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

63,368 results · page 1458 of 2,113

  • jackson-inject-securitySkillSecurity

    Teaches your agent how to prevent Jackson @JacksonInject attacks where JSON input overrides server-side values.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • jackson-injection-securitySkillSecurity

    Teaches your agent how to prevent JSON input from overriding Jackson-injected values, covering known CVE patterns and defenses.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • java-patch-workflowSkillSecurity

    Lets your agent create and apply patches to Java projects and rebuild them with Maven for security fixes.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • jq-processingSkillDev tools

    Lets your agent parse, filter, and summarize JSON data using jq to build reports.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • json-data-analysisSkillDev tools

    Lets your agent analyze enterprise data queries and return answers as structured JSON.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • json-data-extractionSkillFiles & storage

    Lets your agent extract, parse, and query JSON data from large files.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • json-report-generationSkillDev tools

    Lets your agent generate structured JSON reports with proper formatting and validation.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • json-result-formattingSkillDev tools

    Lets your agent format query results as clean JSON and track token usage.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • langgraph-architectureSkillAI & models

    Guides your agent through LangGraph design choices like state management, multi-agent setup, and persistence.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • langgraph-code-reviewSkillDev tools

    LangGraph Claude skill lets your agent review LangGraph code for bugs, bad patterns, and fixes.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • langgraph-implementationSkillAI & models

    Lets your agent write LangGraph code that builds stateful agent graphs with nodes, edges, state, and checkpointing.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • liveview-code-reviewSkillSecurity

    Lets your agent review Phoenix LiveView code for lifecycle patterns, assigns, components, and security issues.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • llm-artifacts-detectionSkillAI & models

    Lets your agent find leftover AI-generated code clutter like dead code, weak tests, and over-abstraction in a codebase.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • llm-judgeSkillAI & models

    Lets your agent compare two or more code implementations against a spec and judge which one is better.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • macros-code-reviewSkillDev tools

    Lets your agent review Rust macro code for hygiene issues, misuse, and compile-time impact.

    Ready to connect★ 83

    github.com/existential-birds/beagle83 stars

    View details
  • make-store-assetsSkillAI & models

    Lets your agent make Claude skill files that set up an automated AI company organization.

    Ready to connect★ 83

    github.com/toktokhan-dev/agent-company74 stars

    View details
  • mandarin-rhyming-guideSkillDev tools

    Lets your agent write rhymes for classical Chinese poetry using modern Mandarin pronunciation and tones.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • maven-druid-buildSkillDocs & knowledge

    Lets your agent build Apache Druid with Maven, managing memory limits and skipping verification checks.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • meeting-request-parsingSkillCommunication

    Lets your agent read meeting request emails and pull out the duration and time constraints.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • model-calibrationSkillMonitoring & ops

    Lets your agent calculate RMSE metrics and calibrate parameters to validate lake models.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • netcdf-analysisSkillDev tools

    Lets your agent read and analyze NetCDF climate model output files and compute RMSE error metrics with Python.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • netcdf-processingSkillAI & models

    Lets your agent read and analyze NetCDF data files from lake simulation models.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • nlp-project-setupSkillDev tools

    Lets your agent set up a Python environment for NLP and preference optimization projects.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • openclaw-control-centerSkillMonitoring & ops

    Local-first, security-first control center for OpenClaw agents — visibility dashboard with readonly defaults, token attribution, collaboration tracing, and safe write operations.

    Ready to connect★ 83

    github.com/aradotso/trending-skills83 stars

    View details
  • opencv-grayscaleSkillMedia

    Lets your agent convert color images to grayscale using OpenCV and save them in place.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • opencv-template-matchingSkillMedia

    Lets your agent count how many times a template object appears in an image using OpenCV template matching.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • openpyxl-formula-editingSkillFiles & storage

    Lets your agent edit existing Excel files, adding formulas while keeping the original formatting intact.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • optimize-seo-geoSkillAI & models

    Lets your agent set up and run an automated organization structured like an AI company.

    Ready to connect★ 83

    github.com/toktokhan-dev/agent-company74 stars

    View details
  • package-lock-parsingSkillFiles & storage

    Lets your agent read npm package-lock.json files and list the dependencies with their installed versions.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 stars

    View details
  • parallel-grid-searchSkillSearch

    Lets your agent run hyperparameter grid searches in parallel across multiple CPU cores using joblib.

    Ready to connect★ 83

    github.com/cxcscmu/skilllearnbench83 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.

61,234 of the 63,368 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 workspace 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