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 641 of 1,823
- View details
rho-cloud-onboardSkillCommunication
Lets your agent register an email address on Rhobot Mail and set up its own agent email account.
Ready to connect★ 372
- View details
small-improvementSkillDev tools
Lets your agent run an explore-and-build loop to ship one small useful improvement.
Ready to connect★ 372
- View details
sonarqubeSkillSecurity
Lets your agent run code quality and security checks on your repositories, reviewing issues, quality gates, and risks.
Ready to connect★ 372
- View details
sttSkillMedia
Lets your agent transcribe spoken audio from the microphone into text for voice commands or dictation.
Ready to connect★ 372
- View details
tasker-xmlSkillProductivity
Lets your agent create Tasker profiles and tasks in XML to automate things on Android.
Ready to connect★ 372
- View details
update-piSkillAI & models
Lets your agent update the pi coding agent tool to its latest version.
Ready to connect★ 372
- View details
vault-cleanSkillDocs & knowledge
Finds notes in your vault that nothing links to and helps connect or clean them up.
Ready to connect★ 372
- View details
advanced-redteamSkillSecurity
Lets your agent run offensive security tasks like red team testing, exploit development, and penetration testing.
Ready to connect★ 367
- View details
browser-exploitationSkillWeb & browsing
Guides your agent through building browser exploits like JIT type confusion, sandbox escapes, and 1-click RCE chains.
Ready to connect★ 367
- View details
cicd-supply-chainSkillAI & models
Lets your agent audit CI/CD pipelines and software supply chains for attack techniques and weak spots.
Ready to connect★ 367
- View details
coding-masterySkillSecurity
Helps your agent write security code like scanners, exploits, and network tools in Python, C, Go, Rust, or assembly.
Ready to connect★ 367
- View details
container-k8s-escapeSkillCloud & infra
Lets your agent test container and Kubernetes escape techniques for security assessment.
Ready to connect★ 367
- View details
cookSkillProductivity
Lets your agent run work in review loops, repeated passes, parallel attempts, and step through task lists.
Ready to connect★ 371
- View details
crypto-analysisSkillMonitoring & ops
Lets your agent analyze cryptography for weaknesses, from TLS and key issues to JWT forgery and hash cracking.
Ready to connect★ 367
- View details
engagement-flowSkillSecurity
Guides your agent through planning and running security testing engagements in ordered phases with quality checks before attacking.
Ready to connect★ 367
- View details
engagement-memorySkillDocs & knowledge
Lets your agent recall techniques from past security engagements and record confirmed findings ranked by impact.
Ready to connect★ 367
- View details
exploit-developmentSkillWeb & browsing
Guides your agent through turning memory-corruption bugs into working proof-of-concept exploits.
Ready to connect★ 367
- View details
finding-disciplineSkillSecurity
Guides your agent to properly record, rate severity, and report security findings before confirming them.
Ready to connect★ 367
- View details
initial-accessSkillSecurity
Provides the agent with techniques for gaining initial access to target systems, including phishing, payload delivery, and exploitation.
Ready to connect★ 367
- View details
keylogger-archSkillSecurity
Lets your agent run offensive security tasks like red teaming, exploit development, and penetration testing.
Ready to connect★ 367
- View details
malware-analysisSkillDocs & knowledge
Lets your agent analyze suspicious files and memory to detect and reverse-engineer malware.
Ready to connect★ 367
- View details
mobile-pentestSkillMonitoring & ops
Guides your agent through security testing of Android and iOS apps, including bypassing security controls and analyzing app behavior.
Ready to connect★ 367
- View details
network-attackSkillSecurity
Lets your agent run network attack techniques like poisoning, relaying, pivoting, and man-in-the-middle during security testing.
Ready to connect★ 367
- View details
oneclickvirtSkillMonitoring & ops
Lets your agent manage containers, virtual machines, provider nodes, health checks, and metrics.
Ready to connect★ 371
- View details
opsec-disciplineSkillAI & models
Makes your agent check its detection footprint, cleanup needs, and secret redaction before taking offensive security actions.
Ready to connect★ 367
- View details
privesc-windowsSkillSecurity
Lets your agent run Windows privilege escalation techniques like service hijacking, UAC bypasses, and credential harvesting.
Ready to connect★ 367
- View details
recon-osintSkillCloud & infra
Lets your agent map a company's public-facing systems and find exposed subdomains, leaked secrets, and security issues.
Ready to connect★ 367
- View details
red-team-opsSkillAI & models
Guides your agent through running a full red-team engagement, from initial access to persistence and evasion.
Ready to connect★ 367
- View details
reverse-engineeringSkillAI & models
Lets your agent analyze and decompile binaries and firmware using tools like Ghidra, GDB, and Frida.
Ready to connect★ 367
- View details
scope-disciplineSkillAI & models
Makes your agent check and respect the authorized scope of a target before any security testing or interaction.
Ready to connect★ 367
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.