/ Каталог / Песочница / DDC_Skills_for_AI_Agents_in_Construction
← Все серверы ↗ GitHub
● Сообщество datadrivenconstruction ⚡ Сразу

DDC_Skills_for_AI_Agents_in_Construction

автор datadrivenconstruction · datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

221 construction-industry skills for Claude Code — BIM analysis, cost estimation, scheduling, and document control in one bundle.

DDC Skills for AI Agents in Construction is a domain-heavy bundle from Data Driven Construction covering BIM (IFC, Revit data), cost estimation, schedule analysis, and document workflows. Claude picks up construction vocabulary, units, and typical deliverables so it can actually be useful on job-site data instead of generic sheet munging.

▶ Смотреть демо 📦 Установить 💡 Сценарии

Зачем использовать

Ключевые функции

Живое демо

Как выглядит на практике

ddc-skills-for-ai-agents-in-construction-skill.replay ▶ готово
0/0

Установка

Репозиторий автора · Официальная документация Claude Skills

Сценарии использования

Реальные сценарии: DDC_Skills_for_AI_Agents_in_Construction

How to audit a BIM IFC model for basic data quality

👤 BIM coordinators and VDC teams ⏱ ~60 min advanced

Когда использовать: You receive an IFC file from a consultant and need a quality check.

Поток
  1. Parse the IFC
    Audit model.ifc — count entities by class, find missing Psets, flag orphan geometry.✓ Скопировано
    → Entity counts + quality flags
  2. Check naming and classification
    Verify wall and room naming against our company standard.✓ Скопировано
    → Per-element conformance report
  3. Produce a coordinator-ready report
    Generate an issue list the consultant can act on.✓ Скопировано
    → Ordered issue list

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

Подводные камни
  • Huge IFC files exceed memory — Stream-parse rather than load full tree; or pre-filter by spatial structure
Сочетать с: filesystem

Produce a quick order-of-magnitude cost estimate

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

Когда использовать: Early-phase numbers for a concept before you commit to a detailed estimate.

Поток
  1. Describe the project
    Concrete frame office, ~12,000 sqm, Tier-1 city, shell-only. Give me a per-sqm cost range.✓ Скопировано
    → Range with the assumptions stated
  2. Break into WBS
    Break the estimate into WBS sections with % allocations.✓ Скопировано
    → Top-level WBS with line items
  3. Flag risks
    List the top 5 cost risks for this concept.✓ Скопировано
    → Risks with impact

Итог: A defensible concept estimate ready for internal review.

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

Review a construction schedule for common issues

👤 Schedulers and PMs ⏱ ~30 min intermediate

Когда использовать: You got a schedule from a subcontractor and need to check for the obvious red flags.

Поток
  1. Feed the schedule
    Review schedule.xlsx — flag missing logic, negative float, open ends, and unrealistic durations.✓ Скопировано
    → Categorized findings
  2. Prioritize
    Rank by impact on completion date.✓ Скопировано
    → Sorted list

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

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

Комбинации

Сочетайте с другими MCP — эффект x10

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

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

Walk project/ and produce a weekly coordination packet.✓ Скопировано

Инструменты

Что предоставляет этот MCP

ИнструментВходные данныеКогда вызыватьСтоимость
bim-audit IFC path On any incoming IFC ifcopenshell compute
cost-estimation project concept Early phase 0
schedule-review schedule export Sub-submittal review 0
document-control RFIs/submittals/COs Project admin 0

Стоимость и лимиты

Во что обходится

Квота API
none
Токенов на вызов
5–30k per task
Деньги
free at skill level
Совет
Use only the sub-skills relevant to your role — this bundle is wide

Безопасность

Права, секреты, радиус поражения

Хранение учётных данных: none
Исходящий трафик: none

Устранение неполадок

Частые ошибки и исправления

ifcopenshell install fails

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

Проверить: python -c 'import ifcopenshell; print(ifcopenshell.version)'
Estimates are wildly off

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

Альтернативы

DDC_Skills_for_AI_Agents_in_Construction в сравнении

АльтернативаКогда использоватьКомпромисс
generic csv-data-summarizer-claude-skillYour construction data is CSV and you don't need BIM semanticsNo domain knowledge

Ещё

Ресурсы

📖 Читать официальный README на GitHub

🐙 Открытые задачи

🔍 Все 400+ MCP-серверов и Skills