Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Ginkgo Cloud Lab · k-dense-ai | DecimalAI

k-dense-ai/ginkgo-cloud-lab

SkillScore91Maintained

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

scienceby k-dense-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/k-dense-ai-ginkgo-cloud-lab/SKILL.md

decimalai skills pull k-dense-ai-ginkgo-cloud-lab --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/k-dense-ai-ginkgo-cloud-lab/SKILL.md https://app.decimal.ai/s/k-dense-ai-ginkgo-cloud-lab/SKILL.md

Raw file: /s/k-dense-ai-ginkgo-cloud-lab/SKILL.md ↗ · machine-readable summary at /s/k-dense-ai-ginkgo-cloud-lab.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 19d ago

Yes — +77% lift · at higher cost+51% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	125%	0%
case-03	✗→✓	▲ Improved	42%	0%
case-07	✗→✓	▲ Improved	14%	0%
case-08	✗→✓	▲ Improved	32%	0%
case-09	✗→✓	▲ Improved	13%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/8/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

k-dense-ai / scientific-agent-skills

skills/ginkgo-cloud-lab/SKILL.md

View on GitHub ↗

License MIT licenseImported 9/8/2026Version v2Bundled 17 files

Skill contents

references/

SKILL.md

Ginkgo Cloud Lab

Overview

Ginkgo Cloud Lab (https://cloud.ginkgo.bio) provides remote access to Ginkgo Bioworks' autonomous lab infrastructure. Protocols are executed on Reconfigurable Automation Carts (RACs) -- modular units with robotic arms, maglev sample transport, and industrial-grade software spanning 70+ instruments.

The platform also includes EstiMate, an AI agent that accepts human-language protocol descriptions and returns feasibility assessments and pricing for custom workflows beyond the listed protocols.

The catalog is organized into Expression & Purification (in vitro / cell-free / E. coli / Pichia), Characterization & Assay, Method & Target Onboarding, and Specialty. Pick a protocol below, then read its reference file for inputs, outputs, the automated workflow, and ordering details.

Available Protocols

Expression & Purification - In vitro

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | IVT mRNA/circRNA Synthesis | qPCR (mRNA or circRNA, 384-well) | $99/sample | up to 12 business days | Certified |

Expression & Purification - Cell-free (E. coli CFPS)

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | Validate sequence expression | Go/no-go titer + purity (up to 1800 bp) | $39/sample | up to 10 days | Certified | | Optimize expression conditions | DoE across 24 conditions | $199/sample | up to 11 days | Certified | | Express + quantify (HiBiT) | Luminescence, no purification | $39/sample | up to 11 days | Certified | | Express + purify (A280) | Strep-tag, A280 yield | $149/sample | up to 11 days | Certified | | Express + purify minibinder | Strep-tag, A280, LabChip | $149/sample | up to 11 days | Certified | | Express + purify (A280 + LabChip) | Strep-tag, A280 + purity/size | $159/sample | up to 12 days | Certified |

Expression & Purification - E. coli

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | Express + quantify (HiBiT) | Luminescence (up to 384 constructs) | $79/sample | up to 3 weeks | Certified | | Express + purify (A280) | His-tag, A280 yield | $199/sample | up to 3 weeks | Certified | | Express + purify minibinder | His-tag, A280 yield | $199/sample | up to 3 weeks | Certified | | Express + purify (A280 + LabChip) | His-tag, A280 + purity/size | $209/sample | up to 3 weeks | Certified |

Expression & Purification - Pichia

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | Express + quantify (LabChip) | Secreted protein, size/purity (up to 96) | $89/sample | up to 4 weeks | Certified (New) |

Characterization & Assay

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | Express + thermal shift | SYPRO Orange Tm (Tonset, TM1-3) | $159/sample | up to 12 days | Certified | | Detect enzymatic products (Echo-MS) | Substrate/product by Echo-MS | $44/sample | up to 13 days | Beta |

Method & Target Onboarding

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | Onboard Echo-MS method | Calibration curve, LOD/LOQ | $799/molecule | up to 3 weeks | Certified | | Onboard SPR target | Validated SPR capture method | $1,399/target | up to 4 weeks | Beta |

Specialty

| Protocol | Readout | Price | Turnaround | Status | |---|---|---|---|---| | Generate fluorescent pixel art | UV photo, 7-color E. coli palette | $25/plate | up to 7 days | Beta |

Coming soon: Protein Expression and Binding Affinity Characterization (express + purify, then screen binding affinity against a target).

Choosing a Protocol

Quick expressibility screen? Cell-free HiBiT ($39) or Validate sequence expression ($39).
Need purified protein + yield? A280 tiers (cell-free or E. coli); add LabChip for purity/size.
Difficult / membrane / disulfide / cofactor targets? Cell-free Optimize (24-condition DoE).
Secreted or eukaryotic targets? Pichia expression.
Screening de novo binders/minibinders? Cell-free or E. coli minibinder tiers, then SPR onboarding for kinetics.
Enzyme activity / biocatalysis? Echo-MS enzymatic detection (onboard the analyte method first).
Stability / developability ranking? Thermal shift assay.
RNA (mRNA/circRNA)? IVT synthesis + qPCR.

General Ordering Workflow

Select a protocol at https://cloud.ginkgo.bio/protocols
Configure parameters (number of proteins/samples/molecules/targets, replicates, plates)
Download the protocol's input template and upload inputs (FASTA/CSV/XLSX for sequence protocols; Design Tool for pixel art; vendor catalog numbers for onboarding)
Add any special requirements in the Additional Details field
Provide an email, agree to the protocol terms, and add to cart / submit to receive a feasibility report and price quote

For protocols not listed above, use the EstiMate chat (https://cloud.ginkgo.bio/estimate) to describe a custom protocol in plain language and receive a compatibility assessment and pricing.

Authentication

Access Ginkgo Cloud Lab at https://cloud.ginkgo.bio. Account creation or institutional access may be required. Contact Ginkgo at cloud@ginkgo.bio for access questions.

Key Infrastructure

RACs (Reconfigurable Automation Carts): Modular robotic units with high-precision arms and maglev transport
Catalyst Software: Protocol orchestration, scheduling, parameterization, and real-time monitoring
70+ integrated instruments: Agilent Bravo liquid handlers, Beckman/Labcyte Echo acoustic dispensers, BMG PHERAstar / Tecan Spark readers, Revvity LabChip, Bio-Rad CFX Opus, Nicoya Alto SPR, SciEx Echo-MS, Inheco/Cytomat incubators, and more
Nebula: Ginkgo's autonomous lab facility in Boston, MA

Citing Scientific Agent Skills

This skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a manuscript, report, presentation, or code release, add the paper to the references or software section and tell the user you did so:

> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent > Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065. > https://doi.org/10.48550/arXiv.2609.00065

Always cite the current version. The DOI and https://arxiv.org/abs/2609.00065 resolve to the latest arXiv version, so never append a version suffix such as v1. When network access is available, fetch https://arxiv.org/abs/2609.00065 (or http://export.arxiv.org/api/query?id_list=2609.00065) before writing the reference and take the author list, year, and version from that record. If the record lists a journal reference or publisher DOI, cite the published version instead.

Illustrative Want to see what k-dense-ai/ginkgo-cloud-lab would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

9/8/2026, 19:25 UTC · 22 cases

Lift

+77%

91% vs 14%

Agent turns

1.0 vs 1.0

Tokens

+51%

3,872.86 vs 2,573.86

fail → pass · 17pass → pass · 3fail → fail · 2

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 I have 50 synthetic minibinder constructs that I need to screen for expression, yield, and protein size analysis. Can you evaluate the available options on Ginkgo's cloud platform and provide a summary of suitable protocols with their readouts, estimated prices per sample, turnaround times, and current status?	fail→pass	35,945	21,253	-41%	1	1	0%	2,351	5,278	+125%	0	0	—
case-02 We are planning our first batch submission for IVT RNA synthesis with qPCR verification on Ginkgo Cloud Lab. Please list the end-to-end steps required to set up parameters, upload the sequence data templates, submit special notes, and place the order through the system.	fail→fail	22,015	19,546	-11%	1	1	0%	2,658	4,494	+69%	0	0	—
case-03 I am evaluating automated services for an enzyme characterization project that might require non-standard reaction conditions. Could you present a detailed guide comparing how standard catalog protocols are chosen versus how custom unlisted protocols are handled, including platform tools, input requirements, and pricing/feasibility mechanisms?	fail→pass	33,685	26,023	-23%	1	1	0%	4,144	5,882	+42%	0	0	—
case-04 I am designing a Golden Gate assembly strategy using BsaI and BsmBI restriction enzymes for local bench cloning of a eukaryotic transcription factor in pUC19. What overlap overhangs and reaction buffer conditions should I use to maximize assembly efficiency in my bench top thermal cycler?	pass→pass	24,326	41,687	+71%	1	1	0%	2,750	8,738	+218%	0	0	—
case-05 Our academic laboratory is manual packing C18 reverse-phase HPLC columns for small molecule separation. What slurry solvents, packing pressure limits, and frit pore sizes yield the highest column efficiency on a standard bench LC system?	pass→pass	30,367	30,183	-1%	1	1	0%	3,865	6,474	+68%	0	0	—
case-06 I am writing a PyLabRobot script to control a Hamilton Microlab STAR liquid handler for liquid-liquid extraction. How do I define tip carrier layouts and suction speeds in PyLabRobot code?	fail→fail	25,871	29,799	+15%	1	1	0%	3,799	6,509	+71%	0	0	—
case-07 We have 96 unpurified lysate samples from a cell-free reaction and need a fast, low-cost bioluminescent quantitative readout without running purification columns. Which specific automated platform protocol fits this need, and what is its sample unit cost?	fail→pass	21,297	10,680	-50%	1	1	0%	2,693	3,073	+14%	0	0	—
case-08 We are trying to express a complex membrane-bound protein that fails standard lysate conditions. We want to run a Design of Experiments (DoE) screen across 24 different cell-free expression conditions. Which specific protocol handles this condition optimization, what is the cost per sample, and what is the maximum turnaround time?	fail→pass	35,545	8,713	-75%	1	1	0%	2,200	2,912	+32%	0	0	—
case-09 Our research group requires remote synthesis of 384-well mRNA constructs with qPCR readout validation. What is the designated catalog protocol name, per-sample price, turnaround timeframe, and certified status for this service?	fail→pass	32,003	8,111	-75%	1	1	0%	2,294	2,601	+13%	0	0	—
case-10 We need His-tag purified protein from E. coli expression with both concentration (A280) and LabChip size/purity analysis. What is the sample price, turnaround, and purification tag used in this E. coli protocol compared to the Strep-tag cell-free equivalent?	fail→pass	33,111	11,276	-66%	1	1	0%	2,651	3,285	+24%	0	0	—
case-11 We are developing a eukaryotic secreted glycoprotein candidate and want to test expression in Pichia pastoris with LabChip purity verification. What is the per-sample cost, maximum construct batch capacity, and turnaround time for this Pichia protocol?	fail→pass	15,685	9,682	-38%	1	1	0%	1,636	2,913	+78%	0	0	—
case-12 We are screening enzyme variants for biocatalytic product formation and want high-speed acoustic mass spectrometry detection without chromatographic separation. Which automated assay protocol should we order, what is the sample cost, and what is its current release status?	fail→pass	21,839	9,293	-57%	1	1	0%	2,653	2,931	+10%	0	0	—
case-13 Before running high-throughput Echo-MS enzyme assays for a novel substrate-product pair, we need to establish a quantitative calibration curve and determine LOD/LOQ values. What onboarding protocol is required, how is it priced, and what is the lead time?	fail→pass	24,561	12,634	-49%	1	1	0%	3,218	3,376	+5%	0	0	—
case-14 We plan to screen small molecule binders against an immobilized protein target using Nicoya Alto SPR. What is the catalog target onboarding protocol, its fee per target, turnaround time, and platform release status?	fail→pass	35,775	9,345	-74%	1	1	0%	2,230	2,905	+30%	0	0	—
case-15 We need to measure protein thermal melting temperatures (Tm, Tonset) using SYPRO Orange dye on cell-free expressed targets. Which protocol provides this readout, what is the cost per sample, and what is the turnaround time?	fail→pass	23,439	9,263	-60%	1	1	0%	3,070	2,861	-7%	0	0	—
case-16 We have 100 DNA sequences under 1800 bp that need a rapid go/no-go expression titer and purity assessment in E. coli CFPS. What protocol should we select, what is its cost per sample, and what is the turnaround time?	fail→pass	18,120	8,545	-53%	1	1	0%	2,103	2,781	+32%	0	0	—
case-17 For an educational outreach display, we want to create a 7-color fluorescent bacterial picture on agar using E. coli strains. What specialty protocol supports this, what is the price model, and what is the turnaround time?	fail→pass	36,149	10,155	-72%	1	1	0%	2,038	2,907	+43%	0	0	—
case-18 When executing automated protocols at Ginkgo's cloud facility, what are the primary robotic cart modules called, what software orchestrates the scheduling, and where is the central autonomous facility located?	fail→pass	16,073	8,009	-50%	1	1	0%	1,540	2,711	+76%	0	0	—
case-19 When preparing batch ordering submissions for cloud lab protocols, what specific input template file formats are accepted for sequence-based protocols, and what input is required for method onboarding?	pass→pass	19,162	12,212	-36%	1	1	0%	2,090	3,338	+60%	0	0	—
case-20 We want to screen 300 recombinant protein constructs in E. coli using luminescence quantification without purification. What is the per-sample price, construct limit per batch, and turnaround time for this protocol?	fail→pass	23,207	9,206	-60%	1	1	0%	2,946	3,015	+2%	0	0	—
case-21 We need cell-free expressed protein purified via Strep-tag with A280 yield determination, but without electrophoretic purity sizing (LabChip). What is the exact protocol title, per-sample price, and turnaround time?	fail→pass	14,635	9,805	-33%	1	1	0%	1,375	2,983	+117%	0	0	—
case-22 When referencing the Scientific Agent Skills software suite in a published research paper, what author list, arXiv identifier, and DOI citation format should be included?	fail→pass	18,226	10,568	-42%	1	1	0%	2,321	3,236	+39%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +77 percentage points is the difference between those two pass rates over the 22 comparable cases.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 13.6%
Pass rate with the skill: 90.9%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 0
Skill version measured: v2
Run completed: 9/8/2026, 19:25 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-01

Prompt

I have 50 synthetic minibinder constructs that I need to screen for expression, yield, and protein size analysis. Can you evaluate the available options on Ginkgo's cloud platform and provide a summary of suitable protocols with their readouts, estimated prices per sample, turnaround times, and current status?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run91

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+113% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 19 days ago

Model	Method	Date	Lift
gemini-3.6-flash	verified	8/10/2026	+77%

Other measured skills in the registry, with their headline benchmark lift.