Generate report\r\n project_name = Path(model_path).stem\r\n result = estimator.generate_estimate_report(\r\n line_items=line_items,\r\n project_name=project_name,\r\n output_path=output_dir\r\n )\r\n\r\n print(f\"\\nEstimate Complete!\")\r\n print(f\"Total Cost: {result['currency']} {result['total_cost']:,.2f}\")\r\n print(f\"Excel Report: {result['excel_path']}\")\r\n\r\n return result\r\n\r\n\r\nif __name__ == \"__main__\":\r\n result = estimate_from_bim_model(\r\n model_path=r\"C:\\Projects\\Building.rvt\",\r\n qdrant_url=\"https://your-qdrant-instance.io\",\r\n language=\"DE\",\r\n output_dir=r\"C:\\Projects\\Estimates\"\r\n )\r\n```\r\n\r\n## n8n Workflow\r\n\r\nSee: `n8n_4_CAD_(BIM)_Cost_Estimation_Pipeline_4D_5D_with_DDC_CWICR.json`\r\n\r\n```yaml\r\nstages:\r\n - convert: RvtExporter β†’ XLSX\r\n - detect_project: LLM identifies project type\r\n - generate_phases: LLM creates construction phases\r\n - decompose: LLM breaks types into work items\r\n - vector_search: Qdrant finds CWICR matches\r\n - calculate: Qty Γ— Unit Price\r\n - validate: CTO review\r\n - report: HTML + Excel output\r\n```\r\n\r\n## Output Example\r\n\r\n```\r\n╔══════════════════════════════════════════════════════════════╗\r\nβ•‘ COST ESTIMATE SUMMARY β•‘\r\nβ•‘ Project: Office Building Berlin β•‘\r\nβ•‘ Date: 2026-01-24 β•‘\r\n╠══════════════════════════════════════════════════════════════╣\r\n\r\nTOTAL PROJECT COST: EUR 4,523,678.00\r\n───────────────────────────────────────────────────────────────\r\n Labor: EUR 1,847,234.00 (41%)\r\n Materials: EUR 2,312,456.00 (51%)\r\n Equipment: EUR 363,988.00 ( 8%)\r\n\r\nBY TRADE\r\n───────────────────────────────────────────────────────────────\r\n Concrete: EUR 1,234,567.00 (27%)\r\n Masonry: EUR 876,543.00 (19%)\r\n Steel Structure: EUR 654,321.00 (14%)\r\n MEP: EUR 543,210.00 (12%)\r\n Finishes: EUR 432,109.00 (10%)\r\n Other: EUR 782,928.00 (18%)\r\n\r\nCONFIDENCE ANALYSIS\r\n───────────────────────────────────────────────────────────────\r\n High (>0.85): 78%\r\n Medium (0.70-0.85): 18%\r\n Low (<0.70): 4%\r\n\r\nβ•šβ•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•β•\r\n```\r\n\r\n## Resources\r\n\r\n- **CWICR Repository**: https://github.com/datadrivenconstruction/OpenConstructionEstimate-DDC-CWICR\r\n- **Live Demo**: https://openconstructionestimate.com\r\n- **Qdrant**: https://qdrant.tech\r\n\r\n---\r\n\r\n*\"Resource-based costing separates physical quantities from volatile prices, enabling transparent and auditable estimates.\"*\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn75fhjxn1jz5xbgd9ggj0nrtd80q1dz\",\n \"slug\": \"bim-cost-estimation-cwicr\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1770474886541\n}","readmeExcerpt":"Skill: Bim Cost Estimation Cwicr Owner: datadrivenconstruction Summary: Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing. Tags: latest:2.1.0 Version history: v2.1.0 | 2026-02-13T21:08:30.955Z | auto - Added \"homepage\" and \"metadata\" fields to the skill manifest with relevant information. - Specified platform compatibility","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\r\nname: \"bim-cost-estimation-cwicr\"\r\ndescription: \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\"\r\nhomepage: \"https://datadrivenconstruction.io\"\r\nmetadata: {\"openclaw\":{\"emoji\":\"πŸ—οΈ\",\"os\":[\"darwin\",\"linux\",\"win32\"],\"homepage\":\"https://datadrivenconstruction.io\",\"requires\":{\"bins\":[\"python3\"],\"env\":[\"OPENAI_API_KEY\",\"QDRANT_URL\"]},\"primaryEnv\":\"OPENAI_API_KEY\"}}\r\n---\r\n\r\n# BIM Cost Estimation with DDC CWICR\r\n\r\nGenerate accurate cost estimates from BIM models using AI classification and the DDC CWICR construction cost database.\r\n\r\n## Business Case\r\n\r\n**Problem**: Traditional cost estimation:\r\n- Manual and time-consuming (weeks for detailed estimate)\r\n- Subjective and inconsistent between estimators\r\n- Requires specialized knowledge\r\n- Difficult to update with design changes\r\n\r\n**Solution**: Automated BIM-to-cost pipeline:\r\n- Extract quantities directly from model\r\n- AI classifies elements to work items\r\n- Vector search finds matching prices in CWICR\r\n- Complete estimate in hours, not weeks\r\n\r\n**ROI**: 80% reduction in estimation time, consistent methodology\r\n\r\n## System Architecture\r\n\r\n```\r\nβ”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”\r\nβ”‚ BIM TO COST ESTIMATION PIPELINE β”‚\r\nβ”œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€\r\nβ”‚ β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ BIM β”‚ β”‚ DDC β”‚ β”‚ AI β”‚ β”‚ DDC CWICR β”‚ β”‚\r\nβ”‚ β”‚ Model │────►│Converter│────►│ LLM │────►│ Vector Search β”‚ β”‚\r\nβ”‚ β”‚.rvt/.ifcβ”‚ β”‚ β”‚ β”‚ β”‚ β”‚ (Qdrant) β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β–Ό β–Ό β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ .xlsx β”‚ β”‚ Work β”‚ β”‚ Matched β”‚ β”‚\r\nβ”‚ β”‚ QTO β”‚ β”‚ Items β”‚ β”‚ Rates β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β”‚ β”‚ β”‚ β”‚\r\nβ”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”Όβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚\r\nβ”‚ β–Ό β”‚\r\nβ”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚\r\nβ”‚ β”‚ COST ESTIMATE β”‚ β”‚\r\nβ”‚ β”‚ β”‚ β”‚\r\nβ”‚ β”‚ β€’ By element β”‚ β”‚\r\nβ”‚ β”‚ β€’ By trade β”‚ β”‚\r\nβ”‚ "},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn75fhjxn1jz5xbgd9ggj0nrtd80q1dz\",\n \"slug\": \"bim-cost-estimation-cwicr\",\n \"version\": \"2.1.0\",\n \"publishedAt\": 1771016910955\n}"},{"path":"instructions.md","content":"You are a BIM-to-cost estimation assistant powered by the DDC CWICR database (55,719 work items across 9 languages). You automate the full pipeline from BIM model to cost estimate using AI classification and vector search.\n\nWhen the user asks to estimate costs from a BIM model:\n1. Guide them through the pipeline stages: BIM export -> QTO -> AI classification -> vector search -> cost calculation\n2. Explain the 10-stage pipeline (collect, detect project, generate phases, assign elements, decompose work, vector search, unit mapping, cost calculation, validation, aggregation)\n3. Help configure: language/region (EN, DE, RU, ES, FR, AR, HI, PT, ZH), Qdrant connection, OpenAI API for embeddings\n4. Present results by trade, phase, and element type\n\nWhen the user asks about CWICR database:\n1. Explain the database structure: 55,719 work items, 27,672 resources, 85 fields per item\n2. Help with vector search queries using text-embedding-3-large (3072 dimensions)\n3. Show matching results with confidence scores\n\n## Input Format\n- BIM model path (.rvt or .ifc) or pre-exported QTO data (.xlsx)\n- Target language/region for pricing\n- Qdrant URL and API credentials (environment variables)\n\n## Output Format\n- Cost estimate by trade (Concrete, Masonry, Steel, MEP, etc.)\n- Cost breakdown: labor, material, equipment percentages\n- Confidence analysis (high >0.85, medium 0.70-0.85, low <0.70)\n- Excel report with Summary, By Trade, and Detail sheets\n\n## Pipeline Stages\n| Stage | Description |\n|-------|-------------|\n| 0 | Collect BIM data from Revit/IFC |\n| 1-3 | AI detects project type, generates phases, assigns elements |\n| 4 | AI decomposes element types into work items |\n| 5 | Vector search matches work items to CWICR rates |\n| 6-7 | Unit mapping and cost calculation |\n| 8-9 | Aggregation and report generation |\n\n## Constraints\n- Network permission required for Qdrant vector database and OpenAI embeddings API\n- Filesystem permission required for BIM model reading and Excel export\n- subprocess.run() is used solely for invoking the DDC RvtExporter CAD conversion tool\n- All API keys must be loaded from environment variables, never hardcoded"},{"path":"claw.json","content":"{\n \"name\": \"bim-cost-estimation-cwicr\",\n \"version\": \"2.0.0\",\n \"description\": \"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.\",\n \"author\": \"datadrivenconstruction\",\n \"license\": \"MIT\",\n \"permissions\": [\"filesystem\", \"network\"],\n \"entry\": \"instructions.md\",\n \"tags\": [\"construction\", \"BIM\", \"estimation\", \"CWICR\", \"vector-search\", \"AI\", \"cost-management\"],\n \"models\": [\"claude-*\", \"gpt-*\"],\n \"minOpenClawVersion\": \"0.8.0\"\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing. Skill: Bim Cost Estimation Cwicr Owner: datadrivenconstruction Summary: Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing. Tags: latest:2.1.0 Version history: v2.1.0 | 2026-02-13T21:08:30.955Z | auto - Added \"homepage\" and \"metadata\" fields to the skill manifest with relevant information. - Specified platform compatibility","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1141,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T02:18:00.692Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T02:18:00.692Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:35:39.934Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation β€’ (~400 MCP servers for AI agents) β€’ AI Automation / AI Agent with MCPs β€’ AI Workflows & AI Agents β€’ MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}