Skip to content
TrustedSkillsbeta
Back to all skills

Tooluniverse Adverse Event Detection

Checked
mims-harvard·vlatest·other·Apache-2.0

Detects potential adverse events from clinical notes using ToolUniverse, improving patient safety monitoring and rapid response identification.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add mims-harvard/tooluniverse --skill tooluniverse-adverse-event-detection -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

mims-harvard

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned mims-harvard/tooluniverse at f5c37eebeb.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
f5c37eebeb
Manifest
skills/tooluniverse-adverse-event-detection/SKILL.md
Scanned
16 files, 3,669 lines
Copies in repo
3 — all of them scanned
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill, Tooluniverse Adverse Event Detection, automatically identifies and analyzes potential adverse drug events from clinical data. It leverages a pipeline incorporating FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence to generate a quantitative Safety Signal Score (0-100). The goal is to improve patient safety monitoring and enable rapid response identification by quantifying signals for regulatory and clinical decision-making.

When to use it

  • When investigating reports of unexpected adverse events associated with a drug.
  • To prioritize serious adverse events like deaths or hospitalizations for immediate analysis.
  • For assessing the potential risk of a new drug based on available data sources.
  • To determine if an observed adverse event is specific to a drug, common across a class, or potentially due to confounding factors.

Key capabilities

  • Adverse Event Signal Detection: Identifies adverse events reported more than expected using statistical thresholds (PRR >= 2.0, N >= 3, lower CI > 1.0).
  • Quantitative Scoring: Generates a Safety Signal Score (0-100) to quantify the severity and likelihood of an adverse event.
  • Multi-Source Data Integration: Combines data from FAERS, FDA labels, OpenTargets, DrugBank, and literature sources.
  • Mechanism of Action Analysis: Uses tools like OpenTargets_get_drug_mechanisms_of_action_by_chemblId and drugbank_get_targets_by_drug_name_or_drugbank_id to assess biological plausibility.
  • Evidence Grading: Assigns evidence grades (T1-T4) to support findings.

Example prompts

  • "Analyze the adverse event 'myocardial infarction' associated with drug X."
  • "What is the Safety Signal Score for 'liver failure' and drug Y?"
  • "Is the adverse event 'rash' biologically plausible given the mechanism of action of drug Z?"

Tips & gotchas

  • Always use English drug names when interacting with ToolUniverse tools.
  • The skill prioritizes serious adverse events (deaths, hospitalizations) for analysis.
  • Results are based on statistical thresholds and data from specific sources; consider these limitations when interpreting findings.