Agent skill · mvanhorn
pp-clinical-trials
A multi-source clinical-trials intelligence system — aggregates, normalizes, and analyzes trials across ClinicalTrials.gov, EU CTIS, and biomedical sources, with an offline SQLite engine no single-registry tool has. Trigger phrases: `what clinical trials are running for`, `recruiting trials for`, `phase 3 trials for`, `compare these two drugs trials`, `emerging therapies in`, `is this trial risky`, `watch trials for`, `clinical trials intelligence`, `use clinical-trials`, `run clinical-trials`.
What it needs
About 10k tokens when loaded.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT. This file is a verbatim mirror of library/health/clinical-trials/SKILL.md, regenerated post-merge by tools/generate-skills/. Hand-edits here are silently overwritten on the next regen. Edit the library/ source instead. See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". --> ClinicalTrials.gov — Printing Press CLI Prerequisites: Install the CLI This skill drives the clinical-trials-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows: 2. Verify: clinical-trials-pp-cli --version 3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill. If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead: If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds. Every other ClinicalTrials.gov tool is a single-source pass-through. This one merges registries into one normalized trial model, dedups across NCT/EUCTR/WHO IDs, and computes intelligence: emerging therapies, recruitment velocity, drug comparisons, abandonment risk, geographic hotspots, and sponsor dominance. It degrades gracefully down a fallback chain and never crashes, caching everything locally for offline, agent-native analysis. When to Use This CLI Reach for this CLI when the task is understanding the clinical-trials landscape — what is running, what is emerging, how two drugs compare, whether a trial is risky, or where recruitment is concentrated — across more than one registry. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills mvanhorn/pp-clinical-trials