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
55,257 results · page 167 of 1,842
- View details
batch-processing-clinical-textSkillDatabases & data
Lets your agent run named-entity recognition, PII extraction, or de-identification over many clinical notes in batches.
Ready to connect★ 5k
- View details
benchmark-pii-recallSkillAI & models
Lets your agent test how well a PII detection model finds sensitive spans and report recall scores.
Ready to connect★ 5k
- View details
benchmarking-clinical-nerSkillAI & models
Lets your agent score a clinical or biomedical NER model on your own labeled data with precision, recall, F1 and per-label error breakdowns.
Ready to connect★ 5k
- View details
bridging-presidio-and-spacySkillDev tools
Lets your agent connect OpenMed clinical text analysis with Presidio, spaCy, or LangChain tools.
Ready to connect★ 5k
- View details
building-gold-corpusSkillAI & models
Lets your agent set up a gold-standard annotation project with label schemas, guidelines, and train/dev/test splits.
Ready to connect★ 5k
- View details
building-patient-timelinesSkillDocs & knowledge
Lets your agent build a chronological patient timeline by ordering clinical events and fixing relative dates.
Ready to connect★ 5k
- View details
building-with-openmedSkillProductivity
Helps your agent set up and choose models in OpenMed for clinical text tasks like de-identification and FHIR export.
Ready to connect★ 5k
- View details
checking-hipaa-complianceSkillCloud & infra
Lets your agent check a healthcare data pipeline against HIPAA rules and report gaps before handling patient data.
Ready to connect★ 5k
- View details
choosing-openmed-modelsSkillSearch
Helps your agent find and pick the right OpenMed model for a clinical, biomedical, or language-specific task.
Ready to connect★ 5k
- View details
coding-hcc-risk-adjustmentSkillDocs & knowledge
Lets your agent map patient diagnoses to CMS-HCC risk categories and estimate a RAF score.
Ready to connect★ 5k
- View details
coding-icd10SkillDev tools
Lets your agent suggest billable ICD-10 diagnosis and procedure codes for diagnoses, with explanation.
Ready to connect★ 5k
- View details
computing-ecqmsSkillDocs & knowledge
Lets your agent compute healthcare quality measures from patient data using clinical quality logic.
Ready to connect★ 5k
- View details
configuring-privacy-policiesSkillDatabases & data
Lets your agent pick and customize privacy policy profiles for de-identifying sensitive text.
Ready to connect★ 5k
- View details
defining-cohort-phenotypesSkillDev tools
Lets your agent write computable patient cohort definitions and phenotypes over OMOP data using OHDSI-style criteria.
Ready to connect★ 5k
- View details
deidentify-a-datasetSkillDatabases & data
Lets your agent remove personal health information from text columns in a CSV, JSONL, or Parquet file and make a redacted copy.
Ready to connect★ 5k
- View details
deidentifying-clinical-textSkillDocs & knowledge
Lets your agent remove or mask patient identifiers like names and dates in medical text.
Ready to connect★ 5k
- View details
deidentifying-multilingual-textSkillDocs & knowledge
Lets your agent remove personal details from medical notes in 11 languages and replace them with fake values.
Ready to connect★ 5k
- View details
deploying-openmed-mcpSkillCloud & infra
Lets your agent run an on-device server that finds medical terms and removes personal info from clinical text.
Ready to connect★ 5k
- View details
detecting-pv-signalsSkillDev tools
Lets your agent scan FDA drug side-effect report data to find unusual drug-reaction patterns that may signal safety issues.
Ready to connect★ 5k
- View details
enforcing-nophi-loggingSkillCloud & infra
Lets your agent add logging guards that scrub patient health information from logs, traces, and error reports.
Ready to connect★ 5k
- View details
etl-to-omop-cdmSkillDatabases & data
Lets your agent map extracted clinical facts into OMOP CDM tables for health research analytics.
Ready to connect★ 5k
- View details
evaluating-with-leakage-gatesSkillAI & models
Lets your agent test a medical de-identification model to check if patient data might leak before release.
Ready to connect★ 5k
- View details
exporting-bulk-fhirSkillDev tools
Lets your agent export bulk FHIR health records and run de-identification and entity extraction on them.
Ready to connect★ 5k
- View details
exporting-to-fhirSkillDev tools
Lets your agent convert medical text analysis results into standard FHIR health data records.
Ready to connect★ 5k
- View details
extract-clinical-entities-to-fhirSkillAI & models
Lets your agent pull clinical entities like conditions and medications out of de-identified text and map them into FHIR R4 resources.
Ready to connect★ 5k
- View details
extracting-clinical-entitiesSkillFiles & storage
Lets your agent find diseases, drugs, genes, and other medical terms in text and return them as or csv.
Ready to connect★ 5k
- View details
extracting-dicom-metadataSkillFiles & storage
Lets your agent read medical imaging file headers to pull study details and report text and flag patient identifiers.
Ready to connect★ 5k
- View details
extracting-lab-tablesSkillFiles & storage
Lets your agent pull lab results like test names, values, and reference ranges out of scanned PDFs or images into structured rows.
Ready to connect★ 5k
- View details
extracting-pii-entitiesSkillDev tools
Lets your agent find personal identifiers like names, dates, and phone numbers in clinical text without changing it.
Ready to connect★ 5k
- View details
extracting-sdohSkillSecurity
Lets your agent find health-related social factors in clinical notes and map them to ICD-10 Z-codes.
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.
54,826 of the 55,257 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.