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
55,055 results · page 702 of 1,836
- View details
radiomics-mlSkillDev tools
Lets your agent build or check radiomics and clinical ML studies using classical models on imaging or tabular data.
Ready to connect★ 310
- View details
random-stimulusSkillMedia
Lets your agent spark new ideas by forcing random unrelated concepts onto a problem you're brainstorming.
Ready to connect★ 311
- View details
render-pdf-docSkillDocs & knowledge
Lets your agent turn academic Markdown documents into polished PDF files with tables and formatting.
Ready to connect★ 310
- View details
replicate-studySkillDatabases & data
Lets your agent rerun an existing cohort study's methods on a different database and report differences.
Ready to connect★ 310
- View details
reviseSkillDocs & knowledge
Lets your agent turn peer reviewer comments into a structured Response to Reviewers with tracked manuscript changes.
Ready to connect★ 310
- View details
scamperSkillDev tools
Lets your agent take one existing idea and generate structured variations using seven creative-thinking prompts.
Ready to connect★ 311
- View details
search-litSkillSearch
Lets your agent search PubMed, Semantic Scholar, and bioRxiv for verified medical citations and generate BibTeX entries.
Ready to connect★ 310
- View details
self-reviewSkillDev tools
Lets your agent review your manuscript draft before submission and list likely reviewer comments by severity.
Ready to connect★ 310
- View details
setup-medsciSkillAI & models
Checks whether scientific and coding tools like Python, R, Git, and Zotero are installed and reports what is missing.
Ready to connect★ 310
- View details
six-hatsSkillDev tools
Guides your agent to think through a decision from six separate angles like facts, risks, and benefits one at a time.
Ready to connect★ 311
- View details
sync-submissionSkillDev tools
Lets your agent check a manuscript matches its source-of-truth files and build journal submission manifests.
Ready to connect★ 310
- View details
uncertainty-imagingSkillCloud & infra
Helps design and audit uncertainty scoring and OOD detection for a medical-imaging model.
Ready to connect★ 310
- View details
verify-refsSkillDev tools
Lets your agent check manuscript citations against PubMed and CrossRef to catch fabricated or mismatched references.
Ready to connect★ 310
- View details
version-datasetSkillDatabases & data
Lets your agent snapshot a dataset's contents and later check if any files, rows, or values have changed.
Ready to connect★ 310
- View details
worst-ideaSkillMedia
Lets your agent brainstorm deliberately bad solutions to a problem, then flip the flaws into strong features.
Ready to connect★ 311
- View details
write-paperSkillDocs & knowledge
Guides your agent through writing a medical or scientific paper step by step, from outline to a submission-ready manuscript.
Ready to connect★ 310
- View details
write-protocolSkillSearch
Lets your agent draft a research protocol with background, study design, sample size, and statistical plan sections.
Ready to connect★ 310
- View details
add-commandSkillProductivity
Lets your agent add new commands and subcommands to the Todoist CLI tool.
Ready to connect★ 310
- View details
compliance_checkSkillDev tools
Lets your agent run compliance checks on documents.
Ready to connect★ 309
- View details
content_genSkillDev tools
Lets your agent generate body text in four different modes.
Ready to connect★ 309
- View details
core-data-expertSkillAI & models
Gives your agent expert guidance on building and debugging Core Data apps on iOS and macOS, from setup to CloudKit sync.
Ready to connect★ 310
- View details
docx_formatSkillDocs & knowledge
Lets your agent format and lay out Word documents automatically.
Ready to connect★ 309
- View details
tender_interpretSkillDocs & knowledge
Lets your agent analyze tender documents across 15 dimensions like requirements, deadlines, and qualification criteria.
Ready to connect★ 309
- View details
todoist-cliSkillProductivity
Lets your agent view, create, complete, and organize your Todoist tasks, projects, labels, and reminders.
Ready to connect★ 310
- View details
account-based-blueprintSkillAI & models
Lets your agent organize account intelligence and buying signals for manufacturing sales targets.
Ready to connect★ 289
- View details
account-health-frameworkSkillAI & models
Lets your agent score customer accounts, flag risks, and trigger standard remediation steps.
Ready to connect★ 289
- View details
account-tieringSkillAI & models
Lets your agent define account tiers, scoring rules, and coverage rules for account-based marketing.
Ready to connect★ 289
- View details
activation-mapSkillAI & models
Lets your agent link customer segments and insights to go-to-market plays, owners, and measurement.
Ready to connect★ 289
- View details
ad-lead-quality-analyzerSkillAI & models
Lets your agent measure real cost per qualified lead from ad campaigns by joining ad data with your own funnel data.
Ready to connect★ 289
- View details
ad-to-landing-page-auditorSkillCommunication
Lets your agent check whether your ad copy matches your landing page and flag mismatches.
Ready to connect★ 289
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.
54,624 of the 55,055 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.