Skill
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.
New to Amass? Connect Amass to Claude first
The prompt
Paste this into Claude
The phase 3 trials of ulotaront (SEP-363856), with their Japanese and EU registry copiesUse the amass-watchlist-monitor skill. I want to watch the phase 3 trials of ulotaront (SEP-363856), including their Japanese and EU registry copies. Set it up directly; you don't need to check the list with me first.
Why not just ask the model?
Ask a plain model "what changed on the ulotaront phase 3 trials since last month?" and it has nothing to compare against. It does not remember last month, so it describes the trials as it last saw them in training and presents that as news.
- Plain model: no memory between conversations, no record of the previous state, and statuses or dates that may be years old.
- Amass: each check re-reads the live TrialCore records and compares them field by field with the copies stored in the board. The digest lists only what actually moved: a status change, a new completion date, enrollment revised, results posted, a new link to a paper or drug. Every record carries its registry id, so each change can be checked at the source.
Why a skill, not a prompt?
A watchlist needs memory and an exact comparison, and a prompt has neither. The skill keeps both in one Excel file, the board. A small script stores every tracked field, diffs each check against the last one, and writes the changes to the board; Claude never compares values itself. The board opens on an Overview sheet with what changed, what is worth watching, and a timeline of the trials by indication. In Claude chat you keep the file and attach it next time; in Cowork and Claude Code it stays in its folder.
The setup is careful work too. Here it matched each Japanese and EU registry copy to its trial only where the records agree on title, sponsor, dates, ages and countries, and it flagged the copies that have gone stale.
Honest scope
The list is fixed: a new trial does not join it by itself, so re-scope from time to time, or map the whole field with the Landscape Monitor skill. Each check sees the state of each record at that moment, so a change shows up at the next check, not on the day it happened. Over the MCP connector the watch covers status, dates, enrollment, results posted, label and SmPC revision numbers, retractions and cross-links. For revised results, why a trial stopped, which label section changed, or a scheduled watch over hundreds of records, the skill's API mode reads the Amass change feed with an API key.
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

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.
| record_type | title | id | source |
|---|---|---|---|
| paper | Mechanisms of Resistance to KRASG12C Inhibitors | PMID:33466360 | Cancers (JuFo 2) |
| paper | Oncogenic KRAS blockade therapy: renewed enthusiasm and persistent challenges | PMID:34607583 | Molecular Cancer (JuFo 3) |
| paper | KRAS G12C Mutations in NSCLC: From Target to Resistance | PMID:34064232 | Cancers (JuFo 2) |
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