replicator-cad

Parametric CAD modeling with build123d (Python) - enclosures, mechanical parts, assemblies. Builds a scene from cad/parts/*.py, exports STEP/GLB, renders PNG views for visual self-review, and prepares STL/3MF for printing. Use after PCB release (or directly for non-PCB products).

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Excellent skill body: dense, command-first, and entirely free of padding. It defines a tight file convention, gives verified executable commands for every workflow stage, embeds an explicit visual-feedback loop with numeric validation gates, and pushes all deep API/DFM knowledge to one-level references. The build/render/inspect/plate pipeline is fully reproducible from the page alone.

Dimension	Reasoning	Score
Conciseness	Lean throughout: no explanations of concepts Claude already knows, every line is a file convention, a runnable command, or a hard number ("Wall thickness for FDM enclosures: >= 1.6mm (2 perimeters at 0.4mm nozzle x2)"). Nothing reads as padding, matching anchor 5's 'every token earns its place'.	5 / 5
Actionability	Fully executable guidance: copy-paste bash invocations for all four scripts (verified against the scripts' actual argparse interfaces, including --part/--stl/--pairs/--printer presets) and a concrete make_screw_joint_v1 Python example with the kit's real signature and error class, covering the common cases per anchor 5.	5 / 5
Workflow Clarity	The core loop is explicitly sequenced with validation checkpoints: "edit one part file → rebuild → Read the PNG views → make the smallest next correction. Never infer success from the script exiting 0; the image is the evidence", plus numeric validation ("Run --pairs before claiming parts fit; a PNG can hide a 0.3 mm interference") and a printability check before plating — matching anchor 5's feedback-loop profile.	5 / 5
Progressive Disclosure	A clear overview body with one-level-deep, well-signaled references that all exist in the bundle: references/build123d-notes.md for API, four real scripts in scripts/, and each vendored know-how file named with a content description (e.g. "pitfalls.md (API mistakes table)"). Nothing that belongs in a separate file is inlined; matches anchor 5.	5 / 5
	Total	20 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete, and explicit about both capabilities and when to use it. It enumerates the full build-export-render-print pipeline with file formats and natural CAD/enclosure keywords. The only weaknesses are a missing mention of the inspection/collision-check capability and a few absent synonyms like "case" or "3D model".

Suggestions

Add the measurement capability to the description, e.g. "checks part clearances and collision interference", since cad_inspect.py is a core, explicitly-mandated workflow step in the body.

Include one or two common synonyms such as "case" or "housing" (for enclosures) and "3D printing" to broaden natural trigger coverage without adding length.

"Use after PCB release" describes pipeline position; also name the user-facing goal (e.g. "Use when designing a printable enclosure or mechanical part") so the trigger matches what a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists four concrete pipeline actions ("Builds a scene from cad/parts/*.py, exports STEP/GLB, renders PNG views", "prepares STL/3MF for printing") in a named domain, but omits the skill's measurement/collision-inspection capability, matching the 'several specific actions; minor gaps in coverage' anchor rather than the fully comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what (build scene from part files, export STEP/GLB, render PNG views, prepare STL/3MF) and when ("Use after PCB release (or directly for non-PCB products)"), covering both usage cases with concrete trigger phrasing — a clear anchor 5, not 4 where the when-clause is only partial.	5 / 5
Trigger Term Quality	Good natural keyword coverage ("CAD modeling", "enclosures", "mechanical parts", "assemblies", "printing") including file formats (STEP, GLB, STL, 3MF), but common synonyms like "case", "housing", or "3D model" are absent, fitting anchor 4 ('good keyword coverage; a few natural terms missing') rather than anchor 5's synonym-complete bar.	4 / 5
Distinctiveness Conflict Risk	Clear niche of parametric CAD with build123d in Python for enclosures/mechanical parts tied to a PCB-release pipeline; distinctive tooling terms (build123d, STEP/GLB, cad/parts) give minimal overlap risk with other skills, matching anchor 5. Uses third person throughout.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: JimmyPang02/open-replicator
Path: skills/replicator-cad/SKILL.md
Commit: 18436cc

Reviewed: 17 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.