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
54,018 results · page 166 of 1,801
- 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 health-related social factors in clinical notes and map them to ICD-10 Z-codes.
Ready to connect★ 5k
- View details
fetching-fhir-resourcesSkillDev tools
Lets your agent fetch patient records like lab results and clinical notes from an EHR's FHIR API.
Ready to connect★ 5k
- View details
gating-deid-leakageSkillAI & models
Lets your agent add a build check that fails when a de-identification model misses private health data or leaks identifiers.
Ready to connect★ 5k
- View details
generating-synthea-dataSkillFiles & storage
Lets your agent generate realistic fake patient health records for testing without using any real patient data.
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 extract clean text from scanned faxes, images, and CSV or CDA clinical documents via on-device OCR.
Ready to connect★ 5k
- View details
linking-umls-conceptsSkillDev tools
Lets your agent match medical terms to standard UMLS concept IDs using your own UMLS API key.
Ready to connect★ 5k
- View details
loading-openmed-modelsSkillAI & models
Lets your agent load biomedical language models once and reuse them across text-analysis tasks.
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 standard 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 abstracts and citations for biomedical topics.
Ready to connect★ 5k
- View details
normalizing-rxnormSkillDev tools
Lets your agent convert medication names into standard RxNorm codes and link brands, doses, and NDCs.
Ready to connect★ 5k
- View details
parsing-ccda-documentsSkillDocs & knowledge
Lets your agent extract readable sections and coded entries from C-CDA clinical XML documents.
Ready to connect★ 5k
- View details
parsing-hl7v2-messagesSkillCommunication
Lets your agent decode pipe-delimited HL7 v2.x healthcare messages into structured segments, fields, and narrative text.
Ready to connect★ 5k
- View details
parsing-lab-valuesSkillDev tools
Lets your agent read lab values from clinical text and flag each result as low, normal, high, or critical.
Ready to connect★ 5k
- View details
parsing-trial-eligibilitySkillDev tools
Lets your agent turn clinical-trial eligibility text into structured rules and match patients against them.
Ready to connect★ 5k
- View details
pick-a-pii-modelSkillCloud & infra
Helps your agent pick the right on-device PII detection model by language, format, and size before deploying it.
Ready to connect★ 5k
- View details
pseudonymizing-for-gdprSkillDev tools
Lets your agent replace personal details in text with codes so the data can be safely re-linked later.
Ready to connect★ 5k
- View details
querying-openfda-labelsSkillSearch
Lets your agent look up FDA drug labels, indications, boxed warnings, and recalls from the public OpenFDA database.
Ready to connect★ 5k
- View details
querying-terminology-serviceSkillDev tools
Lets your agent validate and expand clinical codes like SNOMED CT and ICD-10 against a FHIR terminology server.
Ready to connect★ 5k
- View details
reconciling-problem-listsSkillDev tools
Lets your agent merge duplicate medical diagnoses from clinical notes into one clean problem list with active or resolved status.
Ready to connect★ 5k
- View details
reidentifying-textSkillDev tools
Lets your agent mask personal health details in clinical text and restore them later from a saved mapping.
Ready to connect★ 5k
- View details
reporting-adverse-eventsSkillDev tools
Lets your agent turn drug side-effect mentions into standardized safety report fields like suspect drug, reaction, and outcome.
Ready to connect★ 5k
- View details
resolving-clinical-contextSkillDev tools
Lets your agent label medical findings as negated, historical, or uncertain so mentions like 'denies chest pain' aren't misread.
Ready to connect★ 5k
- View details
reviewing-reidentification-riskSkillDatabases & data
Lets your agent score a de-identified dataset for re-identification risk and write up the residual risk findings.
Ready to connect★ 5k
- View details
running-openmed-ondeviceSkillWeb & browsing
Lets your agent run OpenMed medical text models fully on-device on Apple Silicon, iOS, or in the browser.
Ready to connect★ 5k
- View details
running-zeroshot-nerSkillDev tools
Lets your agent find custom things like drugs or symptoms in medical text by just naming the labels you want.
Ready to connect★ 5k
- View details
scaffolding-smart-on-fhirSkillDev tools
Lets your agent generate starter code for a healthcare app that launches inside Epic or Cerner EHRs.
Ready to connect★ 5k
- View details
searching-clinicaltrialsSkillDev tools
Lets your agent search ClinicalTrials.gov for studies by condition, drug, and recruitment status.
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.
53,586 of the 54,018 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.