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.

Quality

86%

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

72%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.

Well-structured, lean overview with excellent progressive disclosure and mostly actionable guidance; the main gap is the absence of an explicit validation/verification checkpoint in the batch ordering workflow.

Suggestions

Add a validation step to the General Ordering Workflow (e.g., 'Review the returned feasibility report and price quote; if any target is flagged infeasible, adjust parameters/inputs and resubmit before proceeding to cart').

Trim the instrument model-number list in 'Key Infrastructure' to the categories that affect protocol selection, or move the full inventory into a reference file.

Make the post-submission feedback loop explicit — note what to check in the feasibility report and when to contact cloud@ginkgo.bio versus resubmit.

Dimension	Reasoning	Score
Conciseness	Dense, well-organized tables and Ginkgo-specific context (RACs, EstiMate, instrument list) with little padding; the instrument-model enumeration in 'Key Infrastructure' is minor over-detail that could be trimmed, keeping it just below the top anchor.	4 / 5
Actionability	Concrete URLs, a 5-step ordering workflow, a decision-tree 'Choosing a Protocol' section, and per-protocol reference links give mostly executable guidance; it stops short of 5 only because the web-UI interaction has no literal copy-paste commands.	4 / 5
Workflow Clarity	The ordering workflow is a clear 5-step sequence, but submitting protocols is a batch/cost-incurring operation with no explicit validation or verification checkpoint (e.g., review the feasibility report and resubmit if infeasible), so per the rubric cap it cannot exceed 3.	3 / 5
Progressive Disclosure	SKILL.md is a concise catalog overview pointing to 17 verified, one-level-deep reference files via clearly signaled link tables, with detail appropriately split out — matching the top anchor.	5 / 5
	Total	16 / 20 Passed

Description

100%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, model description: concrete actions, comprehensive natural trigger terms, explicit 'Use when' guidance, and a distinctive vendor niche with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Submit and manage protocols', 'protocol selection, input preparation, pricing, and ordering workflows') alongside a comprehensive enumeration of supported protocol types, matching the 'comprehensive coverage' anchor.	5 / 5
Completeness	Explicitly answers 'what' (submit and manage protocols on Ginkgo Cloud Lab) and 'when' via a concrete 'Use when the user wants to run...' clause enumerating triggers, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural terms a user would actually say — 'protein expression and purification', 'cell-free', 'E. coli', 'Pichia', 'HiBiT', 'A280', 'LabChip', 'IVT mRNA/circRNA', 'thermal shift', 'Echo-MS', 'SPR target onboarding', 'fluorescent pixel art' — including synonyms and specific assay names.	5 / 5
Distinctiveness Conflict Risk	A clear Ginkgo Cloud Lab niche with vendor-specific triggers (cloud.ginkgo.bio, RACs, named assays), giving it minimal overlap risk with other skills.	5 / 5
	Total	20 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/ginkgo-cloud-lab/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.