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.

Category: Dev tools

17,237 results · page 193 of 575

  • submittal-trackerSkillDev tools

    Lets your agent track construction submittals through review, approvals, revisions, and compliance.

    Ready to connect★ 330

    github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction330 stars

    View details
  • athena-devSkillDev tools

    Lets your agent run a full engineering workflow from gathering requirements to delivering code.

    Ready to connect★ 328

    github.com/m-xlsea/ruoyi-plus-soybean322 stars

    View details
  • athena-initSkillDev tools

    Sets up a new project for Athena by scanning it and generating environment scripts and state files.

    Ready to connect★ 328

    github.com/m-xlsea/ruoyi-plus-soybean322 stars

    View details
  • athena-migrateSkillDev tools

    Lets your agent upgrade a v9.5.5 project's .ai_state/ directory to the v9.6 schema with restructured index and details files.

    Ready to connect★ 328

    github.com/m-xlsea/ruoyi-plus-soybean322 stars

    View details
  • athena-reviewSkillDev tools

    Lets your agent run a code quality review on its own without going through the full development workflow.

    Ready to connect★ 328

    github.com/m-xlsea/ruoyi-plus-soybean322 stars

    View details
  • compoundSkillDev tools

    Lets your agent record lessons learned from a finished sprint into a lessons.md file.

    Ready to connect★ 328

    github.com/m-xlsea/ruoyi-plus-soybean322 stars

    View details
  • engine-call-contractSkillDev tools

    Teaches your agent the calling rules for a text engine so it can safely add or change engine entry points and errors.

    Ready to connect★ 328

    github.com/pmndrs/glyph124 stars

    View details
  • visualizationSkillDev tools

    Lets your agent follow best-practice rules when creating charts, graphs, and plots like line, bar, or pie.

    Ready to connect★ 327

    github.com/frankchen021/datastoria327 stars

    View details
  • bb-workflowSkillDev tools

    Lets your agent run an autonomous bug-bounty campaign end to end, driving recon through reporting step by step.

    Ready to connect★ 324

    github.com/encod3d-sec/torch325 stars

    View details
  • campaign-healthSkillDev tools

    Lets your agent run a health check that verifies the bb/pt/ctf workflow driver is consistently set up across all machines.

    Ready to connect★ 324

    github.com/encod3d-sec/torch325 stars

    View details
  • ctf-workflowSkillDev tools

    Lets your agent run an autonomous CTF hacking campaign, driving recon through exploitation on a target box step by step.

    Ready to connect★ 324

    github.com/encod3d-sec/torch325 stars

    View details
  • evidenceSkillDev tools

    Lets your agent clean up security findings by redacting cookies, personal data, HAR files, and screenshot metadata before reporting.

    Ready to connect★ 324

    github.com/encod3d-sec/torch325 stars

    View details
  • hunt-icsSkillDev tools

    Lets your agent test and exploit industrial control systems like PLCs, Modbus, and SCADA devices.

    Ready to connect★ 324

    github.com/encod3d-sec/torch325 stars

    View details
  • next-moveSkillDev tools

    Lets your agent rank and explain the highest-value next steps during a security engagement.

    Ready to connect★ 324

    github.com/encod3d-sec/torch325 stars

    View details
  • alphagenome-single-variant-analysisSkillDev tools

    Lets your agent analyze how a genetic variant affects gene expression and other genome signals via the AlphaGenome API.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • biostatisticsSkillDev tools

    Lets your agent run medical statistics tests like t-tests, ANOVA, chi-square, and survival analysis, plus power calculations.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • chainladderSkillDev tools

    Lets your agent run insurance loss reserving calculations like chain ladder and bootstrap simulation in Python.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • dicom-pipelineSkillDev tools

    Lets your agent parse, anonymize, convert, and retrieve medical imaging (DICOM) files.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • econmlSkillDev tools

    Lets your agent estimate causal effects of a treatment from observational data using methods like Double ML and Causal Forests.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • gdm-science-bundleSkillDev tools

    Lets your agent run DeepMind science skills like variant effect analysis and AlphaFold database lookups.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • label-quality-auditSkillDev tools

    Lets your agent audit training data labels and flag likely mislabeled examples for review.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • prime-intellect-cliSkillDev tools

    Lets your agent rent and manage Prime Intellect GPU compute, run RL training, and publish RL environments.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • triton-kernel-programmingSkillDev tools

    Gives your agent a hands-on template and API reference for writing, tuning, debugging, and benchmarking Triton GPU kernels.

    Ready to connect★ 324

    github.com/mkurman/zorai321 stars

    View details
  • analyse-issueSkillDev tools

    Lets your agent analyze GitHub issues for validity and suggest improvements.

    Ready to connect★ 323

    github.com/monarch-initiative/mondo322 stars

    View details
  • merge-termsSkillDev tools

    Lets your agent merge two ontology terms by obsoleting one and moving its data to the other.

    Ready to connect★ 323

    github.com/monarch-initiative/mondo322 stars

    View details
  • odkSkillDev tools

    Lets your agent run ODK-backed ontology commands like owltools, robot, and make targets in this repo.

    Ready to connect★ 323

    github.com/monarch-initiative/mondo322 stars

    View details
  • release-announcementSkillDev tools

    Lets your agent draft a formatted release announcement with a statistics table from release diff reports.

    Ready to connect★ 323

    github.com/monarch-initiative/mondo322 stars

    View details
  • favicon-icon-generatorSkillDev tools

    Lets your agent generate and validate favicons and app icons, including SVG icons, manifests, and metadata for web projects.

    Ready to connect★ 320

    github.com/kennyzir/7deer_skills319 stars

    View details
  • multi-game-codes-hubSkillDev tools

    Lets your agent build a Next.js codes page for a Roblox game from validated JSON data.

    Ready to connect★ 320

    github.com/kennyzir/7deer_skills319 stars

    View details
  • nextjs-seo-boosterSkillDev tools

    Adds SEO to Next.js apps with structured data, sitemaps, and meta tags — a nextjs claude skill.

    Ready to connect★ 320

    github.com/kennyzir/7deer_skills319 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.

55,004 of the 55,435 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