Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Drug-Drug Interaction Prediction & Risk Assessment · mims-harvard | DecimalAI

scienceby mims-harvard

Drug-Drug Interaction Prediction & Risk Assessment

mims-harvard/tooluniverse-drug-drug-interaction

Source mims-harvard/ToolUniverse ↗License Apache-2.0

Assess drug-drug interactions — CYP metabolic interactions (substrate/inhibitor/inducer), transporter (P-gp, BCRP, OATP) effects, pharmacodynamic synergy/antagonism, clinical significance scoring, and management recommendations.

SkillScore77Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Clinical / Healthcare pack

Last verified 8/6/2026

What it changes

Passed 13 of 17 test cases with the skill, and 5 of 17 without it.

Without skill32%

With skill77%

Checks it passed that the model alone missed

Calculates the risk score on a 0-100 scale.
Calculates risk using the 0-100 scale system.
Quantifies risk using a 0-100 numerical score.

and 15 more in the full report

11 fixed6 passed either way4 still failing1 broke

Pass-rate lift: +45 pp
Tokens: +302%
Agent turns: 0%
Response time: +113%

Model gemini-3.6-flashMeasured 8/6/2026v117 of 22 cases passed with skill · 17 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/mims-harvard-tooluniverse-drug-drug-interaction/SKILL.md https://app.decimal.ai/s/mims-harvard-tooluniverse-drug-drug-interaction/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add mims-harvard-tooluniverse-drug-drug-interaction, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/mims-harvard-tooluniverse-drug-drug-interaction/ and pins it in .decimal/skills.lock

decimalai skills add mims-harvard-tooluniverse-drug-drug-interaction

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/mims-harvard-tooluniverse-drug-drug-interaction/SKILL.md https://app.decimal.ai/s/mims-harvard-tooluniverse-drug-drug-interaction/SKILL.md

Raw file: /s/mims-harvard-tooluniverse-drug-drug-interaction/SKILL.md ↗ · machine-readable summary at /s/mims-harvard-tooluniverse-drug-drug-interaction.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

I need a complete polypharmacy safety review for a patient concurrently taking simvastatin, amiodarone, warfarin, and clarithromycin. Please provide a structured interaction analysis covering metabolic pathways, severity grading, evidence ratings, risk scoring, monitoring parameters, and suggested substitute medications.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies the contraindicated CYP3A4-mediated rhabdomyolysis risk between simvastatin and clarithromycin.	Passed	Passed
Rates evidence using star grading notation like ★★★ for FDA labels.	Missed	Passed
Calculates interaction risk using a 0 to 100 numerical score scale.	Missed	Passed

case-02 · gemini-3.6-flash · 8/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md334 lines2 filesincludes scripts

Drug-Drug Interaction Prediction & Risk Assessment

Systematic analysis of drug-drug interactions with evidence-based risk scoring, mechanism identification, and clinical management recommendations.

KEY PRINCIPLES:

Report-first approach - Create DDI_risk_report.md FIRST, then populate progressively
Bidirectional analysis - Always analyze A→B and B→A interactions (effects may differ)
Evidence grading - Grade all DDI claims by evidence quality (★★★ FDA label, ★★☆ clinical study, ★☆☆ theoretical)
Risk scoring - Multi-dimensional scoring (0-100) combining mechanism + severity + clinical evidence
Patient safety focus - Provide actionable clinical guidance, not just theoretical interactions
Mandatory completeness - All analysis sections must exist with explicit "No interaction found" when appropriate

LOCAL PHARMACOLOGY REFERENCE (USE FIRST)

Before querying any external database, consult the local reference script for instant answers on CYP/UGT roles and known critical interactions:

scripts/pharmacology_ref.py   (no external dependencies, runs offline)

# Q927 pattern — valproate + lamotrigine:
python scripts/pharmacology_ref.py --type interaction --drug1 "valproate" --drug2 "lamotrigine"

# What does a drug do to UGT enzymes?
python scripts/pharmacology_ref.py --type ugt_inhibitor --drug "valproate"

# What enzymes metabolise a drug?
python scripts/pharmacology_ref.py --type ugt_substrate --drug "lamotrigine"
python scripts/pharmacology_ref.py --type cyp_substrate --drug "warfarin"

# Which drugs inhibit / induce a specific CYP?
python scripts/pharmacology_ref.py --type cyp_inhibitor --enzyme "CYP3A4"
python scripts/pharmacology_ref.py --type cyp_inducer  --enzyme "CYP2C9"

# Narrow therapeutic index checklist:
python scripts/pharmacology_ref.py --type narrow_ti

# All known interactions for one drug:
python scripts/pharmacology_ref.py --type all_interactions --drug "lamotrigine"

Track record

Benchmark

13 / 17

test cases passed, vs 5 / 17 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mims-harvard / ToolUniverse

skills/tooluniverse-drug-drug-interaction/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/2/2026Version v1Bundled 1 file · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Drug-Drug Interaction Prediction & Risk Assessment

LOCAL PHARMACOLOGY REFERENCE (USE FIRST)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills