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 700 of 1,836
- View details
wp-playgroundSkillCloud & infra
Lets your agent spin up a disposable local WordPress site with a plugin for quick testing, no Docker needed.
Ready to connect★ 317
- View details
build-agentSkillAI & models
Lets your agent create new Claude Code agents with a consistent structure and project-specific settings.
Ready to connect★ 313
- View details
build-skillSkillAI & models
Lets your agent create new well-structured Claude Code skills for automating workflows or commands.
Ready to connect★ 313
- View details
core-brainstormSkillAI & models
Lets your agent brainstorm ideas and think through problems with you before planning any work.
Ready to connect★ 313
- View details
codemodSkillAI & models
Lets your agent write and run TypeScript codemods to rename symbols, rewrite call signatures, and migrate code across your codebase.
Ready to connect★ 312
- View details
diataxis-docsSkillDocs & knowledge
Lets your agent plan, write, audit, and organize technical documentation using the Diátaxis framework.
Ready to connect★ 312
- View details
engine-call-contractSkillDev tools
Teaches your agent the calling rules for a text engine so it can safely add or change engine entry points and errors.
Ready to connect★ 312
- View details
evidence-firstSkillDocs & knowledge
Guides your agent to write reports, PRs, and docs with clear claims, evidence, and stated gaps.
Ready to connect★ 312
- View details
maintainability-reviewSkillMedia
Lets your agent review and improve your code for clarity, correctness, and easier long-term maintenance.
Ready to connect★ 312
- View details
open-knowledge-formatSkillDocs & knowledge
Lets your agent create, check, and maintain Open Knowledge Format knowledge bundles of linked Markdown files.
Ready to connect★ 312
- View details
tslSkillFiles & storage
Helps your agent write, debug, and convert Three.js shading language code for WebGPU graphics work.
Ready to connect★ 312
- View details
typegpuSkillMedia
Helps your agent write and debug TypeGPU WebGPU code in TypeScript, like shaders, buffers, and render pipelines.
Ready to connect★ 312
- View details
academic-aioSkillSearch
Helps your agent write and review medical research papers so AI search engines find and cite them better.
Ready to connect★ 310
- View details
add-journalSkillDatabases & data
Lets your agent add a new journal to the MedSci profile database with generated write-paper and find-journal profiles.
Ready to connect★ 310
- View details
analogySkillDev tools
Helps your agent solve a problem by borrowing structures and mechanisms from an unrelated domain as an analogy.
Ready to connect★ 311
- View details
analyze-statsSkillDev tools
Lets your agent run statistical analyses for medical research papers and generate reproducible Python or R code with tables and figures.
Ready to connect★ 310
- View details
architecture-zooSkillProductivity
Lets your agent pick suitable model architectures for a medical-imaging research question based on task, data size, and imbalance.
Ready to connect★ 310
- View details
author-strategySkillDev tools
Lets your agent analyze a researcher's PubMed publication record and produce a career strategy report.
Ready to connect★ 310
- View details
batch-cohortSkillDev tools
Lets your agent generate many analysis scripts at once by applying one validated template to multiple exposure/outcome variable pairs.
Ready to connect★ 310
- View details
calc-sample-sizeSkillDev tools
Lets your agent calculate the sample size needed for a medical study and generate reproducible code plus justification text.
Ready to connect★ 310
- View details
check-reportingSkillDev tools
Lets your agent check a medical research manuscript against 49 reporting guidelines like STROBE and CONSORT.
Ready to connect★ 310
- View details
clean-dataSkillFiles & storage
Lets your agent profile and clean medical CSV or Excel data, flagging issues and generating cleaning code you approve.
Ready to connect★ 310
- View details
concept-fanSkillDev tools
Lets your agent step back from a chosen solution, find the broader concept behind it, and generate alternative approaches.
Ready to connect★ 311
- View details
contributeSkillDev tools
Lets your agent submit your local changes to a project as a pull request or issue without git commands.
Ready to connect★ 310
- View details
cross-nationalSkillDev tools
Lets your agent run cross-national health survey comparisons with variable harmonization, weighted analysis, and comparison tables.
Ready to connect★ 310
- View details
define-variablesSkillDev tools
Turns your data dictionary and research question into a citation-backed table of variable definitions and cutoffs.
Ready to connect★ 310
- View details
deidentifySkillAI & models
Lets your agent remove personal information from clinical research data before analysis.
Ready to connect★ 310
- View details
design-ai-benchmarkingSkillMedia
Helps your agent design valid studies that compare AI systems against a panel of human experts.
Ready to connect★ 310
- View details
design-studySkillMedia
Lets your agent review radiology and medical AI research for study design flaws, data leakage, and validation gaps.
Ready to connect★ 310
- View details
explainabilitySkillAI & models
Lets your agent run and audit explainability analyses like Grad-CAM and saliency maps for medical imaging models.
Ready to connect★ 310
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.