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

8,898 results · page 288 of 297

  • skill-atlasSkillAI & models

    Graph, categorize and visualize the installed Claude Code skill collection. Use when the user wants to map, audit or categorize their skills, move skills into the searchable tier, or asks which skills are broken, dangling, dead, disabled or duplicated — and for any mention of the skill atlas, skill

    Ready to connect

    github.com/daniellublinsky/skill-atlas23 stars

    View details
  • smart-suggestionsSkillAI & models

    Skill for intelligent next-action suggestions. Analyzes the current pipeline state, artifacts produced, pending items, and project context to suggest the most relevant next action to the user. Triggered by: "o que fazer agora", "sugestao", "suggest", "proximo passo", "next", "what now", "me ajuda a

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • sota-identity-accessSkillAI & models

    State-of-the-art identity and access management engineering (2026) for BUILDING/configuring identity infrastructure AND AUDITING it — federation, IdPs, authorization models, the joiner-mover-leaver lifecycle, privileged/break-glass access, workload identity, MFA/passkeys, and assurance levels; audit

    Ready to connect

    github.com/martinholovsky/sota-skills23 stars

    View details
  • sota-jvmSkillAI & models

    State-of-the-art JVM engineering rules (2026 baseline) for Java and Kotlin that Claude applies when writing or auditing JVM code. Baseline Java 25 LTS (virtual threads final since 21; structured concurrency still preview), Kotlin 2.x. Covers modern idioms (records, sealed types, pattern matching, Ko

    Ready to connect

    github.com/martinholovsky/sota-skills23 stars

    View details
  • sota-llm-engineeringSkillAI & models

    State-of-the-art LLM application engineering rules (mid-2026 baseline) for BUILDING and AUDITING LLM-powered features. Claude should use this skill whenever it is building, modifying, or reviewing anything that calls a language model — chat features, RAG pipelines, agents and tool use, structured ex

    Ready to connect

    github.com/martinholovsky/sota-skills23 stars

    View details
  • sota-sandboxingSkillAI & models

    State-of-the-art sandboxing and isolation engineering (2026). Use when designing isolation for untrusted code, untrusted input parsing, multi-tenant workloads, or AI/agent execution — and when auditing existing systems for isolation gaps. Covers least privilege, defense in depth, isolation boundary

    Ready to connect

    github.com/martinholovsky/sota-skills23 stars

    View details
  • step11-packagerSkillAI & models

    Build complete manual Step 11 refinement prompts for Claude-Fable/Opus or OpenRouter Fusion per-pair use from step10+step11 output with full personality YAML, Suno construction rules, and production mandates.

    Ready to connect

    github.com/localsymmetry/lofn23 stars

    View details
  • sweepsSkillAI & models

    Apply when running, resuming, ticking, adding or retiring a repo-wide sweep or its ledger, or when deciding whether a mechanical pass needs one. Esposter repo-wide sweep conventions — progress as a ledger in .agents/ledgers/ named after the owning skill, a find recipe proven able to fail, one behavi

    Ready to connect

    github.com/esposter/esposter23 stars

    View details
  • tdd-engineerSkillAI & models

    Test-Driven Development with red-green-refactor enforced. Use when building a feature or bug fix using TDD, mentioning "red-green-refactor", wanting tracer bullets, or requesting test-first development. Combats the "horizontal slicing" anti-pattern (writing all tests before all the implementat

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • testpoint-plannerSkillAI & models

    RAG-backed. Measure and improve explicit standalone-pad testpoint coverage through a guarded DipTrace PCB transaction. Use when the user says “Plan guarded fixture testpoints for these PCB nets.”

    Ready to connect

    github.com/fireostendere/mcp_diptrace22 stars

    View details
  • ui-polishSkillAI & models

    Interface polish skill — the small details that make a UI feel refined instead of "ok". Use when building components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, or any visual detail work. Trigger words: "polish", "deixar mais ref

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • unreal-best-practicesSkillAI & models

    Comprehensive best practices guide for modern Unreal Engine 5.x development. Covers Epic's strategic direction toward modern systems (GAS, Enhanced Input, StateTree, MetaSounds, Niagara, PCG, CommonUI, World Partition, Game Feature Plugins, Gameplay Tags), the "research first" philosophy of always c

    Ready to connect

    github.com/maystudios/claude-skills23 stars

    View details
  • unreal-pcg-pythonSkillAI & models

    Guide for Unreal Engine 5.x PCG (Procedural Content Generation) Python integration. Covers the PCGPythonInterop plugin, the Execute Python Script node, PCG Python API (PCGComponent, PCGBlueprintElement, PCGSpatialData, PCGPointData), editor automation, custom PCG nodes via Python, and known limitati

    Ready to connect

    github.com/maystudios/claude-skills23 stars

    View details
  • unreal-thirdpartySkillAI & models

    Expert guide for integrating third-party C/C++ libraries into Unreal Engine 5.x projects and plugins. Covers static linking, dynamic linking (DLL/SO/dylib), Build.cs configuration, ModuleType.External, delay loading, runtime dependency staging, wrapping patterns, cross-platform considerations (Windo

    Ready to connect

    github.com/maystudios/claude-skills23 stars

    View details
  • ux-researchSkillAI & models

    Qualitative UX Research / Discovery skill — user interviews, research-based persona creation, journey mapping, qualitative usability testing, information architecture, card sorting, and problem validation before specification. Precedes the PO (01) and UI/UX (02): ent

    Ready to connect

    github.com/felvieira/claude-skills-fv23 stars

    View details
  • word-countSkillAI & models

    Counts the words and characters of a given text and generates a JSON artifact

    Ready to connect

    github.com/yrris/pro-agent23 stars

    View details
  • a11ySkillAI & models

    Frontend accessibility audit (WCAG): semantic HTML, keyboard access, focus management, contrast, ARIA, screen readers. Use when building or changing UI, or before shipping a user-facing screen.

    Ready to connect

    github.com/byerlikaya/claude-starter-kit22 stars

    View details
  • a11y-engineeringSkillAI & models

    Deep accessibility engineering beyond automated tooling — focus management architecture, ARIA role correctness under dynamic mutation, live-region discipline, keyboard contract specification, and manual WCAG 2.2 AA verification for the two criteria automated tools miss. Triggers on "audit this surfa

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • academy-learnSkillAI & models

    Use when the user wants to be taught an Anthropic product or feature - "teach me Claude Code", "learn Cowork", "academy lesson", "train me on MCP or the Claude API", "quiz me", "next lesson" - or asks for structured learning rather than a one-off answer. Covers Claude Code, Claude.ai, Cowork, Tag, P

    Ready to connect

    github.com/mrmarudi/academy-coach22 stars

    View details
  • academy-reviewSkillAI & models

    Use when the user wants their way of working with Claude assessed — "review my session", "how am I using Claude Code", "audit my setup / workflow", "am I following best practices", "coach me", "what should I improve" — or pastes a Claude.ai/Cowork/Tag transcript and asks how they could have worked b

    Ready to connect

    github.com/mrmarudi/academy-coach22 stars

    View details
  • adapt-to-projectSkillAI & models

    Use this skill to diagnose and improve an adopter repository's agent guidance or to walk through the four classes of post-install change (substitution, .upstream companion merges, discovery + restructuring, within-layout consolidation). Repository anchoring is marker-independent and read-only by def

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • adrSkillAI & models

    Architecture Decision Record: context-decision-consequences, for decisions that are expensive to reverse. Written under docs/adr/.

    Ready to connect

    github.com/byerlikaya/claude-starter-kit22 stars

    View details
  • apply-conventionsSkillAI & models

    Use when writing or reviewing PlayCanvas Engine code involving entity transforms, cameras, physics, materials, model orientation, bounds, or imports to apply the Engine's coordinate and API conventions.

    Ready to connect

    github.com/playcanvas/skills22 stars

    View details
  • architect-assessSkillAI & models

    Use when the user wants to understand, assess, harden, optimize, scale, modernize, rationalize, replace, or plan action for the architecture that exists in a repository or implemented system. Routes the generic request "assess architecture and provide an action plan" here. Builds a correctable curre

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • architecture-lenses-referenceSkillAI & models

    Route into the compiled OKF bundle `architecture-lenses` using generated indexes.

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • arxiv-fetchSkillAI & models

    Fetch the latest arXiv papers and generate an on-demand digest. Use when the user asks to fetch/check today's (or the latest) arXiv papers, find new papers on a topic, or generate an ad-hoc arXiv digest. The agent judges relevance itself — no API keys needed.

    Ready to connect

    github.com/yang3kc/daily_arxiv_digest22 stars

    View details
  • assemble-sceneSkillAI & models

    Use when composing PlayCanvas Engine, React, or Web Components gameplay entities, model hierarchies, colliders, or physics objects to create one semantic root per object with calibrated visuals and predictable lifecycle ownership.

    Ready to connect

    github.com/playcanvas/skills22 stars

    View details
  • assimilate-primitiveSkillAI & models

    Use to bring a single external agent primitive — one skill, subagent, hook, or command (or a small connected bundle) — from a local path or URL into this catalogue. Fetches it, diagnoses the destination pack and lifecycle from the local charter, and migrates it to pack convention, or rejects it with

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • assimilate-repoSkillAI & models

    Use to survey a whole external repo or catalogue (local path or URL) for ingestion candidates and produce a reviewable RFC of per-candidate verdicts (assimilate, reject, or needs-new-pack), resumable across sessions and git worktrees via a ledger. Triggers on "survey this repo for skills we can adop

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 stars

    View details
  • author-briefSkillAI & models

    Deprecated compatibility alias for author-delivery-brief create. Use only when an older caller explicitly invokes author-brief.

    Ready to connect

    github.com/eugenelim/agent-ready-repo22 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.

53,789 of the 54,221 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