Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Filter by category
53,895 results · page 149 of 1,797
- View details
configuring-privacy-policiesSkillDatabases & data
Lets your agent pick and customize privacy policy profiles for de-identifying health data under HIPAA, GDPR, and other rules.
Ready to connect★ 5k
- View details
defining-cohort-phenotypesSkillDev tools
Lets your agent write patient cohort and phenotype definitions in OHDSI ATLAS style over the OMOP data model.
Ready to connect★ 5k
- View details
deidentify-a-datasetSkillDatabases & data
Lets your agent remove personal health details from text columns in a local CSV, JSONL, or Parquet file.
Ready to connect★ 5k
- View details
deidentifying-clinical-textSkillDocs & knowledge
Lets your agent remove or mask patient identifiers like names and dates from medical notes before sharing.
Ready to connect★ 5k
- View details
deidentifying-multilingual-textSkillDocs & knowledge
Lets your agent remove personal information from medical notes in languages like Spanish, German, or Arabic.
Ready to connect★ 5k
- View details
deploying-openmed-mcpSkillCloud & infra
Lets your agent run a local server that extracts medical entities, personal info, and de-identifies clinical text.
Ready to connect★ 5k
- View details
detecting-pv-signalsSkillDev tools
Lets your agent analyze FDA drug side-effect reports to flag possible safety signals using statistical methods.
Ready to connect★ 5k
- View details
enforcing-nophi-loggingSkillCloud & infra
Lets your agent add a guard that scrubs patient health information out of logs, traces, and error reports.
Ready to connect★ 5k
- View details
etl-to-omop-cdmSkillDatabases & data
Lets your agent load medical facts extracted from clinical notes into OMOP CDM tables for health research analytics.
Ready to connect★ 5k
- View details
evaluating-with-leakage-gatesSkillAI & models
Lets your agent test a clinical text model for patient-identity leaks before deciding if it is safe to release.
Ready to connect★ 5k
- View details
exporting-bulk-fhirSkillDev tools
Lets your agent export bulk FHIR health data and run de-identification and entity recognition on it at scale.
Ready to connect★ 5k
- View details
exporting-to-fhirSkillDev tools
Lets your agent convert medical text analysis results into standard FHIR health records like conditions and medications.
Ready to connect★ 5k
- View details
extract-clinical-entities-to-fhirSkillAI & models
Lets your agent pull clinical terms out of de-identified medical text and turn them into standard FHIR health records.
Ready to connect★ 5k
- View details
extracting-clinical-entitiesSkillFiles & storage
Lets your agent find medical terms like diseases, drugs, and genes in text and return them as JSON, CSV, or HTML.
Ready to connect★ 5k
- View details
extracting-dicom-metadataSkillFiles & storage
Lets your agent read medical imaging file headers to pull study metadata, report text, and flag patient-identifying info.
Ready to connect★ 5k
- View details
extracting-lab-tablesSkillFiles & storage
Lets your agent pull lab results like CBC or lipid panels from PDFs and scans into structured rows.
Ready to connect★ 5k
- View details
extracting-pii-entitiesSkillDev tools
Lets your agent find personal identifiers like names, dates, and SSNs in clinical text and report where they appear.
Ready to connect★ 5k
- View details
extracting-sdohSkillSecurity
Lets your agent find social factors like housing or food insecurity in clinical notes and map them to ICD-10 Z-codes.
Ready to connect★ 5k
- View details
fetching-fhir-resourcesSkillDev tools
Lets your agent pull patient charts, reports, and lab results from a hospital records system and extract clinical notes.
Ready to connect★ 5k
- View details
gating-deid-leakageSkillAI & models
Adds a CI check that fails your build if a de-identification model misses personal health info or leaks identifiers.
Ready to connect★ 5k
- View details
generating-synthea-dataSkillFiles & storage
Lets your agent generate realistic fake patient health records for testing and demos.
Ready to connect★ 5k
- View details
generating-synthetic-surrogatesSkillDocs & knowledge
Lets your agent replace patient details in clinical notes with realistic fake values so text stays readable.
Ready to connect★ 5k
- View details
ingesting-clinical-documentsSkillFiles & storage
Lets your agent turn scanned faxes, photos, and CSV/XML exports of clinical documents into clean text for de-identification.
Ready to connect★ 5k
- View details
linking-umls-conceptsSkillDev tools
Lets your agent link extracted medical terms to standard UMLS concept codes, resolving synonyms across vocabularies.
Ready to connect★ 5k
- View details
loading-openmed-modelsSkillAI & models
Lets your agent load biomedical NER models and reuse them efficiently across calls, even fully offline.
Ready to connect★ 5k
- View details
mapping-loincSkillDev tools
Lets your agent convert lab test and clinical observation names into standard LOINC codes.
Ready to connect★ 5k
- View details
mapping-to-snomedSkillDev tools
Lets your agent map clinical terms like findings and procedures to SNOMED CT codes using your own terminology server.
Ready to connect★ 5k
- View details
mining-pubmed-literatureSkillDev tools
Lets your agent search PubMed and fetch biomedical abstracts and citations for conditions or drugs.
Ready to connect★ 5k
- View details
normalizing-rxnormSkillDev tools
Lets your agent convert medication names into standard RxNorm codes and find related drug identifiers.
Ready to connect★ 5k
- View details
parsing-ccda-documentsSkillDocs & knowledge
Lets your agent read C-CDA clinical documents and extract readable sections plus coded medical entries.
Ready to connect★ 5k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
53,462 of the 53,895 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.