agentsclimarketplace

Garment ready check

Skill wjlgatech/design-anything/skills/garment-ready-check

Any design intent in (text, picture) → execution-ready 3D blueprint out — construction- and 3D-print-verified. Game design · simulation · architecture (3DCP+AI) · interior · landscape.

Install
npx -y skills add wjlgatech/design-anything --skill garment-ready-check

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Run the pattern gate on a garment marker (pieces placed on fabric): valid pieces + grain, fabric fit, seam allowance, marker efficiency (zero-waste as a number), human-fit tables. Trigger: "is this pattern cuttable", "check my marker", "validate this sewing pattern". NOT a drape simulator and NOT a grading service (yet).

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.9 KB, as published. Nobody here has run it

garment-ready-check

When to use

Any sewing-pattern marker claiming to be cut-and-sew ready — generated by brief-to-blueprint or transcribed from an existing pattern.

What it does

  1. F1 pieces: valid polygons, unique names, grain angle declared (0/45/90).
  2. F2 fabric-fit: every piece inside the fabric width, no bbox overlaps.
  3. F3 seam allowance ≥ data/garment.yml minimum.
  4. F4 marker efficiency ≥ the zero-waste floor.
  5. F5 human-fit: declared dimensions inside the garment's fit table; unknown garment types are not measured ⇒ fail.
  6. F6 seam/symmetry pairs: declared pairs match in length within tolerance (grading breaks symmetric pieces first).
  7. Factory export on request: python3 pipeline/dxf_aama.py marker.json out.dxf — the AAMA subset every pattern CAD imports, round-trip verified.

Example

python3 examples/apron/generate.py marker.json
python3 pipeline/pattern_gate.py marker.json --json

Verification (eval-with-teeth)

Success may be declared ONLY when the gate exits 0. The gate is held by tests that mutate the golden apron eight known-bad ways and assert each fails:

python3 -m pytest tests/test_pattern_gate.py -q

Safety

A READY marker cuts; it does not guarantee drape, sewability order, or fit beyond the declared dimensions — make a muslin (the garment world's prototype). Overlap check is bbox-level, not exact nesting; stated in every report.

Cross-runtime

Python + PyYAML; exit codes gate any CI.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.