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

55,435 results · page 871 of 1,848

  • vasp-relaxSkillDev tools

    Lets your agent set up and run VASP geometry optimizations for bulk crystals, surfaces, and adsorbates.

    Ready to connect★ 201

    github.com/hello-qm/catgo-lrg193 stars

    View details
  • vasp-routerSkillProductivity

    Lets your agent route materials simulation calculation requests to the right task type with correct settings.

    Ready to connect★ 201

    github.com/hello-qm/catgo-lrg193 stars

    View details
  • vasp-staticSkillDev tools

    Lets your agent run fixed-geometry quantum chemistry energy calculations to get a material's total energy or prepare charge density files.

    Ready to connect★ 201

    github.com/hello-qm/catgo-lrg193 stars

    View details
  • vlcSkillAI & models

    Teaches your agent to configure, control, and verify VLC media player state using Python scripts and config files.

    Ready to connect★ 201

    github.com/xlang-ai/cua-gym194 stars

    View details
  • volcano-plotSkillDev tools

    Lets your agent build volcano plots that compare catalyst activity across a descriptor to spot the best candidates.

    Ready to connect★ 201

    github.com/hello-qm/catgo-lrg193 stars

    View details
  • vs-codeSkillFiles & storage

    Lets your agent configure and verify VSCode settings, keybindings, extensions, and workspace files using Python.

    Ready to connect★ 201

    github.com/xlang-ai/cua-gym194 stars

    View details
  • workflow_errorsSkillProductivity

    Lets your agent diagnose and fix CatGo workflow errors like HPC connection failures, missing POTCARs, and stuck tasks.

    Ready to connect★ 201

    github.com/hello-qm/catgo-lrg193 stars

    View details
  • auditcodexSkillAI & models

    Lets your agent send recent code changes to OpenAI Codex for an independent review.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • auditcodexdirectSkillFiles & storage

    Lets your agent send specific files to OpenAI Codex CLI for an independent code review.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • audithandoffdocSkillDocs & knowledge

    Lets your agent perform a deep audit of a project and write a handoff document to brief another agent.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • packet-tracerSkillCloud & infra

    Lets your agent build and configure Cisco Packet Tracer network simulations, adding devices, links, and configs.

    Ready to connect★ 200

    github.com/mats2208/mcp-packet-tracer158 stars

    View details
  • pairSkillAI & models

    Lets your agent continue a pair programming session from where it left off.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • ralphinitSkillAI & models

    Lets your agent run a ralph-style looping session that repeats tasks iteratively.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • ralphonceSkillDocs & knowledge

    Lets your agent pick one top-priority feature from your docs, build it, test it, update docs, and commit.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • researchquestionsSkillDocs & knowledge

    Lets your agent write a structured research prompt document made up of questions only.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • sanitycheckSkillAI & models

    Lets your agent sanity check your project by chatting through where things stand in plain language.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • selfauditSkillAI & models

    Has your agent pause and critically review its own recent work from first principles.

    Ready to connect★ 200

    github.com/sterlingcrispin/claude_slash_commands200 stars

    View details
  • universal-video-prompt-skillSkillMedia

    Lets your agent write one video prompt spec and adapt it for different video generation models.

    Ready to connect★ 200

    github.com/atlascloudai/awesome-seedance-2.5-prompts-skills200 stars

    View details
  • create-videoSkillMedia

    Lets your agent create a short vertical social media video with Vietnamese voiceover.

    Ready to connect★ 199

    github.com/cuongyd196/auto-compare-video199 stars

    View details
  • d3kSkillDev tools

    Helps your agent debug web apps by guiding it through d3k debugging workflows.

    Ready to connect★ 198

    github.com/varandrew/moor199 stars

    View details
  • niubiskillSkillWeb & browsing

    Lets your agent analyze a product or idea and suggest the best way to monetize it and who would pay.

    Ready to connect★ 199

    github.com/nathanskill/niubiskill199 stars

    View details
  • agent-delegationSkillMedia

    Lets your agent design multi-agent setups, splitting work across sub-agents and managing how they share context and tasks.

    Ready to connect★ 198

    github.com/kangarooking/system-prompt-skills198 stars

    View details
  • citation-systemSkillWeb & browsing

    Guides your agent to design citation formats and source attribution systems so answers can be traced back to sources.

    Ready to connect★ 198

    github.com/kangarooking/system-prompt-skills198 stars

    View details
  • code-engineeringSkillFiles & storage

    Helps you write system prompts for coding agents that edit code, handle files, and run Git workflows.

    Ready to connect★ 198

    github.com/kangarooking/system-prompt-skills198 stars

    View details
  • codeckSkillFiles & storage

    Lets your agent scan your local files and guide you step by step to build a presentation deck.

    Ready to connect★ 198

    github.com/hiyeshu/codeck198 stars

    View details
  • codeck-designSkillFiles & storage

    Lets your agent turn a deck.md outline into a single styled HTML presentation file with slides and design system.

    Ready to connect★ 198

    github.com/hiyeshu/codeck198 stars

    View details
  • codeck-outlineSkillDocs & knowledge

    Lets your agent read your materials and plan a presentation outline with a story arc.

    Ready to connect★ 198

    github.com/hiyeshu/codeck198 stars

    View details
  • codeck-reviewSkillDocs & knowledge

    Lets your agent visually review rendered slide decks and fix issues in the HTML or CSS.

    Ready to connect★ 198

    github.com/hiyeshu/codeck198 stars

    View details
  • codeck-speechSkillMedia

    Lets your agent turn slide deck content into a ready-to-read speech transcript with stage directions.

    Ready to connect★ 198

    github.com/hiyeshu/codeck198 stars

    View details
  • content-ledgerSkillDev tools

    Lets your agent check which content already exists, reserve new content IDs, and record publishing history.

    Ready to connect★ 160

    github.com/manor-os/manor-ai198 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