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
54,680 results · page 145 of 1,823
- View details
pentest-verificationSkillSecurity
Keeps a pentesting agent honest by requiring evidence for every confirmed finding and marking unverified guesses as tentative.
Ready to connect★ 7k
- View details
proxy-tool-bootstrapSkillSecurity
Lets your agent route blocked web requests through rotating SOCKS5, HTTP, or Tor proxies and improvise missing tools in Python.
Ready to connect★ 7k
- View details
redteam-opsecSkillSecurity
Teaches your agent operational-security rules to stay stealthy during authorized red-team testing, like rate-limited scanning and minimal traces.
Ready to connect★ 7k
- View details
source-code-huntingSkillSecurity
Lets your agent hunt for leaked source code, exposed secrets, and supply-chain flaws during security testing.
Ready to connect★ 7k
- View details
specialized-attack-playbooksSkillFiles & storage
Gives your agent step-by-step guides for offensive security testing of CDNs, panels, and storage services.
Ready to connect★ 7k
- View details
unlimited-attack-scopeSkillSecurity
Lets your agent follow a pentest mindset rule that pushes it to keep searching, verifying, chaining, and recording findings without limiting attack scope.
Ready to connect★ 7k
- View details
web-attack-methodsSkillSecurity
Loads a reference playbook of web attack techniques (SQL injection, XSS, SSRF, JWT/OAuth bypasses, CDN/WAF evasion) for penetration testing.
Ready to connect★ 7k
- View details
wireless-hardware-attackSkillSecurity
Guides your agent through WiFi, BLE, RFID, SDR, and hardware interface attacks for penetration testing.
Ready to connect★ 7k
- View details
zero-day-discoverySkillSecurity
Guides your agent to hunt for new software vulnerabilities via patch analysis, fuzzing, and taint tracing.
Ready to connect★ 7k
- View details
pr-visual-writeupSkillDev tools
Lets your agent write GitHub PR descriptions with screenshots from a running dev server posted via gist.
Ready to connect★ 7k
- View details
roidsSkillDev tools
Lets your agent present several UI design options side by side so you can compare and pick a winner.
Ready to connect★ 7k
- View details
post-exploitationSkillCommerce & finance
Guides your agent through post-exploitation tasks like privilege escalation, lateral movement, tunneling, and password cracking.
Ready to connect★ 7k
- View details
Dev BrowserSkillWeb & browsing
Lets your agent control a browser to visit sites, click, fill forms, and take screenshots.
Ready to connect★ 7k
- View details
liger-autopatchSkillAI & models
Lets your agent add Liger Kernel support to a HuggingFace model by generating patching code, tests, and docs.
Ready to connect★ 7k
- View details
liger-kernel-devSkillFiles & storage
Lets your agent write and update Triton kernels for Liger Kernel from PyTorch code or plain descriptions.
Ready to connect★ 7k
- View details
liger-kernel-perfSkillDocs & knowledge
Lets your agent profile and optimize your Liger Kernel Triton GPU kernels for better speed.
Ready to connect★ 7k
- View details
preline-mcpSkillFiles & storage
Lets your agent add Preline UI components and ready-made page sections into HTML files.
Ready to connect★ 6k
- View details
preline-theme-generatorSkillFiles & storage
Lets your agent create, preview, and validate Preline theme CSS files, including matching brand colors or moods.
Ready to connect★ 6k
- View details
acme-researchSkillSearch
Lets your agent search and summarize documents from the Acme research library, citing titles and source URLs.
Ready to connect★ 6k
- View details
agent-first-screenshotsSkillProductivity
Lets your agent drive a real app in a browser and capture clean, defect-free product screenshots for pages, decks, and social posts.
Ready to connect★ 6k
- View details
context7-docs-researchSkillDocs & knowledge
Lets your agent look up official documentation for the exact library version before answering technical questions.
Ready to connect★ 6k
- View details
context7-version-aware-implementationSkillDocs & knowledge
Lets your agent write or upgrade code using the exact installed dependency versions so it pulls the right API docs.
Ready to connect★ 6k
- View details
create-pluginSkillFiles & storage
Lets your agent scaffold a working OpenCode plugin file with tools and hooks for iPolloWork.
Ready to connect★ 6k
- View details
daytona-chrome-cdpSkillWeb & browsing
Lets your agent launch and control a standalone Chrome browser inside a Daytona sandbox for web sign-in and OAuth flows.
Ready to connect★ 6k
- View details
daytona-cloud-serverSkillDev tools
Sets up and runs the hosted server side of iPolloWork in a Daytona cloud sandbox for testing.
Ready to connect★ 6k
- View details
daytona-devSkillDev tools
Guides your agent through running and testing the iPolloWork desktop app inside a Daytona cloud sandbox.
Ready to connect★ 6k
- View details
daytona-electron-denSkillDev tools
Lets your agent test an Electron desktop app against a cloud Den server running in two separate Daytona sandboxes.
Ready to connect★ 6k
- View details
daytona-recording-artifactsSkillMedia
Lets your agent capture screenshots and videos of an app's UI as proof that a tested flow works.
Ready to connect★ 6k
- View details
daytona-windows-certSkillDev tools
Lets your agent test Windows TLS certificate trust fixes in a cloud Windows sandbox.
Ready to connect★ 6k
- View details
deepseek-harnessSkillProductivity
Lets your agent hand code review, development, and research tasks to a DeepSeek assistant and get results back.
Ready to connect★ 6k
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.
54,249 of the 54,680 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.