setup-project-type
Skill4 starsChanged 8 months agoMITView on GitHub
Configure project type, location, codes, and technical preferences. Populates technical-preferences.md and recommends building-type specialists.
In this repository37 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- budget-checkSkill
- change-orderSkill
- deficiency-reportSkill
- design-decisionSkill
- design-reviewSkill
- design-systemSkill
- drawing-reviewSkill
- estimateSkill
- feasibility-studySkill
- gate-checkSkill
- handover-checklistSkill
- map-systemsSkill
- material-auditSkill
- milestone-reviewSkill
- occupancy-checklistSkill
- onboardSkill
- phase-planSkill
- project-stage-detectSkill
- punch-listSkill
- regulatory-adaptSkill
- retrospectiveSkill
- reverse-documentSkill
- revision-logSkill
- schedule-analysisSkill
- scope-checkSkill
- site-bulletinSkill
- site-inspectionSkill
- startSkill
- team-envelopeSkill
- team-handoverSkill
- team-interiorSkill
- team-mepSkill
- team-safetySkill
- team-siteSkill
- team-structuralSkill
The file
Files
When invoked:
- Ask about the project:
- Building type (commercial, residential, industrial, healthcare, mixed-use)
- Location (city, state, country)
- Climate zone (ASHRAE)
- Approximate size and height
- Determine applicable codes:
- IBC edition and local amendments
- Energy code (ASHRAE 90.1 / IECC)
- Fire code (IFC / NFPA)
- Accessibility (ADA / ICC A117.1)
- Plumbing code (UPC / IPC)
- Ask about structural preferences:
- Steel, concrete, timber, masonry, or hybrid
- Foundation type preferences
- Ask about MEP preferences:
- HVAC system type
- Electrical service requirements
- Ask about sustainability targets:
- Certification (LEED, WELL, none)
- Energy performance target
- Water conservation target
- Configure technical-preferences.md with all selections
- Recommend specialists: Which building-type specialist agent to use
- Suggest next steps:
/map-systemsto decompose into building systems/design-systemto begin per-system design/design-decisionfor key technical decisions
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

