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

Skills & PromptsLandscape Monitor

Skill

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.

New to Amass? Connect Amass to Claude first

196trials in scope
5programmes in Phase 3
6 of 6anchors found
You getxlsxpdf2 files
Skillcompetitive-intelligenceclaude

The prompt

Paste this into Claude

A fieldAmylin analogues in obesity

Use the amass-landscape-monitor skill.

Map the amylin analogues in obesity.

Why not just ask the model?

Ask a plain model to "map the amylin analogues in obesity" and it lists the programmes it remembers from training, with phases and trial counts that sound right and cannot be checked. It cannot tell you what it missed, and it has nothing to compare against next month.

  • Plain model: a remembered shortlist, no record ids, no way to know how complete it is, and no memory for an update.
  • Amass: every trial, paper, patent, drug, gene and authorization on the page is a real Amass record with its registry id, PMID, DOI or publication number. Each one was screened in or out against the field's written criteria, with the reason kept in the workbook. The 2026 Phase 3 starts (AMAZE 1, ENLIGHTEN-1, SELENE 1, ZUPREME-3) are dated registry records, not a guess. The map comes with its own recall checks: all six anchor trials were found by search, and of the 120 trials linked from the drug records, the searches reached 112 and fetches the other 8.

Why a skill, not a prompt?

Mapping a field is a systematic search, not one question. Search is relevance-ranked and capped per call, so one query sees one slice. The skill writes the field's criteria first, builds the roster of drugs, codes and targets, then searches each Core facet by facet (names, development codes, mechanism, sponsors) until new queries stop adding records, within a per-Core allowance. A small script keeps one ledger per Core on disk and computes every number on the page, so nothing is counted by hand or remembered by the model. The same files are the memory for updates: ask "run the update" later, and only the Cores whose refresh interval has passed are searched again, with date filters, and changes are reported by drug and by Core.

Honest scope

The map is as complete as its plan and its saturation numbers say, and the page reports both: which facets stopped producing and which were still producing when the allowance was used. A code the registry text does not carry can only be reached by its sponsor's name or a fetch, and newer compounds have no DrugCore record yet, so their trials and papers are reached by name. Counts are of registry records, so a trial registered in two registries counts twice. Updates use date-filtered searches, which cannot see results revised on an existing trial or label changes confined to section text; for that, export the in-scope trials to the Watchlist Monitor skill.

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 package from GitHub and add it to Claude (Settings → Capabilities → Skills, or unzip it into your Claude Code skills directory). The package holds the SKILL.md and the helper scripts it runs. 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.

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.

csv
2approved, first-gen
record_typetitleidsource
paperMechanisms of Resistance to KRASG12C InhibitorsPMID:33466360Cancers (JuFo 2)
paperOncogenic KRAS blockade therapy: renewed enthusiasm and persistent challengesPMID:34607583Molecular Cancer (JuFo 3)
paperKRAS G12C Mutations in NSCLC: From Target to ResistancePMID:34064232Cancers (JuFo 2)
competitive-intelligenceSkill

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.

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