CtrlK
BlogDocsLog inGet started
Tessl Logo

ginkgo-cloud-lab

Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). Use when the user wants to run protein expression and purification (cell-free, E. coli, or Pichia), HiBiT or A280 or LabChip quantification, IVT mRNA/circRNA synthesis, thermal shift / developability assays, Echo-MS enzyme or analyte methods, SPR target onboarding, fluorescent pixel art, or otherwise interact with Ginkgo Cloud Lab services. Covers protocol selection, input preparation, pricing, and ordering workflows.

76

Quality

93%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A well-structured overview that uses token-efficient tables, actionable URLs, and a clean one-level reference hierarchy covering all linked protocols. Its one weakness is the ordering workflow, which lists steps but omits the explicit verification and feedback-loop checkpoints that a high-stakes batch submission warrants.

Suggestions

Add an explicit input-verification checkpoint before submission in the ordering workflow (e.g., confirm every sequence/sample in the uploaded template matches the configured count and passes FASTA/CSV format checks).

Add a brief validate→fix→resubmit feedback loop describing what to do when Ginkgo's feasibility report rejects inputs or returns a price/turnaround different from the catalog quote.

Note a pre-submit cost check (replicates × price × samples) so users confirm the quote before adding to cart, treating the order as the batch/destructive operation it is.

DimensionReasoningScore

Conciseness

A lean catalog of tables, a decision guide, a numbered ordering flow, and compact infrastructure notes; it does not explain concepts Claude already knows and every section earns its place.

3 / 3

Actionability

Gives concrete URLs, exact input file types (FASTA/CSV/XLSX), specific prices/turnarounds per protocol, and a precise 5-step ordering workflow rather than abstract direction.

3 / 3

Workflow Clarity

The ordering workflow is a clear numbered sequence but lacks explicit input-verification checkpoints and a validate→fix→resubmit feedback loop; for a batch submission to an external lab this gap caps clarity below 3.

2 / 3

Progressive Disclosure

SKILL.md is a concise overview whose catalog links each protocol to a one-level-deep reference file; all 17 referenced files resolve and content is appropriately split for navigation.

3 / 3

Total

11

/

12

Passed

Description

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.

A strong, third-person description that pairs concrete capabilities with an explicit 'Use when' trigger and a well-scoped niche. It names the platform, enumerates the supported protocol families, and avoids vague fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('Submit and manage protocols', 'protocol selection, input preparation, pricing, and ordering workflows') across a specific domain rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (submit/manage protocols, selection, input prep, pricing, ordering) and 'when' via a clear 'Use when the user wants to run...' trigger clause.

3 / 3

Trigger Term Quality

Covers natural domain terms a user would say ('protein expression and purification', 'HiBiT or A280 or LabChip quantification', 'IVT mRNA/circRNA synthesis', 'thermal shift', 'Echo-MS', 'SPR target onboarding', 'fluorescent pixel art') with good breadth.

3 / 3

Distinctiveness Conflict Risk

A clear niche (Ginkgo Cloud Lab on cloud.ginkgo.bio) with specific, domain-scoped triggers makes it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

12

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
K-Dense-AI/scientific-agent-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.