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: AI & models

9,019 results · page 153 of 301

  • claude-code-hooksSkillAI & models

    Expert in Claude Code hooks - user-defined shell commands that execute at specific points in Claude Code's lifecycle. Provides guaranteed automation that doesn't rely on the LLM "remembering" to do something. Essential for enterprise workflows, code quality enforcement, and deterministic behavior in

    Ready to connect★ 147

    github.com/omer-metin/skills-for-antigravity139 stars

    View details
  • control-systemsSkillAI & models

    Patterns for feedback control systems including PID tuning, state-space control, Model Predictive Control (MPC), trajectory tracking, and stability analysis. Covers both classical and modern control approaches for robotics and automation. Use when ", " mentioned.

    Ready to connect★ 147

    github.com/omer-metin/skills-for-antigravity139 stars

    View details
  • upgrade-piSkillAI & models

    升级pi-agent-core和pi-ai到最新版本

    Ready to connect★ 147

    github.com/maotoumao/cebian135 stars

    View details
  • avalon-8-10pSkillAI & models

    Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • dispatching-parallel-agentsSkillAI & models

    The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every resul

    Ready to connect★ 145

    github.com/arbiterforge/codearbiter145 stars

    View details
  • graphviz.causal_kg_styleSkillAI & models

    Represent a causal knowledge graph in Graphviz DOT format following visual conventions for causal inference

    Ready to connect★ 145

    github.com/causify-ai/helpers145 stars

    View details
  • knowledge-baseSkillAI & models

    Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • nexus-configurationSkillAI & models

    Read, plan, confirm, and verify product configurations in the current Nexus private chat or Room that the caller is authorized to manage, including Agent, Room, Provider, preferences, Channel, Connector, Skill, Session, model, tool, and MCP settings.

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • nexus-managerSkillAI & models

    Query or manage platform resources within the owner scope on behalf of the Nexus main agent, including users, Agents, DM/Rooms, conversations, Sessions, other Agents' workspaces, and Skills. Product configuration, Goals, Executions, and Automations use their own dedicated Skills and do not go throug

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • nexus-product-guideSkillAI & models

    Explain current Nexus product features, entry locations, ordinary usage, visible results, and current limits. Use when a user asks what Nexus can do, where a feature is, how to use it, which feature to choose, or says they do not know how to start. Covers conversations, Agents, Rooms, Goals, work gr

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • pixi-vn-charactersSkillAI & models

    Use when defining visual novel characters for a @drincs/pixi-vn game — creating a character with a name, color, icon and other props, registering it so it can be looked up by id, and referencing it from dialogue/narration. Load this before writing any `CharacterBaseModel` or `RegisteredCharacters` c

    Ready to connect★ 145

    github.com/drincs-productions/pixi-vn141 stars

    View details
  • werewolf-6pSkillAI & models

    Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.

    Ready to connect★ 145

    github.com/nexus-research-lab/nexus143 stars

    View details
  • agent-canvas-environmentSkillAI & models

    Work effectively inside a local Agent Canvas environment, including local agent-server auth, frontend/backend port discovery, safe workspace hygiene, and delegating work to a new local conversation through POST /api/conversations.

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • agent-readiness-reportSkillAI & models

    Evaluate how well a codebase supports autonomous AI-assisted development. Analyzes repositories across five pillars (Agent Instructions, Feedback Loops, Workflows & Automation, Policy & Governance, Build & Dev Environment) covering 74 features. Use when users want to assess how agent-ready a reposit

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • agent-sdk-builderSkillAI & models

    Guided workflow for building custom AI agents using the OpenHands Software Agent SDK. Use when you want to create a new agent through an interactive interview process that gathers requirements and generates implementation plans.

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • competitor-researchSkillAI & models

    Research 3–5 competitors for any product or feature. Returns positioning, pricing, key differentiators, and gaps. Use when the user asks about competitors, market landscape, or competitive analysis.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • content-repurposerSkillAI & models

    Turn one long-form piece into 5 platform-specific formats. Use when the user has an article, post, or talk and wants to distribute it across channels without rewriting everything from scratch.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • dart-test-coverageSkillAI & models

    Understand and improve test coverage in a Dart package. Helps agents run coverage, interpret results, and identify missed lines.

    Ready to connect★ 144

    github.com/kevmoo/dash_skills144 stars

    View details
  • feature-prioritizerSkillAI & models

    Score a feature list using RICE (Reach, Impact, Confidence, Effort) and return a ranked table with recommendation. Use when the user wants to prioritize features, decide what to build next, or cut scope.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • improve-agent-readinessSkillAI & models

    Use an agent readiness report to identify and implement improvements that make a repository more agent-friendly. Proposes repo-appropriate fixes for each pillar, then implements them on request. Use after running a readiness report or when a user wants to improve their repo's AI-readiness.

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • industrial-brutalist-uiSkillAI & models

    Lets your agent generate web UIs in an industrial brutalist style instead of generic designs.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • iterateSkillAI & models

    Iterate on a GitHub pull request — drive it through CI, code review, and QA until it is merge-ready. Poll verification layers with `gh` CLI, diagnose and fix CI failures, address review feedback, retry flaky checks, push fixes, and repeat. The agent is the orchestration loop.

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • karpathy-reviewSkillAI & models

    Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship. Use when the user wants a sanity check on code, a plan, or a feature spec.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • linkedin-postSkillAI & models

    Write a LinkedIn post from a topic, idea, or article URL. Matches the user's voice with a strong hook, punchy body, and clear CTA. Use when the user wants to post on LinkedIn or turn something into a LinkedIn post.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • minimalist-uiSkillAI & models

    Guides your agent to write cleaner, less generic user interface code and designs.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • newsletter-ideatorSkillAI & models

    Generate 5–7 unique angles for a newsletter issue using SCAMPER and contrarian frameworks. Use when the user wants newsletter topic ideas, doesn't know what to write about, or wants fresh angles on a subject.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • npmSkillAI & models

    Handle npm package installation in non-interactive environments by piping confirmations. Use when installing Node.js packages that require user confirmation prompts.

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • okr-writerSkillAI & models

    Turn a goal statement into well-formed OKRs — 3 Objectives each with 3 measurable Key Results. Use when the user wants to write OKRs, quarterly goals, or structured targets for their team.

    Ready to connect★ 144

    github.com/hamzafarooq/claude-code-starter139 stars

    View details
  • openhands-apiSkillAI & models

    Reference skill for the OpenHands Cloud REST API (V1) and agent-server APIs, including how to start additional cloud or local backend conversations for fresh-context or delegated work.

    Ready to connect★ 144

    github.com/openhands/extensions141 stars

    View details
  • openhands-enterprise-troubleshootingSkillAI & models

    This skill should be used when a user reports an issue with OpenHands Enterprise (OHE) on a self-hosted (Replicated VM-based) installation. Use for diagnosing sandbox startup failures, auth issues, certificate errors, LLM connectivity problems, Keycloak login issues, Replicated Admin Console access,

    Ready to connect★ 144

    github.com/openhands/extensions141 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