Pp Clinical Trials

<!-- 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:

   npx -y @mvanhorn/printing-press-library install clinical-trials --cli-only

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:

go install github.com/mvanhorn/printing-press-library/library/health/clinical-trials/cmd/clinical-trials-pp-cli@latest

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. It is the right tool for evidence synthesis, competitive trial analysis, and weekly landscape reports.

Anti-triggers

Do not use this CLI for:

• Do not use it to enroll patients or submit trial registrations — it is read-only.
• Do not use it for full EHR or patient-record data — it covers public trial registries only.
• Do not use --source who expecting live data — WHO ICTRP has no public API.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Intelligence engine

• emerging — See the fastest-growing trial categories for a disease area, with percent change.

  Pick this when the user asks where research is heading, not about one specific trial.

  clinical-trials-pp-cli emerging cancer --json

• velocity — Measure how fast a disease area's trials and enrollment are growing over time.

  Use to quantify momentum in a field; buckets a sampled set of trials by start year and reports a recent-vs-prior growth rate (no prior snapshot needed).

  clinical-trials-pp-cli velocity "alzheimer" --json

• compare — Compare two drugs head-to-head across trial counts, phases, sponsors, and recruiting status.

  Use to weigh two interventions by real trial activity, not marketing.

  clinical-trials-pp-cli compare "Keytruda" "Opdivo" --json

• risk — Get an explainable risk read on a single trial from termination, enrollment, site count, sponsor track record, and phase factor (earlier phases = higher risk).

  Use to triage whether a trial is likely to complete and report.

  clinical-trials-pp-cli risk NCT07011732 --json

• forecast — Forward-looking completion outlook for a trial, derived from the same deterministic signals as risk.

  Use to get a plain-language outlook band and the primary concerns behind it. Caveat: heuristic only — a read of registry signals, not a clinical prediction.

  clinical-trials-pp-cli forecast NCT07011732 --json

• sponsors — Rank who runs the most trials in an area, classified as industry, academic, or government.

  Use to see who controls research in a field.

  clinical-trials-pp-cli sponsors "diabetes" --json

• digest — Compact "what's notable" snapshot for a condition or search term: total matched, recruiting count, newest trials, and recently-stopped ones.

  Use for a fast read on a topic's current state; a read-only point-in-time snapshot (use watch for a persistent change feed). --limit bounds the newest and recently-stopped lists.

  clinical-trials-pp-cli digest "type 2 diabetes" --limit 5 --json

Single-trial analysis

• similar — Find trials similar to a given NCT ID by shared condition, phase, and intervention profile.

  Use to surface comparable trials from registry signals only (no ML matching); --limit caps how many matches are returned.

  clinical-trials-pp-cli similar NCT04280705 --limit 5 --json

• timeline — Show a trial's key dates in chronological order: start, primary completion, completion, and last-update posted.

  Use to see a single trial's schedule at a glance; dates with no posted value are omitted.

  clinical-trials-pp-cli timeline NCT04280705 --json

• enrollment-check — Heuristic plausibility check on a trial's posted enrollment target relative to its phase.

  Reuses the risk command's enrollment signal. Caveat: this is a heuristic from observable registry signals only — not a clinical judgment or a prediction of whether the trial will enroll.

  clinical-trials-pp-cli enrollment-check NCT04280705 --json

Interoperability

• export-fhir — Export a trial's registry metadata as a minimal FHIR R4 ResearchStudy resource (JSON) or a flat CSV row.

  Use to hand a trial's core metadata to a FHIR-aware system or a spreadsheet. --format fhir (default) emits the ResearchStudy JSON; --format csv emits one flat row. Caveat: this is a lightweight metadata export, not a full FHIR-conformant clinical dataset, and is not validated against a FHIR profile.

  clinical-trials-pp-cli export-fhir NCT04280705
  clinical-trials-pp-cli export-fhir NCT04280705 --format csv

Local state that compounds

• watch — Track a term and report new, changed, and terminated trials since the last run.

  Use to monitor a topic over time instead of re-reading full result sets.

  clinical-trials-pp-cli watch "vitamin d" --json

Multi-source aggregation

• search — Search a single normalized trial model aggregated and deduplicated across ClinicalTrials.gov, EU CTIS, and OpenAlex.

  Use as the default entry point; it queries the merged multi-source mirror, so it sees more than any single registry.

  clinical-trials-pp-cli search "glioblastoma" --json

Enrichment

• evidence — Link a trial to its publications and citation context via PubMed and OpenAlex.

  Use to check whether a trial actually published results.

  clinical-trials-pp-cli evidence NCT07011732 --json

• safety — Surface FDA adverse-event signals for a trial's intervention drug.

  Use to add a real-world safety lens to a trial's drug.

  clinical-trials-pp-cli safety "pembrolizumab" --json

Output for humans

• report — Compose search, emerging, hotspots, and sponsors into one markdown or CSV briefing for a topic.

  Use for a weekly landscape summary a clinician can read at a glance.

  clinical-trials-pp-cli report "long covid" --format md

Reliability

• health — Show live status, latency, and failure rate for every data source in the fallback chain.

  Use to know which sources are degraded before trusting a result.

  clinical-trials-pp-cli health --json

Command Reference

clinicaltrials-gov-version — Manage clinicaltrials gov version

• clinical-trials-pp-cli clinicaltrials-gov-version — API and data versions. API version follows Semantic Versioning 2.0.0 Schema.

stats — Data statistics

• clinical-trials-pp-cli stats field-values — Value statistics of the study leaf fields.
• clinical-trials-pp-cli stats list-field-sizes — Sizes of list/array fields. To search studies by a list field size, use AREA[FieldName:size] search operator.
• clinical-trials-pp-cli stats size — Statistics of study JSON sizes.

studies — Related to clinical trial studies

• clinical-trials-pp-cli studies enums — Returns enumeration types and their values.
• clinical-trials-pp-cli studies fetch-study — Returns data of a single study.
• clinical-trials-pp-cli studies list — Returns data of studies matching query and filter parameters. The studies are returned page by page.
• clinical-trials-pp-cli studies metadata — Returns study data model fields.
• clinical-trials-pp-cli studies search-areas — Search Docs and their Search Areas.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

clinical-trials-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Recipes

Bounded agent-friendly search

clinical-trials-pp-cli search "glioblastoma" --json --limit 20

Searches the merged multi-source mirror and returns a bounded result set an agent can parse.