CtrlK
BlogDocsLog inGet started
Tessl Logo

pylabrobot

Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.

75

1.20x
Quality

67%

Does it follow best practices?

Impact

87%

1.20x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/pylabrobot/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

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

This is an excellent skill description that clearly defines its niche in vendor-agnostic lab automation, lists specific equipment vendors and types as trigger terms, and explicitly states when to use it versus a competing skill. The inclusion of disambiguation guidance against opentrons-integration is a particularly strong feature that reduces conflict risk.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and domains: controlling equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps), unified programming across vendors, complex workflows, multi-vendor setups, and simulation.

3 / 3

Completeness

Clearly answers both 'what' (vendor-agnostic lab automation framework for controlling multiple equipment types with unified programming) and 'when' (explicit 'Use when' clause specifying multi-vendor setups, complex workflows, simulation). Also includes helpful disambiguation against opentrons-integration skill.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms a user in lab automation would use: specific vendor names (Hamilton, Tecan, Opentrons), equipment types (plate readers, pumps), and domain terms (lab automation, multi-vendor, simulation, workflows). These are highly natural keywords.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche in lab automation with clear vendor-agnostic positioning. The description even explicitly differentiates itself from a related skill (opentrons-integration), reducing conflict risk significantly.

3 / 3

Total

12

/

12

Passed

Implementation

35%

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

This skill is significantly over-verbose, spending most of its token budget on descriptive summaries of capabilities rather than actionable instructions. The code examples are a strength but are incomplete (missing imports) and lack validation steps critical for hardware automation. The progressive disclosure structure is reasonable in concept but undermined by the amount of redundant preview content in the main file.

Suggestions

Cut the 'When to Use This Skill' and 'Core Capabilities' sections down to a brief table or short list — the detailed descriptions belong in the reference files, not repeated here.

Add missing imports to code examples (e.g., TIP_CAR_480_A00, Cos_96_DW_1mL) to make them fully executable.

Add explicit validation/verification steps to workflows, such as checking `await lh.setup()` success, verifying tip pickup state, and using simulation before hardware execution as an integrated workflow step rather than just a best practice bullet.

Remove the 'Working with References' section entirely — it duplicates the Core Capabilities section's reference links without adding value.

DimensionReasoningScore

Conciseness

Extremely verbose. The 'When to Use This Skill' section lists 9 bullet points that are largely redundant with the overview. The 'Core Capabilities' section repeats information that Claude already knows or could find in the referenced files. The 'Working with References' section restates what was already listed in Core Capabilities. Significant padding throughout with explanatory text that doesn't add actionable value.

1 / 3

Actionability

The Quick Start and Common Workflows sections provide concrete, mostly executable code examples, but they're incomplete — the liquid transfer example references `TIP_CAR_480_A00` and `Cos_96_DW_1mL` without imports, and the plate reading workflow has a manual step comment without guidance. Best practices are generic advice rather than specific, actionable instructions.

2 / 3

Workflow Clarity

The workflows show sequential steps but lack validation checkpoints. For lab automation involving physical hardware, there are no verification steps (e.g., confirming setup succeeded, checking tip pickup, validating volumes). The 'Start with Simulation' best practice is mentioned but not integrated into the workflow examples as an explicit step. No error recovery or feedback loops for hardware operations.

2 / 3

Progressive Disclosure

References to 6 files in the references/ directory are clearly signaled, which is good structure. However, no bundle files were provided, so we can't verify these references exist. The SKILL.md itself is bloated with content that should either be in the reference files or omitted — the Core Capabilities section essentially previews each reference file's content at length, defeating the purpose of progressive disclosure.

2 / 3

Total

7

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
K-Dense-AI/claude-scientific-skills
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.