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

55,196 results · page 81 of 1,840

  • proSkillDocs & knowledge

    Adds self-improvement notes, session state summaries, and feedback tools to your agent's workflow.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • puaSkillCommunication

    Lets your agent give tough, motivational productivity coaching when you're stuck or repeatedly failing.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-cancel-loopSkillAI & models

    Lets your agent run a cancel-loop command alias inside Codex coding sessions.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-enSkillProductivity

    Makes your agent keep pushing through failed tasks with structured debugging instead of giving up.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-flavorSkillAI & models

    Lets your agent switch its Codex command style to a different prompt flavor using a short alias.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-jaSkillProductivity

    Makes your agent scold and push itself harder when debugging tasks fail or it tries to give up.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-kpiSkillAI & models

    Lets your agent run the pua-kpi command as an alias for Codex-style KPI prompts.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-loopSkillAI & models

    Guides your agent through iterative development loops with recurring checks, completion evidence, and pause or abort markers.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-mamaSkillAI & models

    Lets your agent run Codex subcommands through a short alias command.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-offSkillAI & models

    Lets your agent run the pua-off alias command in Codex the same way you would use /pua:off.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-offlineSkillAI & models

    Lets your agent run Codex commands offline using the $pua-offline alias.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-onSkillAI & models

    Lets your agent enable pua mode in Codex with the $pua-on command.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-p10SkillAI & models

    Lets your agent run the P10 prompt command from the PUA collection as a shortcut alias.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-p7SkillAI & models

    Lets your agent run the P7 prompt command from the PUA collection as a shortcut alias.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-p9SkillAI & models

    Lets your agent use the PUA P9 command alias to run Codex-style prompts inside Claude Code.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-proSkillAI & models

    Lets your agent use the pua-pro command alias to run Codex tasks from Claude Code.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-reap-orphansSkillAI & models

    Lets your agent run the reap-orphans cleanup command in Codex, mapping Claude Code style invocations.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-surveySkillAI & models

    Lets your agent run a survey-style prompt command through an alias in coding assistant tools.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-team-statusSkillAI & models

    Lets your agent check team status via a Codex subcommand alias.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-teardown-allSkillAI & models

    Lets your agent run a teardown command that removes PUA-related setup created for Codex sessions.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-traeSkillProductivity

    Lets your agent apply strict accountability prompts to itself when it keeps failing, gives up, or claims unfinished work is done.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • pua-yesSkillAI & models

    Lets your agent run the pua:yes command shortcut in Codex by typing $pua-yes.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • shotSkillAI & models

    Lets your agent use a compact prompt style guide to steer sub-agents toward evidence-first answers.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • yesSkillDev tools

    Lets your agent reply with emotional-support, encouraging feedback in a playful ENFP-style leadership tone.

    Ready to connect★ 20k

    github.com/tanweai/pua20k stars

    View details
  • notebooklmSkillSecurity

    Lets your agent create and manage Google NotebookLM notebooks, add sources, and generate artifacts like podcasts.

    Ready to connect★ 19k

    github.com/teng-lin/notebooklm-py13k stars

    View details
  • cranelift-auditorSkillDev tools

    Lets your agent audit the Cranelift compiler codebase to find bugs and miscompilations and write structured reports.

    Ready to connect★ 19k

    github.com/bytecodealliance/wasmtime19k stars

    View details
  • reduce-test-casesSkillDev tools

    Lets your agent shrink a failing Wasmtime/Cranelift test case down to the smallest input that still reproduces the bug.

    Ready to connect★ 19k

    github.com/bytecodealliance/wasmtime19k stars

    View details
  • wasmtime-auditorSkillSecurity

    Guides your agent to audit Wasmtime's code for undiscovered bugs and security vulnerabilities and write test-case-backed reports.

    Ready to connect★ 19k

    github.com/bytecodealliance/wasmtime19k stars

    View details
  • agent-sourcesSkillMonitoring & ops

    Lets your agent understand how ccusage reads agent logs, maps records to tokens and models, and computes costs.

    Ready to connect★ 19k

    github.com/ccusage/ccusage18k stars

    View details
  • cmux-debugSkillDev tools

    Lets your agent run a command in a real terminal pane and capture its rendered output to verify how it displays.

    Ready to connect★ 19k

    github.com/ccusage/ccusage18k 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.

54,764 of the 55,196 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