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: Productivity

2,599 results · page 16 of 87

  • cao-agent-routingSkillProductivity

    Find and select the best installed CAO agent profile for a task before

    Ready to connect★ 1k

    github.com/awslabs/cli-agent-orchestrator1k stars

    View details
  • cao-learningSkillProductivity

    Report task outcomes and distill lessons so the team improves across

    Ready to connect★ 1k

    github.com/awslabs/cli-agent-orchestrator1k stars

    View details
  • cao-worker-protocolsSkillProductivity

    Worker-side callback and completion rules for assigned and handed-off tasks in CAO

    Ready to connect★ 1k

    github.com/awslabs/cli-agent-orchestrator1k stars

    View details
  • open-agent-teamsSkillProductivity

    Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or w

    Ready to connect★ 1k

    github.com/ai-builder-club/skills1k stars

    View details
  • hns-moaiadk-dev-referenceSkillProductivity

    moai-adk-go local dev reference — version management/release process (sec 5), shell-script hook development (sec 7), build & dev commands (sec 10). Load only when performing these specific tasks.

    Ready to connect★ 1k

    github.com/modu-ai/moai-adk1k stars

    View details
  • moaiSkillProductivity

    MoAI unified orchestrator for autonomous development. Routes natural language or subcommands (plan, run, sync, project, fix, loop, mx, feedback, review, clean, codemaps, gate, e2e, harness, goal, todo) to specialized agents.

    Ready to connect★ 1k

    github.com/modu-ai/moai-adk1k stars

    View details
  • dart-new-taskSkillProductivity

    DART New Task: start a feature, bugfix, refactor, docs, build, or test task

    Ready to connect★ 1k

    github.com/dartsim/dart1k stars

    View details
  • dart-nextSkillProductivity

    DART Next: choose the next bounded DART task from plans, issues, and CI, then route it

    Ready to connect★ 1k

    github.com/dartsim/dart1k stars

    View details
  • dart-retroSkillProductivity

    DART Retro: improve the AI harness from successful or unsatisfactory task outcomes

    Ready to connect★ 1k

    github.com/dartsim/dart1k stars

    View details
  • dart-ultraworkSkillProductivity

    DART Ultrawork: kick off a large or autonomous DART task with project-home docs, an optional decision interview, and orchestrated execution

    Ready to connect★ 1k

    github.com/dartsim/dart1k stars

    View details
  • inbound-lead-enrichmentSkillProductivity

    Fills in missing data for inbound leads — researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and updates the lead record. Produces enriched lead data ready for qualification or outreach. Tool-agnostic.

    Ready to connect★ 1k

    github.com/gooseworks-ai/goose-skills1k stars

    View details
  • skillpack-creatorSkillProductivity

    Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with `skillpack.json`, local skills under `skills/`, starter prompts, start scripts, and an optional zip pac

    Ready to connect★ 1k

    github.com/creminiai/skillpack1k stars

    View details
  • closed-loopSkillProductivity

    Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop,

    Ready to connect★ 1k

    github.com/huytieu/cog-second-brain1k stars

    View details
  • create-user-storySkillProductivity

    Create user stories with duplicate checking across any project tracker (Linear, GitHub Issues, Jira)

    Ready to connect★ 1k

    github.com/huytieu/cog-second-brain1k stars

    View details
  • editorial-illustrationsSkillProductivity

    Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent. This is a GENERATIVE GUIDE, not a template gallery: it teaches the "claim -> geometry" method so any

    Ready to connect★ 1k

    github.com/huytieu/cog-second-brain1k stars

    View details
  • establishing-project-contextSkillProductivity

    Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

    Ready to connect★ 1k

    github.com/ganyuanran/aegis1k stars

    View details
  • executing-plansSkillProductivity

    Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.

    Ready to connect★ 1k

    github.com/ganyuanran/aegis1k stars

    View details
  • finishing-a-development-branchSkillProductivity

    Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.

    Ready to connect★ 1k

    github.com/ganyuanran/aegis1k stars

    View details
  • goal-framingSkillProductivity

    Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

    Ready to connect★ 1k

    github.com/ganyuanran/aegis1k stars

    View details
  • long-task-continuationSkillProductivity

    Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

    Ready to connect★ 1k

    github.com/ganyuanran/aegis1k stars

    View details
  • using-git-worktreesSkillProductivity

    Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.

    Ready to connect★ 1k

    github.com/ganyuanran/aegis1k stars

    View details
  • taiwanmd-nodeSkillProductivity

    Turns this machine into a Taiwan.md split-soul node (contributor node) — wakes up once a day, picks one task from the existing ticket sources and completes it (translation gaps / broken links / formatting / metadata), and submits the result back to the main repo via PR; merging is always left to hum

    Ready to connect★ 1k

    github.com/frank890417/taiwan-md1k stars

    View details
  • twmd-nodeSkillProductivity

    Contributor node — a Taiwan.md cron that runs on a contributor's own machine: it picks one task from existing ticket sources in the repo (translation gaps / broken links / formatting / en metadata / ARTICLE-INBOX), completes it, and submits a PR to the main repo. Output always ends at the PR; mergin

    Ready to connect★ 1k

    github.com/frank890417/taiwan-md1k stars

    View details
  • twmd-routineSkillProductivity

    Routine flywheel management — reads ROUTINE.md as the SSOT, then makes the corresponding changes or adds routine tasks (cadence / skill / quality gate / escalation / mirror sync). TRIGGER when: user says "排 routine", "改 routine", "新增 routine", "調整 cron", "更新 quality gate", "routine 飛輪", "routine SSO

    Ready to connect★ 1k

    github.com/frank890417/taiwan-md1k stars

    View details
  • linear-backlogSkillProductivity

    Run a scoped Linear backlog autonomously as a sequence of maximal safe parallel batches by composing orchestrator, autogoal, and task. Use when the user wants Codex to execute ordered Linear issues without prompting for each next batch while parallelizing every dependency-ready ticket that lacks a h

    Ready to connect★ 1k

    github.com/udecode/dotai1k stars

    View details
  • console-commandsSkillProductivity

    Reference for OrangeHRM's two Symfony Console entry points — `bin/console` (production console, lightweight, plugin-registered commands like `cache:clear` / `orm:generate-proxies` / `orangehrm:run-schedule`) and `devTools/core/console.php` (developer-only with its own `composer.json`, registers comm

    Ready to connect★ 1k

    github.com/orangehrm/orangehrm1k stars

    View details
  • scheduled-jobsSkillProductivity

    Reference for OrangeHRM's task scheduling — the `orangehrm:run-schedule` command that operators run from system cron (every minute), the `SchedulerConfigurationInterface` that plugins implement to register tasks at framework boot, the `Schedule` / `Task` / `CommandInfo` value objects (Task extends `

    Ready to connect★ 1k

    github.com/orangehrm/orangehrm1k stars

    View details
  • hep-cloudSkillProductivity

    Staff a task only from the signed-in owner's Agent Cloud agents.

    Ready to connect★ 1k

    github.com/agentlas-ai/agentlas-os1k stars

    View details
  • hep-hubSkillProductivity

    Staff a task only from public Agentlas Hub agents.

    Ready to connect★ 1k

    github.com/agentlas-ai/agentlas-os1k stars

    View details
  • hep-localSkillProductivity

    Staff a task only from Agentlas agents registered on this machine.

    Ready to connect★ 1k

    github.com/agentlas-ai/agentlas-os1k 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.

52,524 of the 52,958 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