CtrlK
BlogDocsLog inGet started
Tessl Logo

cad-workbench

Use for persistent, visual, short-loop CAD modeling with cad.open, cad.add_part, cad.edit_part, cad.place, cad.import, cad.delete, cad.look, cad.inspect, Host-owned CAD Review, and cad.export.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./reference/replicator-original/me/cad-workbench/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is a tight, highly actionable CAD-workflow guide with strong validation and error-recovery loops. Its main limitation is that everything lives in one inline file with snippet-style rather than full runnable examples.

Suggestions

Provide one complete end-to-end example script (open -> add_part -> inspect -> export) to make the actionability copy-paste ready.

If the skill grows, split the Python Cell Contract and Project PCB inputs into reference files linked from the overview to improve progressive disclosure.

Tighten the Placement rationale paragraphs to lift conciseness toward a 5.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (build123d symbols, B-rep, param/publish) without explaining basic concepts, with only minor prose that could be trimmed in the Placement and Python Cell Contract sections.

4 / 5

Actionability

Executable publish/param/Box snippets and specific cad.edit action="..." calls give concrete guidance, but the examples are fragments rather than full end-to-end copy-paste scripts, leaving minor gaps.

4 / 5

Workflow Clarity

The numbered Loop sequences explicit validation checkpoints (inspect preview before continuing, stop and read scene), feedback loops for previewError and stale_build, and a required handoff export for destructive deletes.

5 / 5

Progressive Disclosure

No bundle files exist, so the skill is a single well-organized document with a clear opening overview and section headers; content is all inline with no external references, which is appropriate but not a 5 since it exceeds the simple-skill line count.

4 / 5

Total

17

/

20

Passed

Description

76%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.

The description is highly specific and distinct, naming many concrete cad.* actions and an explicit 'Use for' trigger. Its weakness is trigger-term naturalness: the phrasing leans on jargon and tool names rather than terms a user would naturally say.

Suggestions

Add a concrete user-facing trigger phrase, e.g. 'Use when the user asks to model, edit, or assemble CAD parts visually in short loops'.

Include natural synonyms users might say (e.g. 'CAD design', '3D modeling', 'model this part') alongside the cad.* tool list.

Consider trimming 'persistent, visual, short-loop' jargon or relegating it to the body so the description reads as a natural trigger.

DimensionReasoningScore

Specificity

Lists nine concrete cad.* actions (cad.open, cad.add_part, cad.edit_part, cad.place, cad.import, cad.delete, cad.look, cad.inspect, cad.export) plus Host-owned CAD Review, giving comprehensive concrete-action coverage rather than vague language.

5 / 5

Completeness

It states both what (CAD modeling via the listed tools) and when ('Use for persistent, visual, short-loop CAD modeling'), but the 'when' describes a working mode rather than offering concrete user-trigger phrases, so it is not a full 5.

4 / 5

Trigger Term Quality

'CAD modeling' is a natural user term, but 'persistent, visual, short-loop' is jargon and the cad.* tool names are not phrases users naturally say; common synonyms and file extensions are missing.

3 / 5

Distinctiveness Conflict Risk

The CAD-modeling niche anchored by specific cad.* tool triggers is clearly distinct from other skills with minimal overlap risk.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
JimmyPang02/open-replicator
Reviewed

Table of Contents

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.