agentsclimarketplace
Sign in

Shelves

Healthcare

1,364 rows from 187 repositories

Clinical, medical and life-sciences work.

What Healthcare skills agree on

186 skill files read, by 147 of the 152 authors on this shelf whose files we hold, 2026-08-07

The middle one of the 185 measured here is ~1.9k tokens long, counted with cl100k_base

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Split clinical datasets strictly by patient11 of 147 in 3 filesalso worded as split datasets by patient or visit not sample; split data at the patient level
  2. Export trial data to CSV format11 of 147 in 2 files
  3. Retrieve trial details using an NCT ID11 of 147 in 2 filesalso worded as Retrieve specific trial details using NCT ID
  4. Stop and ask for clarification if inputs or criteria are missing7 of 147 in 3 filesalso worded as ask for clarification if success criteria are missing; stop and ask for clarification if inputs are missing
  5. Validate output file structure before proceeding6 of 147 in 2 files
  6. Verify all required connectors are available6 of 147 in 2 filesalso worded as verify required connectors on startup
  7. Check for an existing incomplete request6 of 147 in 2 filesalso worded as check for existing incomplete requests
  8. Read the actual subskill markdown files6 of 147 in 2 filesalso worded as read subskill files at runtime
  9. Display a notification before and after each connector call6 of 147 in 2 filesalso worded as display a notification before external calls
  10. Warn the user if clinical data extraction confidence is below 60%6 of 147 in 2 filesalso worded as warn user if data extraction confidence is low
  11. Never overwrite existing files without confirmation6 of 147 in 2 filesalso worded as never overwrite existing waypoint without confirmation
  12. Use only when the task clearly matches the described scope6 of 147 in 2 filesalso worded as use only when the task matches the described scope
  13. Put executive summary on page one6 of 147 in 3 filesalso worded as place the complete executive summary on page one; Build a mandatory first-page executive summary
  14. Assign a grade rating to every treatment recommendation5 of 147 in 2 filesalso worded as apply GRADE grading to treatment recommendations
  15. De-identify patient data per HIPAA Safe Harbor5 of 147 in 2 filesalso worded as de-identify patient data before leaving HIPAA environments

What they tell it not to do

  1. Do not include the same patient in multiple data splits9 of 147 in 3 filesalso worded as do not split rows when patients contribute multiple samples; do not put the same patient in both train and test splits
  2. Do not overwrite existing files without checking8 of 147 in 4 filesalso worded as do not overwrite existing waypoint without confirmation; never overwrite existing data
  3. Do not treat output as validation, testing, or expert review7 of 147 in 3 filesalso worded as do not treat output as expert review substitute; treat the output as a substitute for validation
  4. Do not generate fake data when queries fail6 of 147 in 2 files
  5. Do not skip prerequisite checks6 of 147 in 2 files
  6. Do not pre-read the whole skill on startup6 of 147 in 2 filesalso worded as do not pre-read whole skill on bootup
  7. Do not proceed if a subskill had errors6 of 147 in 2 filesalso worded as do not proceed if current subskill had errors
  8. Do not call diagnosis lookup multiple times for same codes6 of 147 in 2 filesalso worded as do not call diagnosis validation repeatedly for same codes
  9. Do not omit confidence intervals5 of 147 in 2 filesalso worded as Omit confidence flags for ambiguous data
  10. Do not diagnose or treat patients5 of 147also worded as do not diagnose or treat injuries; do not diagnose or prescribe

What they expect to be installed

  1. python319 of 147 in 12 files
  2. ClinicalTrials.gov API v213 of 147 in 4 files
  3. requests12 of 147 in 3 files
  4. pyhealth10 of 147 in 2 files
  5. CMS Fee Schedule6 of 147 in 2 files
  6. PubMed5 of 147
  7. LaTeX5 of 147 in 2 files
  8. uv pip8 of 147 in 1 file
  9. CMS Coverage MCP5 of 147 in 1 file
  10. ICD-10 MCP5 of 147 in 1 file

What they ask it to produce

  1. CSV file11 of 147 in 2 filesalso worded as extracted csv file
  2. Waypoints/assessment.json6 of 147 in 2 filesalso worded as waypoints/decision.json
  3. Outputs/notification_letter.txt6 of 147 in 2 files
  4. Treatment recommendation report5 of 147 in 2 files
  5. Patient cohort analysis5 of 147 in 2 filesalso worded as patient cohort analysis report
  6. Compliance report5 of 147also worded as compliance review report; safety compliance check report
  7. Calibrated healthcare predictions8 of 147 in 1 file
  8. Model fairness assessments8 of 147 in 1 file

When Healthcare authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 147 authors, with the skills that name each one

How Healthcare skills are built

1,261 skill directories by 148 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 3 files, 17.3 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill59 of 148 authors, 432 of 1,261 skills
  2. files ship beside it89 of 148 authors, 829 of 1,261 skills
  3. executable scripts ship inside51 of 148 authors, 386 of 1,261 skills

The folders they converge on

  1. references/72 of 148 authors, 395 of 1,261 skills
  2. scripts/46 of 148 authors, 229 of 1,261 skills
  3. assets/24 of 148 authors, 91 of 1,261 skills
  4. agents/14 of 148 authors, 26 of 1,261 skills
  5. evals/11 of 148 authors, 105 of 1,261 skills
  6. examples/10 of 148 authors, 117 of 1,261 skills

  • Nihaisha nishi tcm

    JuneYaooo/nihaisha-nishi-tcm Skill

    no license1,915★

    倪海厦中医课程资料的 Agent Skill：支持课程检索、方证穴位辨析、学习笔记整理与板书截图证据索引。 | An Agent Skill for Ni Haisha TCM course study, formula-pattern lookup, acupoint reference, and screenshot evidence indexing.

  • Academic aio

    Aperivue/medsci-skills/skills/academic-aio Skill

    258★ repo

    Agent Skills for medical research — literature search, reporting-guideline & citation checks, statistics, publication figures, submission. Works with Claude Code, Codex, Cursor & GitHub Copilot. Built by a physician-researcher, tested on real publications. MIT.

  • Aws genai ml architect

    awslabs/hcls-agent-skills/skills/aws-genai-ml-architect Skill

    13★ repo

    Agent skills for healthcare and life sciences: genomics, imaging, claims, drug discovery, and more. Works with Amazon Quick, Kiro, Amazon AgentCore, AWS Strands SDK, Claude Code, Codex, and any Agent Skills-compatible platform.

  • Medical Terminologies MCP

    SidneyBissoli/medical-terminologies-mcp/io.github.SidneyBissoli/medical-terminologies-mcp MCP server

    9★ repo

    Diagnoses, drugs & lab codes: ICD-11, SNOMED, LOINC, RxNorm, MeSH, ATC, CID-10. 37 tools, MIT.

  • Clinical evidence reviewer

    Tuminha/dental-ai-skills/clinical-evidence-reviewer Skill

    5★ repo

    AI Skills for Dentists - Research critique, clinical evidence review, and content creation tools for Claude Desktop and Codex

  • Last EHR — Medplum

    cbetz/last-ehr/io.github.cbetz/last-ehr MCP server

    4★ repo

    FHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes.

  • Evidence based fitness coach

    Lancetnik/evidence-based-fitness-coach/skills/evidence-based-fitness-coach Skill

    3★ repo

    Evidence-based fitness coaching as an installable Agent Skill — strength training programs and nutrition plans grounded in scientific consensus. Summarized from the Podlodka podcast.

  • Med mentor

    Premansh12/med-mentor Skill

    2★

    A Claude skill for medical training, board prep, and clinical reasoning through interactive, step-by-step HTML lessons.

  • Pipeline assessment

    Ficere/pipeline-assessment Skill

    2★

    MNC-style pharmaceutical pipeline asset assessment Agent Skill

  • Hormonaly Clinical Intelligence

    Hormonaly-ai/hormonaly-public/io.github.Hormonaly-ai/hormonaly MCP server

    no license2★ repo

    24 tools for evidence-graded clinical queries, hormones, peptides, longevity & drug interactions.

  • Medical codes mcp server

    cyanheads/medical-codes-mcp-server/io.github.cyanheads/medical-codes-mcp-server MCP server

    2★ repo

    Offline US medical code lookup and crosswalk — ICD-10-CM/PCS, HCPCS Level II, RxNorm. Keyless.

  • Clinical trial design

    wei-ai-lab/clinical-trial-design/io.github.wei-ai-lab/clinical-trial-design MCP server

    2★ repo

    Phase 2/3 clinical trial design via gsDesign / gsDesign2: sample size, GS boundaries, multiplicity

  • Medical research thesis supervisor

    mohamedhadyashry/medical-research-thesis-supervisor/medical-research-thesis-supervisor Skill

    1★ repo

    A Claude Agent Skill that turns Claude into a rigorous medical research supervisor — search strategy, evidence synthesis, scientific writing, and peer-review-grade QA. Never fabricates citations.

  • Medical fact check

    kgraph57/evidentia/skills/medical-fact-check Skill

    1★ repo

    Open-source medical citation verifier: catches fabricated DOI/PMID/NCT references with CLI, MCP, and Claude Code skill.

  • Need a hug

    lonelymoon87/need-a-hug/skills/need-a-hug Skill

    1★ repo

    Lightweight emotional first-aid Agent Skill for AI agents: comfort overwhelmed developers before another plan. Works with Claude Code, Codex, Cursor, Kiro, VS Code and more.

  • Dementia causal cohort auditor

    Tianyu-Qu/nacc-dementia-cohort-auditor-skill/skills/dementia-causal-cohort-auditor Skill

    1★ repo

    A NACC-first Codex skill for dementia cohort design auditing, cohort construction, data-quality checks, and causal-readiness review.

  • Appendix

    appendixhealth/mcp-server/com.appendix/appendix MCP server

    no license1★ repo

    Physician-reviewed medical opinions and prescriptions for AI agents.

  • Anteos Health — Medical Appointment Booking

    Anteos-Health/anteos-mcp/io.github.Anteos-Health/anteos-booking MCP server

    no license1★ repo

    Book medical appointments with French doctors by specialty and city via AI agents.

  • Dingdawg healthcare agent

    DingDawg-dev/dingdawg-healthcare-agent/io.github.DingDawg-dev/dingdawg-healthcare-agent MCP server

    no license1★ repo

    HIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier.

  • Dingdawg healthcare agent

    dingdawg/dingdawg-healthcare-agent/io.github.dingdawg/dingdawg-healthcare-agent MCP server

    no license1★ repo

    HIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier.

  • Hipaa ai compliance

    EliasAli0720/HIPAA-agent-skill/skills/hipaa-ai-compliance Skill

    0★ repo

    HIPAA compliance skills for AI coding agents (Claude Code, Codex, Cursor, Gemini). 10 senior-grade skills: scoping, app dev, websites, AI/LLM, code review + PHI scanner, risk analysis, breach response, BAAs, de-identification, compliance programs. Exact 45 CFR citations, OCR enforcement through 2026.

  • Genomic prediction skill

    scicrow/genomic-prediction-skill Skill

    no license0★

    Execution blueprints and code templates for fitting genomic prediction models, including GBLUP, GFBLUP, MultiBLUP, Bayesian methods (BayesA, BayesB, BayesC, BayesCpi, BayesRC, Bayesian Lasso), and Random Forest using peer-reviewed software.

  • Protocol qa

    thebitanpaul/VERA/.claude/skills/protocol-qa Skill

    no license0★ repo

    Version-Explicit Retrieval & Answering - VERA answers a trial coordinator's question about what a clinical-trial protocol currently requires, using only the version that governs the trial today — and it abstains rather than guessing when the protocol doesn't cover the question.

  • Hipaa marketing check

    Thilina099/rubysky-skills/skills/hipaa-marketing-check Skill

    0★ repo

    Free Claude Skills for local service businesses, healthcare orgs, and nonprofits. Lead follow-up, HIPAA marketing risk checks, event sponsorship revenue. By RubySky Digital, Nashville.

  • Super healthcare wellness

    arpitexplores/super-healthcare-wellness Skill

    0★

    Portable Markdown skill for AI vibe coding with healthcare and wellness workflows: health trend analysis, care workflows, wellness data, safety boundaries, and non-diagnostic guidance.

  • Clinical note eval

    yashpatil582/agent-skills/clinical-note-eval Skill

    0★ repo

    Anthropic Agent Skills packaging shipped eval methods: gaming-resistant clinical-note grounding eval + token-F1 scorer. Stdlib-only, runs offline.

  • Labcoat biomedical discipline

    qchiujunhao/labcoat/skills/labcoat-biomedical-discipline Skill

    0★ repo

    Skills, hooks, and CLI checks for safer biomedical AI coding agents.

  • Medical bill and claim appeal navigator

    satishTheLegend/medical-bill-and-claim-appeal-navigator Skill

    0★

    From a denial letter and an itemized bill to a verified error log, an appeal packet, and a negotiation script — the whole fight, organized.

  • Antigen epitope pipeline

    ruthannepai-tech/inflammatory-target-discovery-skills/skills/antigen-epitope-pipeline Skill

    0★ repo

    Disease-agnostic methodology stack for computational target discovery and antigen-specific therapeutic design in inflammatory/immune disorders (EGIDs, celiac, IBD, autoimmune).

  • Anatomy image auditor

    augustfu-droid/anatomy-image-auditor/skills/anatomy-image-auditor Skill

    0★ repo

    Whole-body anatomy and action-coherence quality control for human and hominin images

  • Nursing Home Database

    jmtroller/nhd-mcp-public-documentation/com.nursinghomedatabase/mcp MCP server

    no license0★ repo

    MCP server for US nursing facility search and ownership lookup (NursingHomeDatabase).

  • Clinical trials ai mcp

    CSOAI-ORG/clinical-trials-ai-mcp/io.github.CSOAI-ORG/clinical-trials-ai-mcp MCP server

    0★ repo

    Clinical Trials Ai MCP Server by MEOK AI Labs

  • Healthcare fhir mcp

    CSOAI-ORG/healthcare-fhir-mcp/io.github.CSOAI-ORG/healthcare-fhir-mcp MCP server

    0★ repo

    healthcare-fhir-mcp MCP server by MEOK AI Labs

  • Mdr medical device mcp

    CSOAI-ORG/mdr-medical-device-mcp/io.github.CSOAI-ORG/mdr-medical-device-mcp MCP server

    0★ repo

    EU MDR (Reg 2017/745) and IVDR (Reg 2017/746) compliance for medical device + IVD manufacturers...

  • GPH Intelligence - Healthcare Vendor Finder

    Crindo2/gph-mcp-server/io.github.Crindo2/gph-mcp-server MCP server

    0★ repo

    Find 76,000+ curated healthcare service vendors across 25 categories and all 50 US states.

  • Fonteum — Healthcare Provider Data

    Fonteum/mcp-server/io.github.Fonteum/mcp-server MCP server

    no license0★ repo

    Source-provenanced US federal healthcare provider data over MCP, with 14-tuple provenance.

  • Painprep mcp server

    Goingparabolic/painprep-mcp-server/io.github.Goingparabolic/painprep-mcp-server MCP server

    0★ repo

    Interventional pain medicine MCP: Medicare checklists, CPT/ICD-10, ASRA, prior-auth & appeals

  • Phi longevity prism

    Philongevity/phi-mcp-server/io.github.Philongevity/phi-longevity-prism MCP server

    0★ repo

    Analyze biomarker panels with an MD-led clinical engine. Guideline-cited. Synthetic data only.

  • 水素分子医学文献データベース — Molecular hydrogen medical literature (H2 Papers)

    h2-papers/h2-papers-mcp-server/io.github.h2-papers/mcp-server MCP server

    0★ repo

    PubMed molecular-hydrogen medical literature with delivery-aware safety notes inline.

  • Cure Cancer With AI

    hifarrer/ccwai-api/io.github.hifarrer/cure-cancer-with-ai MCP server

    no license0★ repo

    Free oncology data (research, trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions.

  • Mcp ratchet clinical charting

    m2ai-mcp-servers/mcp-ratchet-clinical-charting/io.github.m2ai-mcp-servers/mcp-ratchet-clinical-charting MCP server

    0★ repo

    MCP server for clinical charting with Claude - document patient visits to EMR

  • Clinicaltables

    pipeworx-io/mcp-clinicaltables/io.github.pipeworx-io/clinicaltables MCP server

    0★ repo

    NIH Clinical Tables: ICD-10/9, RxTerms, LOINC, NPI, conditions search. Keyless.

  • disease

    pipeworx-io/mcp-disease/io.github.pipeworx-io/disease MCP server

    0★ repo

    Disease MCP — wraps disease.sh API (COVID-19 statistics, no auth required)

  • Hpo Api

    pipeworx-io/mcp-hpo-api/io.github.pipeworx-io/hpo-api MCP server

    0★ repo

    Human Phenotype Ontology — clinical phenotype terms + gene/disease annotations

  • Medical Codes

    pipeworx-io/mcp-medical-codes/io.github.pipeworx-io/medical-codes MCP server

    0★ repo

    Medical codes MCP.

  • Pharma mcp

    pubspro/pharma-mcp/io.github.pubspro/pharma-mcp MCP server

    no license0★ repo

    MCP server for ClinicalTrials.gov, PubMed, FDA drug labels, FAERS, and ICH guidelines.

  • Pharma regulatory

    rootsbymenda/pharma-mcp-server/io.github.rootsbymenda/pharma-regulatory MCP server

    0★ repo

    Drug safety: DrugBank, interactions, FAERS, WHO, TGA. 7 databases. Free.

  • Sniff mcp

    Sniffscore/sniff-mcp/world.sniff/sniff-mcp MCP server

    0★ repo

    Canine genomics for agents: breed allele frequencies, AI pathogenicity + OMIA clinical disease layer

  • Clinical anonymization

    elisaterumi-ai/agent-skills-in-practice/examples/clinical-anonymization Skill

    129★ repo

    Learn what AI skills are and how to design, structure, and use them in real-world agent systems.

  • Biomarker discovery

    awslabs/hcls-agent-skills/skills/biomarker-discovery Skill

    13★ repo

    Agent skills for healthcare and life sciences: genomics, imaging, claims, drug discovery, and more. Works with Amazon Quick, Kiro, Amazon AgentCore, AWS Strands SDK, Claude Code, Codex, and any Agent Skills-compatible platform.

  • Healthcare audit logger

    1Mangesh1/hipaa-guardian/skills/healthcare-audit-logger Skill

    7★ repo

    AI agent skill for HIPAA compliance - PHI/PII detection, code scanning, audit reports, and remediation guidance

  • Dental content creator

    Tuminha/dental-ai-skills/dental-content-creator Skill

    5★ repo

    AI Skills for Dentists - Research critique, clinical evidence review, and content creation tools for Claude Desktop and Codex

  • Ankle sprain

    CyrilLeMat/temper-skills/examples/ankle_sprain/output/ankle-sprain Skill

    2★ repo

    Test suites + deterministic Python for your agent skills' decision logic. Adversarial persona reviewers write the tests; the generated code must keep passing them — zero LLM calls at inference. Try: uvx temper-skills audit <skill.md>

  • Biomarker discovery

    Alim430/bioresearch-agent/skills/biomedical/biomarker-discovery Skill

    1★ repo

    Executable biomedical workflows for AI assistants — literature analysis, biomarker discovery, and Mendelian randomization through reproducible agent skills.

  • Injury prehab

    SkillMedev/health-and-longevity/skills/injury-prehab Skill

    1★ repo

    Evidence-informed skills for building strength, mobility, and lasting health.

  • Clinical data analysis

    palmiro72-coder/palmiros-claude/plugins/palmiros-clinical-br/skills/clinical-data-analysis Skill

    0★ repo

    Marketplace de plugins do Claude Code — 14 skills agrupadas em 5 plugins: operações clínicas BR (endo + derm), revenue cycle US, pesquisa científica (harmonia sexagesimal + patentes + mineração), criação visual via Gemini e SecOps/infra.

  • Glp1 prescriptions

    chia-health/skills/glp1-prescriptions Skill

    0★ repo

    Installable skills.sh skills for the Chia Health prescription MCP — GLP-1 weight loss (semaglutide, tirzepatide) and peptide therapies (sermorelin, NAD+, glutathione).

  • Ab testing healthcare

    rbr7/MedClawMini/skills/ab-testing-healthcare Skill

    0★ repo

    A focused, production-minded library of 197 clinical-AI and healthcare data-science skills for the OpenClaw agent platform featuring data quality, clinical NLP, big-data ML, explainable AI, drug safety, and regulatory.

  • Investigate health

    OpenBioHack/openbiohack/skills/investigate-health Skill

    0★ repo

    Free, non-directive, first-principles thinking partner for hard, ambiguous health challenges & optimisation — runs in your own Claude Code, on your own data. Educational, not medical advice.

  • Labcoat biomedical ml hygiene

    qchiujunhao/labcoat/skills/labcoat-biomedical-ml-hygiene Skill

    0★ repo

    Skills, hooks, and CLI checks for safer biomedical AI coding agents.

All 1,364 in the catalog