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 634 of 1,823
- View details
assets-suspicious-urlSkillCloud & infra
Provides a test fixture of suspicious URL security rules for validating security rule matrix integrations.
Ready to connect★ 388
- View details
base64-execSkillCloud & infra
A test fixture of base64-exec rules used to check security rule matrices, not meant for production use.
Ready to connect★ 388
- View details
base64-networkSkillCloud & infra
Provides a test security rule fixture for base64_network scenarios used in integration testing, not for real deployments.
Ready to connect★ 388
- View details
bash-violationSkillCloud & infra
Provides a security rule matrix fixture for testing bash-violation rules, intended only for integration tests.
Ready to connect★ 388
- View details
bruce-doc-converterSkillFiles & storage
Lets your agent convert Word, Excel, PowerPoint, PDF, and Markdown files between formats, including Markdown to Word with diagrams rendered as images.
Ready to connect★ 388
- View details
bruce-drawioSkillAI & models
Lets your agent create diagrams like flowcharts, UML, ER, and network topology charts.
Ready to connect★ 388
- View details
compound-launderingSkillCloud & infra
Provides a test-only security rule fixture for compound laundering checks in integration tests.
Ready to connect★ 388
- View details
download-chmodSkillCloud & infra
Test fixture skill used to check security rule matrices, not meant for real use.
Ready to connect★ 388
- View details
env-harvestSkillCloud & infra
A security test fixture that lets your agent practice detecting skills that harvest environment variables.
Ready to connect★ 388
- View details
env-var-safe-shellSkillCloud & infra
Lets your agent follow rules for safely using environment variables in shell commands without piping.
Ready to connect★ 388
- View details
eval-userSkillCloud & infra
Provides a test-only security rule fixture for evaluating user permission rules in integration tests.
Ready to connect★ 388
- View details
fake-md-peSkillCloud & infra
Provides a test-only security rule fixture for validating security rule matrix integrations.
Ready to connect★ 388
- View details
file-magic-mismatch-counterexampleSkillFiles & storage
Provides a test file whose extension does not match its actual content, for checking file-type validation.
Ready to connect★ 388
- View details
find-execSkillCloud & infra
Test fixture for verifying agent security rules around the find-exec command lookup, not for real use.
Ready to connect★ 388
- View details
glob-hiddenSkillCloud & infra
Provides a security rule test fixture for glob_hidden used in integration testing, not for production use.
Ready to connect★ 388
- View details
hex-blobSkillCloud & infra
Provides a test-only security rule fixture for hex-blob used in integration tests.
Ready to connect★ 388
- View details
hidden-dataSkillCloud & infra
Provides a security test fixture with rule matrix data for testing hidden-data security rules.
Ready to connect★ 388
- View details
hidden-scriptSkillCloud & infra
Provides a test-only security rule fixture for validating security rule matrix integrations.
Ready to connect★ 388
- View details
homoglyphSkillCloud & infra
Lets your agent test homoglyph detection rules in a security rule matrix test setup.
Ready to connect★ 388
- View details
homoglyph-obfuscation-counterexampleSkillAI & models
Lets your agent generate test examples of mixed-script lookalike account names used to disguise fraud.
Ready to connect★ 388
- View details
infinite-loopSkillCloud & infra
Provides a test-only security rule fixture for running security rule matrix integration tests.
Ready to connect★ 388
- View details
invisible-ctrlSkillCloud & infra
Provides a test-only security rule matrix fixture for integration testing, not for real deployments.
Ready to connect★ 388
- View details
js-fetch-mockSkillCloud & infra
Lets your agent mock fetch calls in JavaScript tests using a rule matrix, for test setups only.
Ready to connect★ 388
- View details
js-fsSkillCloud & infra
Provides a test fixture rule matrix for js-fs used in security rule matrix integration tests, not for production use.
Ready to connect★ 388
- View details
js-fs-exampleSkillFiles & storage
Lets your agent follow example rules for using the file system, meant as documentation only.
Ready to connect★ 388
- View details
localhost-okSkillCloud & infra
A test-only security rule fixture that lets your agent check localhost-ok rule behavior in integration tests.
Ready to connect★ 388
- View details
missing-licenseSkillCloud & infra
A security test fixture that simulates a missing-license scenario for rule matrix integration tests.
Ready to connect★ 388
- View details
network-declaredSkillCloud & infra
Provides a test-only security rule fixture for network-declared checks used in integration testing.
Ready to connect★ 388
- View details
path-safe-realpathSkillFiles & storage
Lets your agent check file paths are real and safe before opening them.
Ready to connect★ 388
- View details
path-traversal-openSkillCloud & infra
Provides a test fixture rule set for path traversal open checks used in security rule matrix testing.
Ready to connect★ 388
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.