Bowen lnp evidence synthesizer
Skill allenlee0430/bowen-ai-skills/skills/bowen-lnp-evidence-synthesizer
Reusable Codex and Claude Code skills for research operations, grants, evidence synthesis, lab-in-the-loop planning, file curation, and faculty workflows.
npx -y skills add allenlee0430/bowen-ai-skills --skill bowen-lnp-evidence-synthesizerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Synthesize literature and project evidence on lipid nanoparticles, biomaterials, RNA medicines, vaccines, gene editing, and AI-guided delivery into rigorous field-level arguments. Use for reviews, perspectives, introductions, discussions, grant rationales, research briefs, or big-picture scientific positioning where evidence, caveats, and biomaterials mechanisms must remain explicit.
SKILL.md
1.7 KB, 247 tokens by cl100k_base, as published. Nobody here has run it
Bowen LNP Evidence Synthesizer
Workflow
- Read
references/editorial-profile.md. - Define the scientific question, audience, venue, and claim strength.
- Build a claim bank before drafting. For every proposed claim, record source, evidence type, system, endpoint, limitation, and allowed wording.
- Cluster evidence by mechanism or design principle rather than paper chronology.
- Draft a field thesis first. Use examples sparingly to test or sharpen that thesis.
- Preserve the distinction between association, mechanism, preclinical validation, and clinical evidence.
- End with concrete research programs, measurement needs, or design rules rather than generic optimism.
Required Output
- one-sentence field thesis;
- evidence map with contradictions and gaps;
- structured synthesis;
- caveats and confidence;
- citation-ready source list when sources are available.
Rules
- Reopen original sources before exact quotation or citation-sensitive claims.
- Never invent citations, results, mechanisms, or numerical values.
- Prefer structure-property relationships, biological interfaces, transport barriers, endosomal escape, degradation, safety, scalability, and manufacturability.
- Avoid paper-by-paper recitation and unsupported superlatives.