The new Amass app is live. Ask in plain language, check every claim. Try it free

Skills & PromptsBiomedical Evidence Scout

Skill

Biomedical Evidence Scout

Name a drug, target, mechanism, or indication; get a landscape briefing that maps the published literature AND the clinical pipeline together — every paper and trial carrying a real Amass ID, PMID, or NCT you can check.

New to Amass? Connect Amass to Claude first

2approved, first-gen
5next-gen inhibitors in trials
You getcsv1 file
Skillcompetitive-intelligenceclaude

The prompt

Paste this into Claude

A drug, target, mechanism, or indicationKRAS G12C inhibitors

I'm scoping a KRAS G12C inhibitor program. Give me the landscape: what does the published literature say, who's running trials right now, what's read out vs. pending, and where is the field heading?

Why not just ask the model?

Ask a plain model "give me the landscape on KRAS G12C" and it writes a confident briefing full of plausible papers and trials — some real, some not, none checkable, and all frozen at its training cutoff.

  • Plain model: invents citations and NCT IDs that "sound right", blurs which trials are recruiting vs. terminated, and cannot tell you what read out last quarter.
  • Amass: every paper is a real BiomedCore record (verbatim journal, publication date, citation count, JuFo quality tier, retraction flag) and every trial a real TrialCore record (sponsor, phase, status, enrollment, NCT). The scan above surfaced the terminated CodeBreaK 201 (NCT04933695) and the active divarasib Phase 3 (NCT06497556) as distinct, current facts — not a guess about "ongoing studies".

Why a skill, not a prompt?

Mapping a field is a multi-step orchestration, not a one-shot search. The skill runs a parallel paper + trial reconnaissance, does a hygiene check on relevance, picks a framing (PICO + pipeline, target map, or competitive landscape), fans out into sub-areas, and follows the paper↔trial cross-links — then synthesizes the two corpora into a single briefing with a strict "nothing that isn't in a returned record" rule. Packaging that as a skill means the orchestration and the data-integrity guardrails ship once and trigger on a phrase like "give me a landscape on X", instead of being re-pasted — and half-followed — every time.

Honest scope

The briefing is a launchpad, not a systematic review: it is built from a focused single-pass scan (top domain-leading-and-above papers since 2021, plus a Phase 2/3 trial search), so niche early-phase and non-oncology work is out of frame. Every count is verbatim from Amass and can lag the source databases by hours; the colorectal 19% → 46% response figures are quoted from a trial record's own summary, not re-derived. The skill is deliberately barred from falling back to web search or model knowledge — if Amass returns thin results, it says so rather than filling the gap.

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

xlsx
14trials watched
Short nameSource idRegistryCopy of
Acute, 50/75 mg vs placeboNCT04072354ClinicalTrials.gov
↳ EUCTR2019-000470-36-BGEU CTRNCT04072354
Acute, 75/100 mg vs placeboNCT04092686ClinicalTrials.gov
competitive-intelligenceSkill

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.

pdf+1
196trials in scope
Landscape Monitor — page 1
competitive-intelligenceSkill

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.

csv
12targets scored
kinasekinase_family_chembl_leafsmall_molecule_tractabilityprotac_tractability
PLK1Other protein kinase PLK familyAdvanced Clinicalpredictive-only
WEE1Other protein kinase WEE familyAdvanced Clinicalpredictive-only
CDK1CMGC protein kinase CDK5 subfamilyAdvanced Clinicalpredictive-only
researchSkill

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