forgecad-grade-model
starsforks
How to install forgecad-grade-model?
forgecad/forgecad-public-kit/forgecad-grade-model
$npx -y skills add ForgeCAD/forgecad-public-kit --skill forgecad-grade-modelGrade a ForgeCAD or CAD-as-code model against a requirement, brief, prompt, reference, or acceptance criteria with evidence and a 0-10 score.
SKILL.md
| 1 | # Grade Model |
| 2 | |
| 3 | Grade the delivered model against the requirement, not against what could be fixed later. Never edit the model unless the user explicitly requests repairs — then record the baseline grade first, change, and re-grade. |
| 4 | |
| 5 | ## Workflow |
| 6 | |
| 7 | 1. **Extract the requirement** into a checklist, must-haves separate from nice-to-haves. If the brief is vague, grade the most reasonable literal interpretation and mark unverifiable items `Unknown`. |
| 8 | 2. **Run the model**: `forgecad run <model>.forge.js` (in the ForgeCAD repo use the local build, `node dist-cli/forgecad.js run ...`). If it fails to execute, stop and apply the caps. |
| 9 | 3. **Render** at least `iso`, `front`, `right`, `top` to a scratch dir; add views (back, bottom, close-up, section) when the model is asymmetric, hollow, mechanical, or likely to hide mistakes. |
| 10 | 4. **Open and look at every PNG** — never score from command output alone. Check silhouette, proportions, required features, part boundaries, interfaces, and whether the model reads as the requested artifact from more than one angle. |
| 11 | 5. **Inspect** whenever hidden internals, fit, wall thickness, or assembly behavior are central to the brief — grading without inspecting them caps the score. Delegate evidence choice, commands, and manifest reading to the `forgecad-inspect-model` skill. Findings (unexpected collisions, thin regions, floating bodies, wrong component counts) are evidence, not warnings to wave away. |
| 12 | 6. **Score**: fill the rubric, apply caps, give a final 0-10 in whole or `.5` increments. Unknowns count against the score. |
| 13 | |
| 14 | ## Rubric |
| 15 | |
| 16 | | Dimension | Points | What To Look For | |
| 17 | | --- | ---: | --- | |
| 18 | | Requirement fit | 4 | Satisfies the stated must-haves, captures the intended object/function, no drift into a generic substitute. | |
| 19 | | Geometric completeness | 2 | Correct silhouette, proportions, visible details, part boundaries, internal structure when required, no missing major components. | |
| 20 | | Mechanical/manufacturing plausibility | 2 | Believable materials/process, real interfaces, clear load paths, fasteners/seats/clearances where needed, no impossible assembly. | |
| 21 | | Validation health | 1 | Runs cleanly, renders from multiple views, targeted inspections reveal no major unaddressed issues. | |
| 22 | | Code/model quality | 1 | Parametric clarity, readable organization, meaningful names, no debug junk, appropriate ForgeCAD APIs. | |
| 23 | |
| 24 | Anchors: 9-10 = evidence-backed match for the brief; 7-8 = recognizable and mostly complete, fixable gaps; 5-6 = main idea only; below 5 = broken or loosely related. |
| 25 | |
| 26 | ## Evidence Caps |
| 27 | |
| 28 | Maximum scores, applied after the rubric: |
| 29 | |
| 30 | - Model does not execute: max `2`. |
| 31 | - Executes but cannot be rendered: max `4`. |
| 32 | - No rendered images visually inspected: max `5`. |
| 33 | - Only one flattering view inspected: max `6`. |
| 34 | - A must-have requirement is absent: max `6`. |
| 35 | - Visually recognizable but physically impossible for the requested use: max `6`. |
| 36 | - Internals, fit, walls, or assembly central to the brief but uninspected: max `7`. |
| 37 | - Multi-part assembly violates the ForgeCAD component model — sibling imports, assembly-space coordinates inside parts, structural `translate()` placement, missing connector mates, or parent/child data flow confusion: max `7`; max `6` when the violation makes the assembly brittle or mechanically wrong. |
| 38 | - Inspection finds unexpected collisions, floating bodies, critical thin walls, or wrong connectivity: max `6`; max `5` when the defect invalidates the main function. |
| 39 | - Delivered as a finished product/prototype but presented with default flat lighting (no `scene()` rig), a generically colorful or material-false palette, or teaching-diagram styling: max `8`. Does not apply when the brief asks for a blockout or bare technical study. |
| 40 | - Any score relying on an assumption the evidence cannot verify: mark it `Unknown`, never score above `8`. |
| 41 | |
| 42 | ## Report Format |
| 43 | |
| 44 | ```markdown |
| 45 | Score: N / 10 |
| 46 | |
| 47 | Requirement checklist: |
| 48 | | Item | Result | Evidence | |
| 49 | | --- | --- | --- | |
| 50 | | ... | Pass/Partial/Fail/Unknown | render/inspection/file evidence | |
| 51 | |
| 52 | Evidence reviewed: run outcome; views inspected; inspection highlights. |
| 53 | Why this score: decisive strengths and defects. |
| 54 | Caps applied: list, or `None`. |
| 55 | Next fixes: the 2-5 highest-leverage improvements. |
| 56 | ``` |
| 57 | |
| 58 | ## Grading Rules |
| 59 | |
| 60 | - A beautiful render with missing functional geometry is not a high score. |
| 61 | - Grade the default returned model unless the user names a parameter set or variant. |
| 62 | - No points for comments, labels, or intentions absent from the geometry. |
| 63 | - Decorative screws, floating labels, and teaching-diagram callouts are not real mechanical interfaces. |
| 64 | - For multi-part assemblies, require the component model: parts build locally at origin, expose connectors/metadata, the parent positions them, and inter-part data flows through parent props and r |
People who liked this also viewed
6 picksType
- 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 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- 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 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
