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
54,220 results · page 432 of 1,808
- View details
offersSkillDocs & knowledge
Helps your agent design and improve what you sell, covering bonuses, guarantees, urgency, naming, and payment structure.
Ready to connect★ 861
- View details
no-negative-echoSkillDev tools
Keeps rejected alternatives and corrections out of your agent's final artifacts like commits, labels, and metadata.
Ready to connect★ 849
- View details
api-testerSkillAI & models
Lets your agent generate and validate API tests from OpenAPI specs and existing code.
Ready to connect★ 849
- View details
db-migratorSkillDatabases & data
Lets your agent compare database schemas and generate migration scripts.
Ready to connect★ 849
- View details
dep-auditorSkillSecurity
Lets your agent check project dependencies for known vulnerabilities, outdated versions, and license issues without changing anything.
Ready to connect★ 849
- View details
ds-mapperSkillAI & models
Lets your agent generate an annotated visual directory tree to quickly understand any codebase.
Ready to connect★ 849
- View details
env-managerSkillFiles & storage
Lets your agent scan, validate, and sync .env files and generate secure config templates.
Ready to connect★ 849
- View details
error-translatorSkillCommunication
Lets your agent translate English programming error messages into Chinese with explanations and fixes.
Ready to connect★ 849
- View details
eslint-fixSkillAI & models
Lets your agent diagnose and fix ESLint errors, warnings, and configuration issues in a project.
Ready to connect★ 849
- View details
github-actions-genSkillCloud & infra
Lets your agent create and fix GitHub Actions workflows for builds, tests, releases, and deployments.
Ready to connect★ 849
- View details
i18n-helperSkillAI & models
Lets your agent find hardcoded text in code, set up translation configs, and batch translate strings.
Ready to connect★ 849
- View details
log-analyzerSkillFiles & storage
Lets your agent parse log files, spot unusual patterns, and find likely root causes.
Ready to connect★ 849
- View details
refactor-advisorSkillAI & models
Lets your agent detect code smells and suggest refactoring improvements.
Ready to connect★ 849
- View details
skill-curatorSkillSecurity
Lets your agent evaluate Chinese-language GitHub skills and workflows for quality and whether they belong in a curated list.
Ready to connect★ 849
- View details
test-generatorSkillAI & models
Lets your agent generate and validate unit or integration tests based on your existing code.
Ready to connect★ 849
- View details
zh-code-reviewerSkillAI & models
Lets your agent write detailed code review reports in Chinese.
Ready to connect★ 849
- View details
zh-docgenSkillDocs & knowledge
Lets your agent automatically generate Chinese technical documentation from your codebase.
Ready to connect★ 849
- View details
zh-readmeSkillAI & models
Lets your agent analyze a code project and generate a README written for Chinese-speaking developers.
Ready to connect★ 849
- View details
401-403-bypass-techniquesSkillDev tools
Lets your agent attempt to bypass 401/403 access-denied errors on websites and APIs using known evasion techniques.
Ready to connect★ 842
- View details
active-directory-acl-abuseSkillDev tools
Lets your agent find and explain ways misconfigured Active Directory permissions could be abused.
Ready to connect★ 842
- View details
active-directory-certificate-servicesSkillDev tools
Lets your agent run attack techniques against misconfigured Windows certificate services to gain higher privileges.
Ready to connect★ 842
- View details
active-directory-kerberos-attacksSkillSecurity
Walks your agent through Active Directory Kerberos attack techniques like Kerberoasting and pass-the-ticket.
Ready to connect★ 842
- View details
ai-ml-securitySkillSecurity
Gives your agent a playbook for assessing AI model security risks like poisoned weights and data privacy attacks.
Ready to connect★ 842
- View details
android-pentesting-tricksSkillSecurity
Guides your agent through authorized Android app security testing like SSL pinning bypass and root detection bypass.
Ready to connect★ 842
- View details
anti-debugging-techniquesSkillDev tools
Teaches your agent how to detect and bypass anti-debugging protections when analyzing protected binaries.
Ready to connect★ 842
- View details
api-auth-and-jwt-abuseSkillSecurity
Gives your agent a step-by-step guide for testing how well an API checks authentication, like bearer tokens, API keys, and JWTs.
Ready to connect★ 842
- View details
api-authorization-and-bolaSkillDev tools
Gives your agent a playbook for testing APIs for authorization flaws like BOLA and weak access controls.
Ready to connect★ 842
- View details
api-recon-and-docsSkillDocs & knowledge
Guides your agent to discover and review an API's endpoints, schemas, versions, and documentation for testing.
Ready to connect★ 842
- View details
api-secSkillSecurity
Points your agent to the right API security workflow, like recon, authorization checks, or token abuse testing.
Ready to connect★ 842
- View details
api-testingSkillDev tools
Lets your agent test APIs for authorization flaws, schema exposure, and business logic weaknesses.
Ready to connect★ 842
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.
53,788 of the 54,220 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.