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 149 of 1,823
- View details
updatefirstmateSkillDev tools
Lets your agent update its own tooling files to the latest version from its source repository and restart affected helpers.
Ready to connect★ 6k
- View details
offensive-active-directorySkillAI & models
Gives your agent a playbook of Active Directory attack techniques for red team work.
Ready to connect★ 6k
- View details
offensive-advanced-redteamSkillMedia
Lets your agent learn red team testing methods like scoping, C2 infrastructure design, and engagement reporting.
Ready to connect★ 6k
- View details
offensive-anti-forensicsSkillMonitoring & ops
Teaches your agent how to clear logs, edit audit trails, and tamper with timestamps during authorized red team engagements.
Ready to connect★ 6k
- View details
offensive-bluetooth-bleSkillAI & models
Lets your agent run Bluetooth Low Energy attacks like device scanning, sniffing, and man-in-the-middle relays.
Ready to connect★ 6k
- View details
offensive-bluetooth-classicSkillFiles & storage
Lets your agent run Bluetooth attack methods like device discovery, PIN cracking, and file-transfer abuse.
Ready to connect★ 6k
- View details
offensive-bug-identificationSkillFiles & storage
Gives your agent expert security-testing methods for finding vulnerabilities like SQL injection and writing exploits.
Ready to connect★ 6k
- View details
offensive-business-logicSkillSecurity
Lets your agent test web, mobile, and API apps for business logic flaws like workflow bypass and price manipulation.
Ready to connect★ 6k
- View details
offensive-c2-frameworksSkillFiles & storage
Lets your agent learn how offensive command-and-control frameworks like Cobalt Strike and Sliver are deployed and configured for red team testing.
Ready to connect★ 6k
- View details
offensive-container-escapeSkillFiles & storage
Teaches your agent container escape and breakout techniques against Docker, containerd, and Podman runtimes.
Ready to connect★ 6k
- View details
offensive-crash-analysisSkillFiles & storage
Gives your agent expert guides for offensive security tasks like SQL injection, shellcode, and exploit development.
Ready to connect★ 6k
- View details
offensive-crypto-attacksSkillCommerce & finance
Teaches your agent how to find and exploit weaknesses in how applications use encryption.
Ready to connect★ 6k
- View details
offensive-data-exfiltrationSkillFiles & storage
Teaches your agent methods for moving data out of networks via DNS, HTTPS, ICMP, cloud storage, and email channels.
Ready to connect★ 6k
- View details
offensive-deauth-disassocSkillSecurity
Lets your agent run Wi-Fi deauthentication and disassociation attacks for security testing.
Ready to connect★ 6k
- View details
offensive-dependency-confusionSkillAI & models
Teaches your agent how dependency confusion and namespace attacks work across package ecosystems for security testing.
Ready to connect★ 6k
- View details
offensive-evil-twinSkillSecurity
Lets your agent set up rogue Wi-Fi access points that lure and phish nearby devices.
Ready to connect★ 6k
- View details
offensive-exploit-developmentSkillFiles & storage
Gives your agent step-by-step offensive security methods for tasks like SQL injection, exploit writing, and evasion.
Ready to connect★ 6k
- View details
offensive-fast-checkingSkillFiles & storage
Gives your agent expert offensive security playbooks for tasks like exploiting vulnerabilities and bypassing defenses.
Ready to connect★ 6k
- View details
offensive-file-uploadSkillFiles & 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-fuzzingSkillAI & models
Teaches your agent how to find software bugs by running fuzzing tools and triaging crashes.
Ready to connect★ 6k
- View details
offensive-graphqlSkillSecurity
Guides your agent through attacking GraphQL APIs in pentests, from finding endpoints to bypassing auth.
Ready to connect★ 6k
- View details
offensive-idorSkillFiles & storage
Gives your agent expert security attack playbooks covering topics like SQL injection, exploits, and evasion techniques.
Ready to connect★ 6k
- View details
offensive-iotSkillFiles & storage
Guides your agent through IoT device security testing steps like firmware extraction, hardware recon, and analysis.
Ready to connect★ 6k
- View details
offensive-jwtSkillFiles & storage
Teaches your agent how to test JWT tokens for common security flaws like weak signing secrets and algorithm tricks.
Ready to connect★ 6k
- View details
offensive-keylogger-archSkillFiles & storage
Gives your agent expert offensive-security attack methods like SQL injection, exploit development, and EDR evasion.
Ready to connect★ 6k
- View details
offensive-krack-fragattacksSkillSecurity
Explains KRACK and FragAttacks Wi-Fi exploits and how they work against WPA2 devices.
Ready to connect★ 6k
- View details
offensive-lateral-movementSkillAI & models
Gives your agent guidance on credential-based lateral movement techniques like pass-the-hash and NTLM relay for red team testing.
Ready to connect★ 6k
- View details
offensive-lorawan-sub-ghzSkillAI & models
Lets your agent learn attack techniques for LoRaWAN and sub-GHz radio systems like key reuse, replay, and signal spoofing.
Ready to connect★ 6k
- View details
offensive-mitigationsSkillFiles & storage
Gives your agent expert offensive security methods for tasks like SQL injection, exploit development, and EDR evasion.
Ready to connect★ 6k
- View details
offensive-mobileSkillAI & models
Gives your agent a step-by-step method for security testing Android and iOS apps, including analysis and bypass techniques.
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.