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

91%

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

92%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.

An information-dense, highly actionable body with explicit validation feedback loops and well-structured one-level-deep references to verified bundle files. The only minor gap is a slightly descriptive live-workbench paragraph that could be trimmed for token efficiency.

Dimension	Reasoning	Score
Conciseness	Dense and assumes CAD competence (no basic-concept padding), with every section earning its place; minor trimmable over-explanation in the "Live workbench" feature-list sentence keeps it just below a 5.	4 / 5
Actionability	Fully executable copy-paste bash commands with real flags and a complete screwjoint Python example, plus exact clearance/thickness numbers covering the common cases.	5 / 5
Workflow Clarity	Explicit feedback loop ("edit → rebuild → Read the PNG views → smallest next correction") with validation gates ("Run --pairs before claiming parts fit"; "Verify printability in the PNG views first") and an admonition not to infer success from exit code.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to the real references/build123d-notes.md and scripts, plus a per-feature "Deep know-how" file list for navigation; content is appropriately split.	5 / 5
	Total	19 / 20 Passed

Description

91%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, concrete description that names the domain and multiple specific actions with good keyword and file-extension coverage. The only weakness is the trigger guidance being framed as a workflow stage rather than natural user-intent phrases.

Suggestions

Reframe the "Use after PCB release (or directly for non-PCB products)" clause to also include natural user-intent triggers, e.g. "Use when designing enclosures, mechanical parts, or assemblies for 3D printing, or when the user asks to model/export CAD geometry."

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Builds a scene from cad/parts/*.py", "exports STEP/GLB", "renders PNG views for visual self-review", "prepares STL/3MF for printing") with comprehensive pipeline coverage.	5 / 5
Completeness	Both what and when are present with an explicit "Use after PCB release (or directly for non-PCB products)" clause, but the when is a workflow-stage trigger rather than concrete user-intent phrases like "when the user wants to model an enclosure".	4 / 5
Trigger Term Quality	Comprehensive natural keywords ("CAD", "enclosures", "mechanical parts", "assemblies", "printing") plus file-format synonyms/extensions (STEP, GLB, STL, 3MF) that a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (parametric CAD with build123d for enclosures/parts/assemblies) with distinct triggers and even an explicit boundary ("load the step-parts skill"), giving minimal conflict risk.	5 / 5
	Total	19 / 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: 1 day 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.