agentleFS
MakeItEzzz555MakeItEzzz555/Gridline/skills/cad-bim-automation/SKILL.md

cad-bim-automation

Skill39 starsChanged 23 days agoMITView on GitHub

Safely automate repetitive architecture CAD/BIM/model/document workflows using available tools. Use for Revit, IFC, DWG, DXF, SVG, Blender, FreeCAD, batch edits, exports, naming, or model-data extraction.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify counts, units, geometry bounds, naming, missing objects/categories, export integrity, and deltas.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CAD/BIM Automation

Inspect formats/versions, available tools/APIs, source-vs-issued status, units, coordinates/origin, levels/grids, layers/categories, naming, and revisions.

Choose the least destructive method: read/report → export to new file → supported API/script → original edit only with explicit permission. For proprietary formats, produce an application-native workflow rather than pretending an unsupported direct edit occurred.

Batch protocol: inventory → dry run → sample → validate → full run → post-change audit.

Verify counts, units, geometry bounds, naming, missing objects/categories, export integrity, and deltas. Never alter surveyed coordinates, structural geometry, life-safety elements, or issued information outside explicit scope and review.

Opt-in local Blender prototype (separately installed skill): if a trusted Blender executable is available and the user requests a NEW conceptual 3D scene, discover the installed architectural-drawing-generation skill first. Its own scripts/blender_native.py (worker and validator included) is the portable entry point; run doctor, then build SPEC.json NEW_OUT from that skill directory. Do not assume the standalone cad-bim-automation skill contains Blender code or repo docs. In a Gridline checkout, scripts/blender_native.py is merely a convenience launcher; docs/BLENDER_NATIVE_BRIDGE.md documents its limits. If the drawing skill is absent, report a missing dependency rather than inventing a path. This bridge creates editable conceptual mesh geometry and .glb with native readback; it cannot edit live models, install MCPs, reconstruct images, establish IFC/AutoCAD compliance or approve drawings. Ask for missing reference measurements and report unsupported details.

Optional signed source workflow: the drawing skill also supplies component_state.py for typed component/level/wall/opening/room proposals, exact Ed25519 owner approvals, immutable revisions, indexed impacts, stale conflicts, revalidated disjoint merges and approved restore. Keep owner keys outside the agent and never self-sign as a real owner. archimesh_components.py build --state-db DB --owner-key-sha256 PIN requires the signed current source and new output only; component_ifc.py additionally requires the state database, requirements and trusted source/owner pins. These source/file operations do not authorize live Revit/AutoCAD writes, replace native transactions/rollback, establish a complete external drawing dependency graph or close the general #15 gate. Read the drawing skill's actual commands/limits; do not assume this standalone automation skill contains its scripts.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.