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 148 of 1,797
- View details
next-ideaSkillFiles & storage
Lets your agent invent product improvement ideas, judge them against a quality bar, and file the winners as GitHub issues.
Ready to connect★ 5k
- View details
next-qaSkillDev tools
Lets your agent run one round of QA work: steward an open test PR, then build one queued test task and open a PR.
Ready to connect★ 5k
- View details
next-qa-ideaSkillFiles & storage
Lets your agent scan a codebase for untested behavior and file one QA issue proposing the test to write.
Ready to connect★ 5k
- View details
next-taskSkillSecurity
Lets your agent run one autonomous coding task: pick a queued issue, build it on a branch, and open a PR.
Ready to connect★ 5k
- View details
pr-review-analysisSkillDev tools
Lets your agent fetch GitHub PR review comments, check each one against the code, and report which are valid.
Ready to connect★ 5k
- View details
pr-to-mainSkillDev tools
Lets your agent open a pull request to main in a pnpm monorepo, including creating the required changeset and picking the right PR template.
Ready to connect★ 5k
- View details
pr-to-main-cleanupSkillDev tools
Lets your agent delete local and remote feature branches after their PR is merged into main.
Ready to connect★ 5k
- View details
workflow-schema-tuningSkillAI & models
Guides your agent to tune the workflow schema file that steers how AI editors generate workflows.
Ready to connect★ 5k
- View details
get-prompt-from-imageSkillMedia
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other
Ready to connect★ 5k
- View details
annotating-variantsSkillDev tools
Lets your agent annotate genetic variants and predict their effects using free tools like Ensembl VEP and gnomAD.
Ready to connect★ 5k
- View details
ask-openmedSkillDev tools
Lets your agent route clinical data tasks like intake, privacy checks, extraction, and verification to the right workflow.
Ready to connect★ 5k
- View details
assembling-fhir-bundlesSkillDev tools
Lets your agent package medical records into a single FHIR bundle ready to send to an EHR system.
Ready to connect★ 5k
- View details
auditing-deid-leakageSkillDatabases & data
Lets your agent scan de-identified clinical text for leftover personal identifiers and report any leaks before sharing.
Ready to connect★ 5k
- View details
auditing-deidentification-runsSkillDev tools
Lets your agent create a signed, tamper-evident audit record of what was redacted in a de-identification run.
Ready to connect★ 5k
- View details
auditing-part11-trailsSkillCloud & infra
Lets your agent create and check tamper-evident audit trails with timestamps and signatures for regulated medical workflows.
Ready to connect★ 5k
- View details
auditing-safe-harbor-checklistSkillDocs & knowledge
Lets your agent check medical notes against the 18 HIPAA Safe Harbor identifier categories to confirm they are de-identified.
Ready to connect★ 5k
- View details
auditing-subgroup-fairnessSkillAI & models
Lets your agent check a medical text model for accuracy gaps across demographic groups like sex, age, and race.
Ready to connect★ 5k
- View details
authoring-model-cardsSkillMonitoring & ops
Lets your agent write a model card for a clinical NER model covering intended use, metrics, limitations, and disclaimers.
Ready to connect★ 5k
- View details
batch-processing-clinical-textSkillDatabases & data
Lets your agent batch-process many clinical notes for entity extraction, PII removal, or de-identification on-device.
Ready to connect★ 5k
- View details
benchmark-pii-recallSkillAI & models
Lets your agent test how well a privacy model finds personal details in text and report the results.
Ready to connect★ 5k
- View details
benchmarking-clinical-nerSkillAI & models
Lets your agent score a biomedical NER model against your gold data and get precision, recall, and F1 per label.
Ready to connect★ 5k
- View details
bridging-presidio-and-spacySkillDev tools
Lets your agent connect clinical text analysis tools with Presidio, spaCy, or LangChain pipelines.
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 for evaluating medical NLP models.
Ready to connect★ 5k
- View details
building-patient-timelinesSkillDocs & knowledge
Lets your agent build a chronological patient timeline by ordering clinical events and normalizing dates from medical notes.
Ready to connect★ 5k
- View details
building-with-openmedSkillProductivity
Guides your agent through setting up and using OpenMed for clinical text tasks like entity recognition and de-identification.
Ready to connect★ 5k
- View details
checking-hipaa-complianceSkillCloud & infra
Checks a data pipeline against a HIPAA compliance checklist and reports gaps before handling health 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
Maps patient diagnoses to CMS-HCC risk categories and estimates a RAF score from clinical notes.
Ready to connect★ 5k
- View details
coding-icd10SkillDev tools
Lets your agent suggest ICD-10-CM diagnosis and procedure codes for medical conditions with explanations.
Ready to connect★ 5k
- View details
computing-ecqmsSkillDocs & knowledge
Lets your agent compute healthcare quality measures (eCQMs) from patient records to check clinical performance.
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.