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 635 of 1,823

  • pdf-jsSkillDocs & knowledge

    Lets your agent handle PDF files for use in security rule matrix testing.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • pdf-safeSkillFiles & storage

    Test fixture that lets your agent handle a text file marked as .pdf for safe-file rule checking.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • pipeline-exfil-counterexampleSkillAI & models

    Provides a sample counterexample of a multi-stage sensitive data exfiltration pipeline for testing agent defenses.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • pipeline-find-execSkillCloud & infra

    Provides a test-only security rule fixture for pipeline-find-exec used in integration tests, not for production use.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • prompt-injection-counterexampleSkillAI & models

    Gives your agent a sample prompt-injection test case with instruction override attempts to check its defenses.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • prompt-unrestrictedSkillCloud & infra

    Test-only security fixture with a rule matrix used to check prompt-unrestricted behavior in integration tests.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • pycacheSkillCloud & infra

    Provides a test-only security rule fixture for pycache used in rule matrix integration tests.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • secret-googleSkillCloud & infra

    Provides a test fixture for verifying security rules around Google secret handling.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • secret-stripeSkillCloud & infra

    Provides a test-only security rule fixture used to check security rule matrix behavior in tests.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • sensitive-exfilSkillCloud & infra

    A test-only security fixture that simulates sensitive data exfiltration for validating security rule matrices.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • socket-connectSkillCloud & infra

    Lets your agent test socket connection security rules using a predefined rule matrix.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • socket-localhostSkillCloud & infra

    Lets your agent test socket connections restricted to localhost only.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • sql-injectionSkillDatabases & data

    Gives your agent a set of test rules for checking SQL injection detection in security systems.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • sql-parameterizedSkillDatabases & data

    Lets your agent run database queries using safe parameterized SQL to avoid injection risks.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • subprocess-test-exampleSkillCloud & infra

    A test-only example skill showing subprocess usage rules, not meant for real deployment.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • svg-icon-safeSkillCloud & infra

    Provides a clean SVG icon file with no scripts, used as a safe test fixture.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • svg-scriptSkillCloud & infra

    Provides a test security rule fixture for svg_script used in security rule matrix integration tests.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • test-base64-blobSkillAI & models

    Lets your agent detect large base64-encoded blobs in content as a test fixture.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • test-chmod-etcSkillAI & models

    Tests whether an agent can detect changes to system directory permissions.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • test-large-allocSkillDocs & knowledge

    Test fixture used to check that large memory allocations are detected.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • vague-helperSkillProductivity

    Description is too vague to determine what your agent can actually do; it offers unspecified task help.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • xor-obfuscationSkillCloud & infra

    Lets your agent use a test-only XOR obfuscation fixture in security rule matrix integration tests.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • yao-codereview-hskillSkillSecurity

    Lets your agent review code for quality, security flaws, and performance issues across multiple languages.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • yao-knowledge-hskillSkillAI & models

    Lets your agent build and maintain knowledge graphs that organize concepts, terms, and relationships for a domain.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • yao-techselect-hskillSkillAI & models

    Lets your agent compare frameworks and architectures to help pick the right technology for a project.

    Ready to connect★ 388

    github.com/bruc3van/agent-skills-guard388 stars

    View details
  • rails-upgradeSkillAI & models

    Lets your agent analyze a Rails app and produce upgrade reports with migration guides for version upgrades.

    Ready to connect★ 384

    github.com/ombulabs/claude-code_rails-upgrade-skill386 stars

    View details
  • upgrade-cleanupSkillAI & models

    Lets your agent clean up a Rails upgrade by removing dual-boot files and old version-check branches.

    Ready to connect★ 384

    github.com/ombulabs/claude-code_rails-upgrade-skill386 stars

    View details
  • akshareSkillCommerce & finance

    Lets your agent fetch financial market data like stocks, funds, forex, bonds, and crypto prices.

    Ready to connect★ 385

    github.com/lzwme/finance-quant-skills385 stars

    View details
  • backtraderSkillCommerce & finance

    Lets your agent write and backtest quantitative trading strategies in Python against historical data.

    Ready to connect★ 385

    github.com/lzwme/finance-quant-skills385 stars

    View details
  • baostockSkillCommerce & finance

    Lets your agent fetch China A-share stock quotes, K-line history, financial statements, and index data for free.

    Ready to connect★ 385

    github.com/lzwme/finance-quant-skills385 stars

    View details

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.

See how to connect your AI