Skill
KOL paper-trial triangulator
Name a KOL plus a context query; get their top-10 most relevant papers, each triangulated to the exact clinical trial it reports — pulled from Amass's publication↔trial graph, with trust metadata and a downloadable engagement-dossier workbook.
New to Amass? Connect Amass to Claude first
The prompt
Paste this into Claude
Mikhail Kosiborod · cardiometabolic heart failureUse the KOL paper-trial triangulator skill.
Author (KOL) + context query: Mikhail Kosiborod · cardiometabolic heart failureWhy not just ask the model?
Ask a plain model "which trials has Mikhail Kosiborod's cardiometabolic-heart-failure work reported on?" and it confidently maps papers to NCTs it never verified.
- Plain model: invents plausible-looking
NCTnumbers, mis-attributes papers to the wrong author, and conflates the trial a paper cites with the trial it actually reports — there is no real author→paper→trial map behind the answer. - Amass: the author is a first-class search filter (
authorNameson BiomedCore), and the paper→trial link is a first-class graph edge (referencesTrialCore). Each row'sNCTis the literal value Amass returned, alongside verbatim journal, date,citationCount,journalQualityJufo, andisRetracted— nothing is guessed.
Why a skill, not a prompt?
This is a multi-step orchestration, not a one-shot lookup: one author-scoped BiomedCore search seeds the corpus, then a get_amass_biomedcore_record by-id fan-out runs once per returned paper to read its referencesTrialCore edge, then a templated roll-up classifies each paper as trial-linked (the exact NCT) or "none (meta-analysis / review)" when the edge is empty. Packaging that as a skill means you trigger the whole fan-out with one line instead of re-pasting a brittle procedure every time.
Honest scope
The 10 results — search returns at most limit, which defaults to 10 and accepts up to 50, and never a total — are a relevance sample, not a census of the author's full bibliography; broaden it by raising limit or re-running with a second wording of the context query and unioning the results. authorNames is an ambiguous token-match with no identity resolution, so verify the named author appears in each returned record before keeping the row. Citation counts and trust metadata are verbatim from Amass and can lag the source databases by hours; a "none" cell is a genuinely empty edge (meta-analyses and reviews aggregate many trials and name none as a single primary), never a skipped lookup.
Install the skill
Add the skill to Claude
Install every Amass skill with one command, npx skills add amass-technologies/public-skills or download the SKILL.md from GitHub and add it to Claude (Settings → Capabilities → Skills, or drop it in your Claude Code skills directory). Then paste the prompt above to trigger it.
More from the library
Keep exploring
| Short name | Source id | Registry | Copy of |
|---|---|---|---|
| Acute, 50/75 mg vs placebo | NCT04072354 | ClinicalTrials.gov | |
| ↳ EUCTR2019-000470-36-BG | EU CTR | NCT04072354 | |
| Acute, 75/100 mg vs placebo | NCT04092686 | ClinicalTrials.gov |
Watchlist Monitor
Name the trials, papers, approvals or drugs you need to follow; get one Excel board that re-reads them through Amass at every check and tells you exactly what changed: status, dates, enrollment, results posted, label revisions, retractions, new links.

Landscape Monitor
Name a field; get it mapped across trials, papers, patents, drugs, genes and approvals into a landscape page with charts, a workbook and a one-page briefing, every record screened with its reason. Ask for an update later to see what is new and what changed.
| kinase | kinase_family_chembl_leaf | small_molecule_tractability | protac_tractability |
|---|---|---|---|
| PLK1 | Other protein kinase PLK family | Advanced Clinical | predictive-only |
| WEE1 | Other protein kinase WEE family | Advanced Clinical | predictive-only |
| CDK1 | CMGC protein kinase CDK5 subfamily | Advanced Clinical | predictive-only |
Target prioritization matrix
A general, interview-driven target-discovery workbench: name the biology and the modality you care about, and get back a scored table of candidate targets — druggability, essentiality, genetic constraint, curated safety, and the real number of drugs already targeting each — assembled from GeneCore intelligence and DrugCore/TrialCore/BiomedCore/PatentCore cross-links.
Run it yourself
Connect Amass to Claude and paste the prompt.
The connector takes about a minute to add, then this workflow runs on your own inputs.
- Data
- No training on your data
- Hosting
- EU-hosted, enterprise
- Isolation
- Tenant-isolated by architecture
- Certification
- ISO 27001, SOC 2, NIS2: in motion