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
54,017 results · page 177 of 1,801
- View details
r3f-animationSkillAI & models
Helps your agent animate 3D scenes with frame loops, GLTF animations, springs, and keyframes.
Ready to connect★ 5k
- View details
r3f-best-practicesSkillProductivity
Gives your agent best-practice guidance when writing or reviewing React Three Fiber 3D code.
Ready to connect★ 5k
- View details
red-team-toolsSkillSecurity
Lets your agent run security testing tasks like finding subdomains and hunting XSS bugs using red team methods.
Ready to connect★ 5k
- View details
regression-modelerSkillFiles & storage
Lets your agent run regression analysis (OLS or logistic) on your CSV or Excel data with coefficients and interpretations.
Ready to connect★ 5k
- View details
regulatory-audit-generatorSkillAI & models
Lets your agent generate compliance checklists for GDPR, PIPL, and advertising laws with legal basis and recommendations.
Ready to connect★ 5k
- View details
repo-auditSkillFiles & storage
Lets your agent analyze Git history to find hotspot files, code ownership, and leaked secrets in commits.
Ready to connect★ 5k
- View details
route-to-openapiSkillDocs & knowledge
Lets your agent generate OpenAPI/Swagger API docs by scanning route definitions in your code.
Ready to connect★ 5k
- View details
scanning-toolsSkillSecurity
Lets your agent run security scans for open ports, web app weaknesses, malware, and compliance issues.
Ready to connect★ 5k
- View details
scholarly-writing-refinerSkillAI & models
Lets your agent polish academic paragraphs for grammar, word choice, and structure with revision suggestions.
Ready to connect★ 5k
- View details
secure-code-reviewSkillDatabases & data
Lets your agent review code for common security vulnerabilities and suggest fixes.
Ready to connect★ 5k
- View details
shodan-reconnaissanceSkillSearch
Lets your agent search Shodan for exposed internet devices, open ports, and services on IP ranges.
Ready to connect★ 5k
- View details
smtp-penetration-testingSkillCommunication
Lets your agent test email server security, like enumerating users, checking open relays, and grabbing SMTP banners.
Ready to connect★ 5k
- View details
sql-injection-testingSkillDatabases & data
Lets your agent test web apps for SQL injection flaws and demonstrate how they could be exploited.
Ready to connect★ 5k
- View details
sql-insightSkillDatabases & data
Helps your agent turn questions into SQL queries, speed up slow ones, and explain query plans.
Ready to connect★ 5k
- View details
sqlmap-database-pentestingSkillDatabases & data
Lets your agent test databases for SQL injection flaws and enumerate their structure and contents.
Ready to connect★ 5k
- View details
test-driven-devSkillAI & models
Guides your agent to build features and fix bugs by writing tests first, then code to pass them.
Ready to connect★ 5k
- View details
test-suite-architectSkillMonitoring & ops
Lets your agent build QA test strategies, write test cases, run test plans, and track bugs by severity.
Ready to connect★ 5k
- View details
three-best-practicesSkillMedia
Lets your agent follow Three.js performance best practices when writing or reviewing 3D WebGL code.
Ready to connect★ 5k
- View details
timeline-builderSkillAI & models
Lets your agent build an interactive HTML timeline page from JSON data with different layouts and custom colors.
Ready to connect★ 5k
- View details
top-web-vulnerabilitiesSkillSecurity
Lets your agent explain common web application vulnerabilities and security flaws like injection and access control weaknesses.
Ready to connect★ 5k
- View details
tos-clause-scannerSkillAI & models
Lets your agent review terms of service and privacy policies and flag unfair or risky clauses.
Ready to connect★ 5k
- View details
vc-industry-researchSkillDocs & knowledge
Lets your agent create industry research reports, investment memos, and market analysis as PDFs.
Ready to connect★ 5k
- View details
windows-privilege-escalationSkillAI & models
Guides an agent to find and use Windows privilege escalation vectors like misconfigurations.
Ready to connect★ 5k
- View details
wireshark-analysisSkillFiles & storage
Lets your agent analyze network packet captures, filter PCAP files, and investigate suspicious traffic.
Ready to connect★ 5k
- View details
wordpress-penetration-testingSkillSecurity
Lets your agent scan WordPress sites for security weaknesses, enumerate users and plugins, and run WPScan tests.
Ready to connect★ 5k
- View details
hami_vgpu_metrics_summarizerSkillDocs & knowledge
Lets your agent summarize GPU usage reports from HAMi metrics, organized by node, device, pod, and namespace.
Ready to connect★ 5k
- View details
k8s-debug-pending-podSkillMedia
Lets your agent diagnose why Kubernetes pods are stuck in Pending, CrashLoopBackOff, or ImagePullBackOff states.
Ready to connect★ 5k
- View details
apk-redteam-pipelineSkillAI & models
Lets your agent download and analyze Android apps to find exposed secrets, API endpoints, and security weaknesses.
Ready to connect★ 4k
- View details
bug-bountySkillSecurity
Lets your agent run bug bounty reconnaissance, learning, and vulnerability hunting workflows like subdomain discovery and XSS testing.
Ready to connect★ 4k
- View details
bugcrowd-reportingSkillSearch
Lets your agent write better bug bounty reports with Bugcrowd severity tactics, VRT category fallbacks, and rebuttal templates.
Ready to connect★ 4k
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.
53,585 of the 54,017 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.