Indication Dossier
Researchindication-dossierIndication Dossier is an Agent Skill for research published in the companion-inc/feynman repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/indication-dossier/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/indication-dossier, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Indication Dossier
Use this skill to assemble a biomedical evidence packet for a disease, target, mechanism, biomarker, or therapy.
Workflow:
- Define the indication, patient segment, intervention or target, and decision the dossier must support.
- Gather evidence from literature, clinical trials, Open Targets, ChEMBL, CIViC, ClinGen, cBioPortal, DepMap/COSMIC-compatible sources, and other Feynman Bio Tools as relevant.
- Separate human evidence, model-system evidence, mechanism, biomarkers, clinical precedent, safety, and open questions.
- Rank claims by source strength and reproducibility. Flag missing cohorts, confounders, and assay limitations.
- Save the dossier and provenance sidecar in
outputs/.
Do not turn sparse evidence into a clinical recommendation.