CtrlK
BlogDocsLog inGet started
Tessl Logo

replicator-pcb

Use before Project Replicator PCB source, layout, routing, DRC, fabrication, or PCB visual-review work.

59

Quality

74%

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/project-replicator/pcb/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 an exceptionally concrete, workflow-driven policy manual with executable examples, exact numeric rules, and strong validate-fix-rerun feedback loops. Its weaknesses are sheer length with some repetition across sections and several detailed sections that would be better split into the existing references directory.

Suggestions

Move the Verified Production Export Support and Electromechanical Footprints catalog lists into a reference file, keeping only the decision rules and pointer inline.

Deduplicate the footprint chirality and HotSwapKeySwitch guidance that appears in Authoring Rules, Electromechanical Footprints, and Useful Patterns, citing the footprints.md section once.

Trim narrative anecdotes to one-line rationale so the rules keep their force at a lower token cost.

DimensionReasoningScore

Conciseness

Almost every sentence carries non-derivable project-specific policy rather than concepts Claude already knows, but the ~500-line body includes repetition (footprint chirality and HotSwapKeySwitch guidance appear in multiple sections) and motivational anecdotes ('A mirrored microphone footprint ... reached JLCPCB order review') that could be trimmed. Anchor 3 (mostly efficient, some tightening possible); not 4 because the repetition and narrative padding across sections is noticeable.

3 / 5

Actionability

Fully executable throughout: copy-paste TSX/TS/JSON blocks, exact commands like `pcb.run(profile="check", reroute_nets=[...])`, numeric thresholds (3.5mm M2.5 keepout, 0.30mm traces, 0.6/0.3mm vias), and named diagnostics (`component_body_overlap`, `freerouting_reroute_target_unknown`). Matches anchor 5; the examples cover the common cases concretely.

5 / 5

Workflow Clarity

Numbered procedures with explicit validation checkpoints and feedback loops: the Preview Loop (run check, inspect previews, fix source, rerun), Connectivity Diagnosis (verify net/DSN/DRC evidence before editing), and Copper Pour Islands (one hypothesis at a time, rerun check, confirm no new island). Anchor 5's sequence-plus-error-recovery-loop pattern is met; not 4 because validation steps are explicit, not merely present.

5 / 5

Progressive Disclosure

Three real reference files are well-signaled and read at the right moments ('Read references/pcb-config.md before editing source/pcb.config.json'; 'See HARD RULE ... in references/footprints.md'), one level deep. However, long detailed policy sections (Verified Production Export Support, Electromechanical Footprints, Standard PCB Fabrication Bias) are inlined in SKILL.md where a reference file would fit. Anchor 4 (good structure, minor organization gaps); not 5 because substantial non-overview content lives in the main file.

4 / 5

Total

17

/

20

Passed

Description

56%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 has a strong explicit trigger clause with specific, natural PCB terminology and a clearly distinct niche. Its main weakness is that it never says what the skill does, leaving the 'what' half of a complete description unaddressed.

Suggestions

Add a 'what' clause before the trigger, e.g. 'Owns Replicator PCB layout, routing, DRC, and fabrication policy and provides the pcb.run check/release workflow. Use before ...'.

Include a few more natural trigger synonyms such as 'footprints', 'Gerbers', or 'netlist' to widen trigger coverage.

State the key deliverable outcome (e.g. 'finish board-design requests with a release package') so users can tell what using the skill produces.

DimensionReasoningScore

Specificity

Names the domain ('Project Replicator PCB') and six concrete work areas ('source, layout, routing, DRC, fabrication, or PCB visual-review work'), but no action verbs state what the skill does. Anchor 3 fits (domain plus limited concrete actions); not 4 because there is no list of specific capabilities, only trigger scopes.

3 / 5

Completeness

The 'when' is explicit ('Use before ... work') but the 'what' is entirely absent — the description never states what the skill provides (policy, references, commands). This matches anchor 2 ('only when is present without what'); it cannot be 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

Natural keywords users would say are present: 'PCB', 'layout', 'routing', 'DRC', 'fabrication', 'visual review'. A few natural terms are missing ('footprint', 'Gerber', 'netlist', 'board'), matching anchor 4 rather than 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

'Project Replicator' plus the scoped PCB work list carves a clear niche with distinct triggers and minimal conflict risk with generic PCB or tscircuit skills. Clearly anchor 5; not 4, since the project name disambiguates even closely related skills.

5 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (505 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

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.