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 150 of 1,823
- View details
offensive-network-attacksSkillAI & models
Lets your agent run network attack techniques like ARP spoofing and DNS poisoning for penetration testing.
Ready to connect★ 6k
- View details
offensive-oauthSkillFiles & storage
Gives your agent a library of offensive security playbooks covering attacks like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-open-redirectSkillFiles & storage
Gives your agent expert offensive security methods for attacks like SQL injection, shellcode, and evasion.
Ready to connect★ 6k
- View details
offensive-osintSkillCommunication
Lets your agent gather open-source intelligence on targets, from domain recon and email harvesting to breach and code leak lookups.
Ready to connect★ 6k
- View details
offensive-osint-methodologySkillFiles & storage
Gives your agent a library of expert offensive security playbooks covering attacks from SQL injection to exploit development.
Ready to connect★ 6k
- View details
offensive-parameter-pollutionSkillFiles & storage
Loads expert offensive security playbooks so your agent can run attack techniques like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-persistenceSkillSearch
Lets your agent learn Windows and Linux persistence techniques for authorized red team testing.
Ready to connect★ 6k
- View details
offensive-phishingSkillSecurity
Guides your agent through running authorized phishing test campaigns, from setting up email infrastructure to delivering payloads.
Ready to connect★ 6k
- View details
offensive-race-conditionSkillFiles & storage
Gives your agent a library of guided offensive security methods for attacks like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-reportingSkillAI & models
Guides your agent through writing penetration test and red team reports, from executive summaries to scored technical findings.
Ready to connect★ 6k
- View details
offensive-request-smugglingSkillFiles & storage
Gives your agent expert guidance for offensive security tasks like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-shellcodeSkillFiles & storage
Gives your agent a reference for writing custom x86/x64 shellcode, loaders, and evasion techniques for offensive security work.
Ready to connect★ 6k
- View details
offensive-social-engineeringSkillCommunication
Teaches your agent social engineering attack methods like pretexting and vishing for authorized penetration testing.
Ready to connect★ 6k
- View details
offensive-sqliSkillDatabases & data
Lets your agent test web apps for SQL injection vulnerabilities during security assessments.
Ready to connect★ 6k
- View details
offensive-sstiSkillAI & models
Lets your agent find and test template injection flaws in web apps across many template engines.
Ready to connect★ 6k
- View details
offensive-supply-chainSkillAI & models
Gives your agent reference material on software supply chain attack methods like dependency confusion.
Ready to connect★ 6k
- View details
offensive-tls-attacksSkillSecurity
Lets your agent audit and exploit TLS/SSL misconfigurations like protocol downgrade attacks in services and apps.
Ready to connect★ 6k
- View details
offensive-toctouSkillFiles & storage
Teaches your agent how time-of-check/time-of-use race condition attacks work across binaries, kernels, filesystems, and containers.
Ready to connect★ 6k
- View details
offensive-vuln-classesSkillFiles & storage
Loads expert attack-methodology guides into your agent for topics like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-wifiSkillMonitoring & ops
Teaches your agent wireless network attack methods used in authorized security testing, from handshake capture to evil-twin setups.
Ready to connect★ 6k
- View details
offensive-wifi-reconSkillMonitoring & ops
Lets your agent run guided Wi-Fi reconnaissance, mapping nearby networks, hidden SSIDs, clients, and encryption details.
Ready to connect★ 6k
- View details
offensive-windows-boundariesSkillFiles & storage
Loads expert offensive security playbooks into your agent, covering attack methods like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-windows-mitigationsSkillFiles & storage
Gives your agent expert guidance on offensive security techniques like SQL injection, shellcode, and exploit development.
Ready to connect★ 6k
- View details
offensive-windows-privescSkillSecurity
Gives your agent a step-by-step method for finding Windows privilege escalation paths during security testing.
Ready to connect★ 6k
- View details
offensive-wpa-enterpriseSkillAI & models
Gives your agent methods for attacking WPA/WPA2/WPA3-Enterprise networks to capture and crack authentication credentials.
Ready to connect★ 6k
- View details
offensive-wpa2-pskSkillSecurity
Lets your agent test Wi-Fi WPA/WPA2 password security by capturing handshakes and running dictionary-based cracking.
Ready to connect★ 6k
- View details
offensive-wpa3-saeSkillSecurity
Runs attack methods against WPA3/SAE Wi-Fi networks for security testing, including downgrade and side-channel attacks.
Ready to connect★ 6k
- View details
offensive-wpsSkillSecurity
Lets your agent run WPS PIN attack methods like Pixie Dust and PIN brute-force against Wi-Fi routers.
Ready to connect★ 6k
- View details
offensive-xxeSkillFiles & storage
Gives your agent expert guidance for running offensive security attacks like SQL injection and exploit development.
Ready to connect★ 6k
- View details
offensive-z-waveSkillCloud & infra
Lets your agent analyze and test Z-Wave smart-home networks for sniffing, key derivation, replay, and injection weaknesses.
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.