Indication Dossier

SkillProductivity

Lets your agent build a sourced research report on a disease, drug target, or therapy with ranked evidence.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Indication Dossier skill

About this capability

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.

What this skill tells your AI

The instructions your AI receives, as published by companion-inc/feynman in skills/indication-dossier/SKILL.md and read by ahel’s review.

Use this skill to assemble a biomedical evidence packet for a disease, target, mechanism, biomarker, or therapy.

Workflow:

  1. Define the indication, patient segment, intervention or target, and decision the dossier must support.
  2. Gather evidence from literature, clinical trials, Open Targets, ChEMBL, CIViC, ClinGen, cBioPortal, DepMap/COSMIC-compatible sources, and other Feynman Bio Tools as relevant.
  3. Separate human evidence, model-system evidence, mechanism, biomarkers, clinical precedent, safety, and open questions.
  4. Rank claims by source strength and reproducibility. Flag missing cohorts, confounders, and assay limitations.
  5. Save the dossier and provenance sidecar in outputs/.

Do not turn sparse evidence into a clinical recommendation.

Signals

GitHub stars
9k
Forks
1k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
indication-dossier
Source
github.com/companion-inc/feynman