Agent skill · data analytics · datadrivenconstruction
semantic-search-cwicr
Semantic search in the DDC CWICR construction cost database using vector embeddings (BGE-M3, 1024-dim, per-language Qdrant collections). Find similar work items and resources for cost estimation across 8 national bases and 30 markets in 26 languages.
Why this skill is useful
Provides domain-specific knowledge for semantic search using vector embeddings in construction cost estimation.
What it needs
Requires openai, pandas, python3, qdrant-client installed locally. Requires openai account access. About 3k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
Semantic Search in DDC CWICR Database Business Case Problem Statement Construction cost estimation requires finding relevant work items from large databases. Traditional keyword search fails when: Users describe work in natural language Terminology varies across regions and languages Similar work items have different naming conventions Solution DDC CWICR provides pre-computed embeddings (BAAI/bge-m3, 1024 dimensions) enabling multilingual semantic search across 8 national bases (78,228 positions) plus the 30-market global base in 26 languages, with 48 PPP-repriced market catalogs per national base. Business Value 90% faster work item lookup compared to manual search Multi-language: Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, English, Finnish, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Mongolian, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swedish, Thai, Turkish, Vietnamese Higher accuracy by finding semantically similar items, not just keyword matches Data landscape (2026) National base Region id Positions --- --- --- Turkey (Birim Fiyat) TRNATIONAL 22,704 China (Beijing Dinge + Bole) ZHCHINA 11,312 Brazil (SINAPI) BRNATIONAL 9,723 Spain (BCCA Andalucía) ESANDALUCIA 6,453 Italy (Prezzario Toscana) ITTOSCANA 5,836 Vietnam (Dinh Muc) VNNATIONAL 4,299 Indonesia (AHSP) IDNATIONAL 2,784 Greece (GGDE) GRNATIONAL 2,647 Each base ships the 95-column CWICR master schema (ratecode, rateoriginalname, ratefinalname, rateunit, totalcostperposition, classification hierarchy collection/department/section/subsection/category, resource component lines with ismaterial/ismachine/islabor flags) plus 26 language editions and 48 markets/.csv catalogs. Latest data release: v0.4.0 (see releases). Technical Implementation Prerequisites Collections (2026) The vector store uses BAAI/bge-m3 (1024-dim dense + sparse + colbert in one forward pass, MIT license, 100+ languages). Production collections are named cwicr{LANG}v3 (e.g. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/semantic-search-cwicr