design-lnp-experiments
Skill0 starsChanged 5 months agoMITView on GitHub
Design and critique AI-assisted LNP and RNA-delivery design-make-test-learn cycles for Bowen Li's research program. Use for candidate-library design, formulation-space selection, assay planning, active-learning rounds, barcoded in-vivo screens, multi-objective optimization, translational criteria, go/no-go decisions, and connecting experimental results back to computational models.
In this repository9 other files it gives its agents.
- build-reimbursement-packetsSkill
- manage-research-portfolioSkill
- organize-research-filesSkill
- run-pi-operationsSkill
- scan-nanomedicine-literatureSkill
- downloads-triageSkill
- lab-pi-opsSkill
- lit-scoutSkill
- reimburse-trackerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Do not fabricate prior results or assume an unpublished claim is validated.
- Very specific: line 18
Read references/dmtl-checklist.md for the minimum closed-loop specification.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design LNP experiments
- Define the therapeutic objective, target cell or tissue, cargo, route, disease model, constraints, and decision the experiment must enable.
- Specify the learning objective before choosing candidates. Distinguish exploitation, exploration, mechanism testing, and model calibration.
- Define the design space: lipid structures, component identities, molar ratios, process variables, dose, and cargo attributes. Record hard chemical, formulation, safety, and manufacturing constraints.
- Select controls, replication, randomization, batch strategy, blinding where relevant, and predefined success thresholds.
- Choose readouts that separate delivery, expression or editing, cell viability, innate immunity, biodistribution, endosomal escape, and durability.
- Plan data capture so every sample maps unambiguously to structure, formulation, process, batch, assay, and outcome.
- For active learning, state acquisition strategy, uncertainty treatment, diversity constraints, retraining trigger, and stopping rule.
- Produce a decision table and next-round logic before results exist. Surface biosafety, animal ethics, clinical, and manufacturability gates.
- Do not fabricate prior results or assume an unpublished claim is validated. Cite current primary sources for external facts.
Read references/dmtl-checklist.md for the minimum closed-loop specification.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

