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 738 of 1,836
- View details
ux-design-systemsSkillMedia
Lets your agent build consistent design systems with tokens, components, theming, and dark mode.
Ready to connect★ 279
- View details
video-to-landing-pageSkillWeb & browsing
Lets your agent turn a video file into a scroll-driven landing page where scrolling plays through the video.
Ready to connect★ 279
- View details
web-accessibilitySkillAI & models
Lets your agent build web apps that follow accessibility rules like WCAG, ARIA, and keyboard navigation.
Ready to connect★ 279
- View details
yuv-decksSkillDocs & knowledge
Lets your agent create a full narrative presentation deck from a topic and audience description.
Ready to connect★ 279
- View details
yuv-design-systemSkillDocs & knowledge
Lets your agent style presentations, decks, bios, and sites using the YUV.AI brand design guidelines.
Ready to connect★ 279
- View details
yuv-pilotSkillAI & models
Lets your agent plan and coordinate YUV.AI brand content across unclear or multi-channel requests.
Ready to connect★ 279
- View details
yuv-reel-coversSkillAI & models
Lets your agent generate branded Instagram Reel covers with a layered Hebrew headline depth effect.
Ready to connect★ 279
- View details
yuv-video-directorSkillMedia
Lets your agent turn an idea or script into a finished MP4 video with animations and captions.
Ready to connect★ 279
- View details
yuv-viral-videoSkillMedia
Lets your agent edit a selfie or screen-share clip into a polished short-form video with captions and motion graphics.
Ready to connect★ 279
- View details
basecampSkillFiles & storage
Lets your agent manage Basecamp projects, todos, messages, files, and schedules using the Basecamp CLI.
Ready to connect★ 278
- View details
basecamp-connectSkillAI & models
Lets your agent set up and manage the local Basecamp connector that hands Basecamp work to a coding agent on this computer.
Ready to connect★ 278
- View details
basecamp-doctorSkillSecurity
Lets your agent diagnose Basecamp CLI setup, authentication, and agent-plugin health issues.
Ready to connect★ 278
- View details
super-video-makerSkillMedia
Lets your agent create, edit, caption, and export videos using AI avatars, b-roll, soundtracks, and screen recordings.
Ready to connect★ 278
- View details
algo-senseiSkillDev tools
Lets your agent explain algorithms, give hints, review code, analyze complexity, and run mock interviews.
Ready to connect★ 277
- View details
bashkitSkillAI & models
Lets your agent run Bashkit scripts, use its CLI, and find Bashkit docs, examples, and packages.
Ready to connect★ 277
- View details
code-transformSkillAI & models
Lets your agent repair, simplify, and extract Lean proofs using code transformation tools.
Ready to connect★ 277
- View details
numina-lean-agentSkillSearch
Lets your agent write and check mathematical proofs in the Lean 4 language and fix proof errors.
Ready to connect★ 277
- View details
ppt-design-skillSkillDocs & knowledge
Lets your agent design, generate, and revise editable PowerPoint presentations from a written brief.
Ready to connect★ 277
- View details
process-issuesSkillDev tools
Lets your agent resolve every open GitHub issue by making one pull request for each.
Ready to connect★ 277
- View details
sorrifierSkillAI & models
Lets your agent split a failing Lean 4 proof by replacing broken steps with sorry placeholders and extracting them into separate lemmas.
Ready to connect★ 277
- View details
<skill-name>SkillSecurity
Lets your agent run security testing techniques from the Red Run catalog for red team practice.
Ready to connect★ 276
- View details
2fa-bypassSkillSecurity
Lets your agent attempt two-factor authentication bypasses during authorized penetration tests.
Ready to connect★ 276
- View details
acl-abuseSkillSecurity
Lets your agent exploit misconfigured Active Directory permissions to escalate privileges during security testing.
Ready to connect★ 276
- View details
ad-discoverySkillSecurity
Lets your agent list Active Directory domains and map their attack surface for penetration testing.
Ready to connect★ 276
- View details
ad-persistenceSkillMonitoring & ops
Teaches your agent how attackers keep access to a compromised Windows domain, for red team detection testing.
Ready to connect★ 276
- View details
adcs-access-and-relaySkillSecurity
Lets your agent abuse Active Directory Certificate Services through ACL misconfigurations and NTLM relay attacks.
Ready to connect★ 276
- View details
adcs-persistenceSkillSecurity
Lets your agent learn techniques for persisting access and exploiting weak certificate mappings in Active Directory certificate services.
Ready to connect★ 276
- View details
adcs-template-abuseSkillSecurity
Lets your agent test whether misconfigured Windows certificate templates let attackers impersonate domain users.
Ready to connect★ 276
- View details
ajp-ghostcatSkillFiles & storage
Lets your agent test Apache Tomcat servers for the Ghostcat AJP flaw that can expose files or run code.
Ready to connect★ 276
- View details
auth-coercion-relaySkillSecurity
Lets your agent run security tests that force servers to send their authentication to a listener you control.
Ready to connect★ 276
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.