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
53,863 results · page 164 of 1,796
- View details
perf-loopSkillDev tools
Iteratively optimize Fallow performance with stable benchmarks, before-and-after evidence, and correctness gates.
Ready to connect★ 5k
- View details
sig-auditSkillDev tools
Lets your agent measure code maintainability using SIG properties and update an evidence-backed audit report.
Ready to connect★ 5k
- View details
sig-audit-loopSkillDev tools
Lets your agent iteratively improve code maintainability, keeping only changes that measurably improve it without regressions.
Ready to connect★ 5k
- View details
slop-auditSkillDev tools
Audit Fallow for unnecessary code, misleading tests, redundant abstractions, avoidable copying, and stale maintenance guidance. Use for a requested slop audit or deep cleanup pass.
Ready to connect★ 5k
- View details
sweepSkillDocs & knowledge
Lets your agent check a work session for missed tasks, unverified changes, and leftover cleanup before calling it done.
Ready to connect★ 5k
- View details
team-assemblySkillDev tools
Picks the smallest set of reviewers needed for a code change based on what files and systems it touches.
Ready to connect★ 5k
- View details
vscode-reviewSkillDev tools
Lets your agent review the VS Code extension's behavior, commands, views, and LSP integration when editing it.
Ready to connect★ 5k
- View details
apk-redteam-pipelineSkillAI & models
Lets your agent download and analyze Android apps for security flaws, from fetching the APK to probing it at runtime.
Ready to connect★ 4k
- View details
bug-bountySkillSecurity
Guides your agent through bug bounty hunting: recon, learning from disclosed reports, and finding vulnerabilities.
Ready to connect★ 4k
- View details
bugcrowd-reportingSkillSearch
Helps your agent write better bug bounty reports with Bugcrowd severity rules and category selection tactics.
Ready to connect★ 4k
- View details
cloud-iam-deepSkillCloud & infra
Lets your agent probe cloud IAM permissions across AWS, Azure, and GCP to find privilege escalation paths.
Ready to connect★ 4k
- View details
enterprise-vpn-attackSkillSecurity
Gives your agent a reference of known attack techniques and CVEs for enterprise VPN appliances like Cisco ASA and FortiGate.
Ready to connect★ 4k
- View details
evidence-hygieneSkillCommunication
Guides your agent to capture and redact bug-bounty evidence, masking cookies, PII, and sensitive fields in PoCs.
Ready to connect★ 4k
- View details
hunt-api-misconfigSkillSecurity
Lets your agent test APIs for security flaws like privilege escalation via mass assignment and JWT forgery.
Ready to connect★ 4k
- View details
hunt-aspnetSkillAI & models
Lets your agent audit ASP.NET apps for known weaknesses like ViewState issues and error-page leaks.
Ready to connect★ 4k
- View details
hunt-atoSkillCommunication
Lets your agent analyze apps for nine account takeover attack paths like password reset flaws and MFA bypass.
Ready to connect★ 4k
- View details
hunt-auth-bypassSkillSecurity
Lets your agent hunt for authentication bypass vulnerabilities using techniques from real bug bounty reports.
Ready to connect★ 4k
- View details
hunt-brute-forceSkillCommunication
Lets your agent test a login system for weak rate limits and brute-force protection gaps.
Ready to connect★ 4k
- View details
hunt-business-logicSkillSecurity
Guides your agent to find business logic flaws like coupon stacking and price tampering in web apps.
Ready to connect★ 4k
- View details
hunt-cache-poisonSkillCloud & infra
Guides your agent through testing websites for web cache poisoning and cache deception vulnerabilities.
Ready to connect★ 4k
- View details
hunt-captcha-bypassSkillAI & models
Guides your agent through testing websites for six common CAPTCHA security flaws.
Ready to connect★ 4k
- View details
hunt-cicdSkillFiles & storage
Lets your agent scan CI/CD setups like GitHub Actions and Jenkins for security vulnerabilities.
Ready to connect★ 4k
- View details
hunt-clickjackingSkillSecurity
Lets your agent check web pages for missing clickjacking protections that could let attackers trick users into hidden clicks.
Ready to connect★ 4k
- View details
hunt-cloud-misconfigSkillFiles & storage
Lets your agent scan AWS and GCP setups for security mistakes like public buckets or exposed credentials.
Ready to connect★ 4k
- View details
hunt-corsSkillCommunication
Lets your agent test websites for CORS misconfigurations that could leak authenticated data to attacker-controlled origins.
Ready to connect★ 4k
- View details
hunt-csrfSkillSecurity
Lets your agent hunt for CSRF vulnerabilities using patterns from public bug bounty reports.
Ready to connect★ 4k
- View details
hunt-deserializationSkillAI & models
Guides your agent to find insecure deserialization flaws like Java gadget chains and Python pickle bugs in a target.
Ready to connect★ 4k
- View details
hunt-dispatchSkillAI & models
Loads the right attack skill set for a security hunt after a mode like red team or web app testing is chosen.
Ready to connect★ 4k
- View details
hunt-domSkillCommunication
Lets your agent scan web pages for client-side vulnerabilities like DOM clobbering and postmessage hijacking.
Ready to connect★ 4k
- View details
hunt-exceptional-conditionsSkillFiles & storage
Lets your agent probe endpoints with malformed input to find error leaks like stack traces and internal paths.
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.
53,430 of the 53,863 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.