forgecad-reconstruct-cad-file

Name: forgecad-reconstruct-cad-file
Author: ForgeCAD

906stars102forks

How to install forgecad-reconstruct-cad-file?

forgecad/forgecad-public-kit/forgecad-reconstruct-cad-file

$npx -y skills add ForgeCAD/forgecad-public-kit --skill forgecad-reconstruct-cad-file

Installs into the current project.

Summary

Reconstruct a readable parametric ForgeCAD model from an existing CAD or mesh file such as STL, OBJ, 3MF, STEP, or STP.

Files · 1

View on GitHub

SKILL.md

1	# Reconstruct CAD File
2
3	The reference asset is evidence, not the deliverable. The deliverable is a readable, parametric `.forge.js` model that runs, renders, and scores well against the source. Never return `Import.mesh()`/`Import.step()` of the source as the final model unless the user explicitly asks for an import wrapper — imports are for measurement, rendering, and scoring only.
4
5	Routing: user wants to KEEP the file as a live component and design around it (bracket, enclosure, mating assembly) → `forgecad-build-model` (Imported Parts section), not this skill; prepared benchmark/RL episodes → use the task-local benchmark instructions, not the public skill library; inspection-bundle interpretation → `forgecad-inspect-model`; independent grading after reconstruction → `forgecad-grade-model`; API and command reference → `forgecad` skill + CLI.md.
6
7	## Workflow
8
9	1. Inspect the source directly — the CLI reads CAD/mesh files as inputs, no wrapper script. Gather four evidence types: `ls --long` stats, an iso render, per-object views, sampled sections (invocations in CLI.md; when sharing a renderer server via `--port`, run renders sequentially).
10	2. 3MF: enumerate every build item before scoring — hidden multi-part structure is a common miss. Item ref syntax: `Import.mesh` docs.
11	3. Reconstruction Brief before modeling: what must be exact vs. approximate vs. parametric; symmetry, origin, key reference planes; likely manufacturing process; scoring tolerance and alignment policy.
12	4. Blockout first. Match bbox and main masses, then add features. Model real geometry with blueprint-first APIs — never vertex-chase a faceted copy.
13	5. Compare numerically — the core loop:
14
15	```bash
16	forgecad compare 3d path/to/source.stl path/to/candidate.forge.js \
17	--samples 3000 --json --output /tmp/<slug>-score.json
18	```
19
20	6. Iterate coarse to fine: bbox/placement → main volumes/silhouette → holes/bosses/ribs/shells → edge treatments → small details.
21
22	## Reading the Score
23
24	Alignment: start `--align none`. Use `--align center` only when origins clearly differ but scale and orientation match. Use `--align center-scale` only for exploratory diagnosis — it hides dimensional errors.
25
26	\| Signal \| Diagnosis \|
27	\|---\|---\|
28	\| Low coverage \| Missing or extra surface \|
29	\| High RMS \| Broad proportional mismatch \|
30	\| High p95/max \| Localized outlier feature (protrusion, hole) \|
31	\| Bounds delta \| Size, origin, or scale mismatch \|
32	\| Volume delta \| Mass, shell, cutout, or scale mismatch \|
33
34	Calibration: 95+ simple prismatic/revolved parts, 90+ ordinary mechanical parts with fillets/cutouts, 80+ acceptable for organic, faceted, or underdetermined sources. Always report raw rms, p95, max, coverage, bounds delta, and volume delta — a high overall score with a large max can hide a missing local feature.
35
36	Faceted sources: decide whether tessellation itself is evidence. Matching low-poly faceting raises the score but reduces parametric clarity — prefer analytic intent unless faceting is part of the artifact or required by the acceptance criteria.
37
38	## Done Criteria
39
40	The final model must run, render, re-compare at `--samples 5000`, and pass an `inspect compare overlay`. Add targeted inspects (`forgecad-inspect-model`) when the object is multi-part, hollow, thin-walled, or surface-sensitive. Report: source and candidate paths, score JSON path, final metrics, and every known mismatch classified as intentional simplification or remaining work.

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

forgecad-reconstruct-cad-file

906stars102forks

View on GitHub

How to install forgecad-reconstruct-cad-file?

forgecad/forgecad-public-kit/forgecad-reconstruct-cad-file

$npx -y skills add ForgeCAD/forgecad-public-kit --skill forgecad-reconstruct-cad-file

Installs into the current project.

Summary

Reconstruct a readable parametric ForgeCAD model from an existing CAD or mesh file such as STL, OBJ, 3MF, STEP, or STP.

Files · 1

View on GitHub

SKILL.md

1	# Reconstruct CAD File
2
3	The reference asset is evidence, not the deliverable. The deliverable is a readable, parametric `.forge.js` model that runs, renders, and scores well against the source. Never return `Import.mesh()`/`Import.step()` of the source as the final model unless the user explicitly asks for an import wrapper — imports are for measurement, rendering, and scoring only.
4
5	Routing: user wants to KEEP the file as a live component and design around it (bracket, enclosure, mating assembly) → `forgecad-build-model` (Imported Parts section), not this skill; prepared benchmark/RL episodes → use the task-local benchmark instructions, not the public skill library; inspection-bundle interpretation → `forgecad-inspect-model`; independent grading after reconstruction → `forgecad-grade-model`; API and command reference → `forgecad` skill + CLI.md.
6
7	## Workflow
8
9	1. Inspect the source directly — the CLI reads CAD/mesh files as inputs, no wrapper script. Gather four evidence types: `ls --long` stats, an iso render, per-object views, sampled sections (invocations in CLI.md; when sharing a renderer server via `--port`, run renders sequentially).
10	2. 3MF: enumerate every build item before scoring — hidden multi-part structure is a common miss. Item ref syntax: `Import.mesh` docs.
11	3. Reconstruction Brief before modeling: what must be exact vs. approximate vs. parametric; symmetry, origin, key reference planes; likely manufacturing process; scoring tolerance and alignment policy.
12	4. Blockout first. Match bbox and main masses, then add features. Model real geometry with blueprint-first APIs — never vertex-chase a faceted copy.
13	5. Compare numerically — the core loop:
14
15	```bash
16	forgecad compare 3d path/to/source.stl path/to/candidate.forge.js \
17	--samples 3000 --json --output /tmp/<slug>-score.json
18	```
19
20	6. Iterate coarse to fine: bbox/placement → main volumes/silhouette → holes/bosses/ribs/shells → edge treatments → small details.
21
22	## Reading the Score
23
24	Alignment: start `--align none`. Use `--align center` only when origins clearly differ but scale and orientation match. Use `--align center-scale` only for exploratory diagnosis — it hides dimensional errors.
25
26	\| Signal \| Diagnosis \|
27	\|---\|---\|
28	\| Low coverage \| Missing or extra surface \|
29	\| High RMS \| Broad proportional mismatch \|
30	\| High p95/max \| Localized outlier feature (protrusion, hole) \|
31	\| Bounds delta \| Size, origin, or scale mismatch \|
32	\| Volume delta \| Mass, shell, cutout, or scale mismatch \|
33
34	Calibration: 95+ simple prismatic/revolved parts, 90+ ordinary mechanical parts with fillets/cutouts, 80+ acceptable for organic, faceted, or underdetermined sources. Always report raw rms, p95, max, coverage, bounds delta, and volume delta — a high overall score with a large max can hide a missing local feature.
35
36	Faceted sources: decide whether tessellation itself is evidence. Matching low-poly faceting raises the score but reduces parametric clarity — prefer analytic intent unless faceting is part of the artifact or required by the acceptance criteria.
37
38	## Done Criteria
39
40	The final model must run, render, re-compare at `--samples 5000`, and pass an `inspect compare overlay`. Add targeted inspects (`forgecad-inspect-model`) when the object is multi-part, hollow, thin-walled, or surface-sensitive. Report: source and candidate paths, score JSON path, final metrics, and every known mismatch classified as intentional simplification or remaining work.

People who liked this also viewed

6 picks

Type