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 176 of 1,801
- View details
code-to-diagramSkillFiles & storage
Lets your agent analyze a codebase and generate architecture diagrams and flowcharts as Mermaid or SVG files.
Ready to connect★ 5k
- View details
code-vuln-auditSkillDatabases & data
Lets your agent scan code for security issues like vulnerable dependencies, leaked secrets, and common injection flaws.
Ready to connect★ 5k
- View details
cv-tailorSkillAI & models
Lets your agent tailor a resume to a job description by matching keywords and rewriting experience bullet points.
Ready to connect★ 5k
- View details
data-viz-rendererSkillAI & models
Lets your agent turn JSON data into self-contained HTML/SVG infographics like charts and dashboards.
Ready to connect★ 5k
- View details
database-scoutSkillDatabases & data
Lets your agent explore SQLite and PostgreSQL databases, inspect table structures, preview data, and run read-only queries.
Ready to connect★ 5k
- View details
dataset-quality-auditSkillDatabases & data
Lets your agent check spreadsheet or data files for missing values, duplicates, outliers, and format problems.
Ready to connect★ 5k
- View details
deep-module-refactorSkillAI & models
Lets your agent explore a codebase to find refactoring changes that improve architecture and testability.
Ready to connect★ 5k
- View details
design-system-builderSkillMedia
Lets your agent turn UI screenshots into design systems and prompts for building matching interfaces.
Ready to connect★ 5k
- View details
dev-guide-generatorSkillAI & models
Lets your agent write complete technical tutorials with setup steps, troubleshooting, and a cheatsheet.
Ready to connect★ 5k
- View details
ethical-hacking-methodologySkillSecurity
Teaches your agent the ethical hacking and penetration testing lifecycle, from reconnaissance to reporting.
Ready to connect★ 5k
- View details
file-path-traversalSkillFiles & storage
Lets your agent test web applications for path traversal flaws that let attackers read files outside the web root.
Ready to connect★ 5k
- View details
html-injection-testingSkillWeb & browsing
Lets your agent test web pages for HTML injection vulnerabilities by injecting content.
Ready to connect★ 5k
- View details
http-load-profilerSkillAI & models
Lets your agent run stepped HTTP load tests on a URL and report latency percentiles and a recommended concurrency level.
Ready to connect★ 5k
- View details
idor-testingSkillSecurity
Guides your agent through testing web apps for IDOR flaws that let one user access another user's data.
Ready to connect★ 5k
- View details
linux-shell-scriptingSkillFiles & storage
Lets your agent write bash scripts for Linux tasks like automation, backups, monitoring, and user management.
Ready to connect★ 5k
- View details
localization-toolkitSkillAI & models
Lets your agent set up and audit internationalization in UI codebases, replacing hard-coded strings with translations.
Ready to connect★ 5k
- View details
log-error-digestSkillFiles & storage
Lets your agent analyze log files to cluster errors, count frequency, and find peak error periods.
Ready to connect★ 5k
- View details
metasploit-frameworkSkillSecurity
Lets your agent run penetration testing tasks like exploiting vulnerabilities, creating payloads, and scanning with Metasploit.
Ready to connect★ 5k
- View details
network-101SkillAI & models
Gives your agent step-by-step guidance for setting up and testing web, HTTP, SNMP, and SMB network services in labs.
Ready to connect★ 5k
- View details
pentest-checklistSkillSecurity
Lets your agent plan penetration tests and build structured security assessment checklists.
Ready to connect★ 5k
- View details
pentest-commandsSkillSecurity
Lets your agent run penetration testing commands like nmap scans, Metasploit exploits, and password cracking with hydra or john.
Ready to connect★ 5k
- View details
pipeline-blueprintSkillAI & models
Gives your agent CI/CD pipeline templates and best practices for GitHub Actions and GitLab CI based on project type.
Ready to connect★ 5k
- View details
playwright-ciSkillWeb & browsing
Gives your agent ready-made CI/CD setup files for running Playwright browser tests on platforms like GitHub Actions and Jenkins.
Ready to connect★ 5k
- View details
playwright-coreSkillWeb & browsing
Gives your agent Playwright testing patterns for end-to-end, API, component, visual, accessibility, and security tests.
Ready to connect★ 5k
- View details
playwright-migrationSkillWeb & browsing
Gives your agent step-by-step guides to migrate test code from Cypress or Selenium to Playwright.
Ready to connect★ 5k
- View details
playwright-pomSkillWeb & browsing
Teaches your agent how to structure browser test code using page object patterns in Playwright.
Ready to connect★ 5k
- View details
playwright-skillSkillWeb & browsing
Gives your agent proven Playwright testing patterns for end-to-end, API, component, visual, and accessibility tests.
Ready to connect★ 5k
- View details
privilege-escalation-methodsSkillAI & models
Explains Linux and Windows privilege escalation techniques like sudo abuse, SUID exploits, and Kerberoasting.
Ready to connect★ 5k
- View details
project-sizing-guideSkillAI & models
Lets your agent estimate software project effort using ranges, T-shirt sizes, or function point counts.
Ready to connect★ 5k
- View details
r2-uploadSkillFiles & storage
Lets your agent upload files to cloud storage like S3 or R2 and create expiring shareable links.
Ready to connect★ 5k
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.