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 150 of 1,797
- View details
parsing-hl7v2-messagesSkillCommunication
Lets your agent decode pipe-delimited HL7 v2 healthcare messages into structured fields and extract narrative text.
Ready to connect★ 5k
- View details
parsing-lab-valuesSkillDev tools
Lets your agent parse 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 them against patient data.
Ready to connect★ 5k
- View details
pick-a-pii-modelSkillCloud & infra
Lets your agent pick the right local PII detection model by language, device, and size, with recall checks before use.
Ready to connect★ 5k
- View details
pseudonymizing-for-gdprSkillDev tools
Lets your agent replace personal and health details in text with pseudonyms under GDPR rules.
Ready to connect★ 5k
- View details
querying-openfda-labelsSkillSearch
Lets your agent look up FDA drug labels, warnings, indications, and recalls for a medication.
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 into one clean problem list with active, resolved, or historical 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 extracted drug side-effect mentions into structured 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 phrases like "denies chest pain" aren't misread.
Ready to connect★ 5k
- View details
reviewing-reidentification-riskSkillDatabases & data
Lets your agent score how likely a de-identified dataset is to be re-identified and write up the risk findings.
Ready to connect★ 5k
- View details
running-openmed-ondeviceSkillWeb & browsing
Lets your agent run OpenMed medical text models locally on your device, including converting, quantizing, and running them.
Ready to connect★ 5k
- View details
running-zeroshot-nerSkillDev tools
Lets your agent pull custom entity types like drugs or symptoms out of medical text without training data.
Ready to connect★ 5k
- View details
scaffolding-smart-on-fhirSkillDev tools
Generates starter code for a healthcare app that launches inside EHR systems like Epic using SMART on FHIR.
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
- View details
segmenting-clinical-sectionsSkillDocs & knowledge
Lets your agent split a clinical note into standard sections like medications and allergies before analysis.
Ready to connect★ 5k
- View details
serving-openmed-rest-apiSkillCloud & infra
Lets your agent run a web API for medical text analysis, finding health terms and removing patient-identifying info.
Ready to connect★ 5k
- View details
setup-openmedSkillAI & models
Lets your agent gather privacy de-identification policy choices and write a reviewable DEID-POLICY.md file.
Ready to connect★ 5k
- View details
shifting-clinical-datesSkillDev tools
Lets your agent shift patient dates by a consistent offset to de-identify records while keeping time intervals intact.
Ready to connect★ 5k
- View details
structuring-radiology-reportsSkillDev tools
Lets your agent turn free-text radiology reports into structured findings with measurements and follow-up recommendations.
Ready to connect★ 5k
- View details
summarizing-clinical-notesSkillDocs & knowledge
Lets your agent turn clinical notes into structured summaries like discharge drafts, handoffs, and problem lists with cited sources.
Ready to connect★ 5k
- View details
validating-us-coreSkillDev tools
Lets your agent check FHIR health data resources against US Core profiles before sending them to an EHR.
Ready to connect★ 5k
- View details
conventions-checkSkillCloud & infra
Lets your agent check a pull request's title, description, and scope against the repo's PR conventions and flag violations.
Ready to connect★ 5k
- View details
dependabot-reviewSkillCloud & infra
Lets your agent review a Dependabot pull request and report whether a package version bump affects the repo.
Ready to connect★ 5k
- View details
pr-mrSkillDocs & knowledge
Creates and updates pull requests and merge requests for cloudflare-docs changes. Covers title conventions, branch naming, request body structure, and documentation checklist templates. Load when asked to open, create, submit, update, or edit a PR or MR, or write a PR or MR title or description.
Ready to connect★ 5k
- View details
rebase-conflictSkillCloud & infra
Lets your agent resolve merge conflicts between a pull request and the latest changes in the cloudflare-docs repository.
Ready to connect★ 5k
- View details
reconcile-code-reviewSkillCloud & infra
Lets your agent sort code review findings into active, fixed, or reviewer-dismissed by checking past reviews and PR comments.
Ready to connect★ 5k
- View details
review-validationSkillFiles & storage
Lets your agent double-check code review findings by reading repo files and marking each as valid or a false positive.
Ready to connect★ 5k
- View details
spam-and-off-topic-filterSkillCloud & infra
Lets your agent review GitHub issues and pull requests and flag obvious spam or off-topic submissions.
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.