Ready to supercharge your AI agents?

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

Clinical Guidelines Search & Retrieval · mims-harvard | DecimalAI

researchby mims-harvard

Clinical Guidelines Search & Retrieval

mims-harvard/tooluniverse-clinical-guidelines

Source mims-harvard/ToolUniverse ↗License Apache-2.0

Search and retrieve clinical practice guidelines from 12+ authoritative sources — NICE, WHO, NCCN, AHA, ADA, SIGN, USPSTF, IDSA, NIH consensus, ESMO/ESC/EASL European societies, and US specialty associations.

NewMaintained

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 4 of 10 test cases with the skill, and 7 of 10 without it.

Without skill74%

With skill43%

Checks it passed that the model alone missed

The response lists NICE at the top of the search priority hierarchy.
The response specifies passing guideline_id as an integer parameter rather than a gene symbol string.
The response specifies deduplicating returned recommendation records by phenotype before presenting recommendations.

2 fixed8 passed either way4 still failing9 broke

Pass-rate lift: -30 pp
Tokens: +255%
Agent turns: 0%
Response time: -10%

Model gemini-3.6-flashMeasured 8/6/2026v110 of 23 cases passed with skill · 10 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-clinical-guidelines/SKILL.md https://app.decimal.ai/s/mims-harvard-tooluniverse-clinical-guidelines/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add mims-harvard-tooluniverse-clinical-guidelines, 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-clinical-guidelines/ and pins it in .decimal/skills.lock

decimalai skills add mims-harvard-tooluniverse-clinical-guidelines

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 2

Prompt

When programmatically retrieving pharmacogenomic clinical recommendations from the CPIC database using API tools, what parameter identifier must be passed to retrieve dosing recommendations, and how should duplicate phenotypes in the returned list be handled?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies passing guideline_id as an integer parameter rather than a gene symbol string.	Missed	Passed
The response specifies deduplicating returned recommendation records by phenotype before presenting recommendations.	Missed	Passed

case-09 · 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.md297 linessingle file

Clinical Guidelines Search & Retrieval

Guideline Hierarchy

Not all guidelines carry equal weight. Evaluate sources in this order:

NICE and WHO — Evidence-graded, regularly updated, rigorous systematic review process. NICE guidelines include explicit recommendation strength (e.g., "offer" vs "consider").
Society guidelines (AHA, ADA, NCCN, SIGN) — Expert-consensus panels within a specialty. May lag behind the latest evidence by 1-3 years. Strong within their domain but narrower scope.
Aggregator databases (GIN, TRIP, OpenAlex) — Index guidelines from multiple societies. Good for breadth and discovery, but you must verify the original source.
Literature databases (PubMed, EuropePMC) — Return guideline-related publications, not curated guideline text. Useful as a fallback, not a primary source.

Always check publication date. A 2015 guideline may be superseded by a 2024 update. When presenting results, include the year prominently and note if newer guidance may exist.

COMPUTE, DON'T DESCRIBE

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Search Strategy

Step 1: Start Narrow, Then Broaden

Search the condition name + "guideline" in NICE, TRIP, and GIN simultaneously (parallel calls).
If the question targets a specialty, add the society tool: AHA for cardiology, ADA for diabetes, NCCN for oncology, CPIC for pharmacogenomics.
If initial searches return nothing, broaden to the disease category (e.g., "heart failure" instead of "HFpEF with SGLT2 inhibitors").
If society-specific tools fail, fall back to PubMed/EuropePMC with [condition] guideline [year].

Step 2: Search at Least 3 Sources

Always query a minimum of 3 databases to catch guidelines that one source may miss. Prioritize: NICE > GIN > TRIP > Society-specific > Literature databases.

Step 3: Retrieve Full Text When Available

After identifying relevant guidelines from search results, use full-text tools to get recommendation details before synthesizing.

Diagnostic Test Selection Reasoning

When a clinical question asks "which test should be ordered?" or "what is the most appropriate next diagnostic step?", apply this reasoning framework BEFORE searching guidelines.

Track record

Benchmark

4 / 10

test cases passed, vs 7 / 10 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-clinical-guidelines/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/2/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

tooluniverse-clinical-guidelinesSearch and retrieve clinical practice guidelines across 12+ authoritative sources including NICE, WHO, ADA, AHA/ACC, NCCN, SIGN, CPIC, CMA, CTFPHC, GIN, MAGICapp, PubMed, EuropePMC, TRIP, and OpenAlex. Covers disease management, cardiology, oncology, diabetes, pharmacogenomics, and more. Use when users ask about clinical guidelines, treatment recommendations, standard of care, evidence-based medicine, or drug-gene dosing recommendations.Close match+32 pp pass-rate lift

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

Clinical Guidelines Search & Retrieval

Guideline Hierarchy

COMPUTE, DON'T DESCRIBE

Search Strategy

Step 1: Start Narrow, Then Broaden

Step 2: Search at Least 3 Sources

Step 3: Retrieve Full Text When Available

Diagnostic Test Selection Reasoning

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills