ahel is live on Product Hunt today. Upvote

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

8,868 results · page 91 of 296

  • seo-auditSkillAI & models

    How to present the deterministic AI-SEO audit returned by audit_page. Use when reporting a page's readability and citation-readiness for AI answer engines (ChatGPT, Claude, Perplexity).

    Ready to connect★ 462

    github.com/shadcn-labs/agentcn453 stars

    View details
  • add-llm-provider-or-modelSkillAI & models

    Add a new LLM model to the preset catalog, or a whole new LLM provider — with the mandatory pre-flight verification of model id, pricing, and context window against the provider's official docs. Use when asked to add/update LLM models, providers, or pricing.

    Ready to connect★ 455

    github.com/bagofwords1/bagofwords453 stars

    View details
  • geo-pipelineSkillAI & models

    Entry point + orchestrator for the recomby-geo GEO (Generative Engine Optimization) workflow on OpenAI Codex CLI. Use when the user wants to run any stage of the GEO pipeline on a client folder — intake, visibility audit, content-gap analysis, content brief, draft production, distribution, or monthl

    Ready to connect★ 454

    github.com/viryazheng/recomby-geo455 stars

    View details
  • readme-showcaseSkillAI & models

    Build or refresh a product README showcase using a seeded Bag of Words workspace, polished in-product screenshots, and repository-ready visual assets. Use when positioning has changed, README screenshots are stale, a launch/demo workspace is needed, or the user asks to populate agents, reports, dash

    Ready to connect★ 455

    github.com/bagofwords1/bagofwords453 stars

    View details
  • skill-debriefSkillAI & models

    Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into the skill. Use whenever the user says: "debrief the X skill", "let's debrief X", "retrospective on X", "feedback on X skill", "improve the X skill", "update the X skill", "let's re

    Ready to connect★ 454

    github.com/computerlovetech/agr454 stars

    View details
  • api2cliSkillAI & models

    Generate a working CLI from any API, then wrap it in a Claude Code skill. Point it at API docs, a live URL, or a peek-api capture and get a dual-mode Commander.js CLI (human + agent output) plus a ready-to-use skill folder. Use when user wants to wrap an API in a CLI, generate a CLI from API docs, t

    Ready to connect★ 451

    github.com/alexknowshtml/api2cli452 stars

    View details
  • swift-testing-expertSkillAI & models

    Expert guidance for Swift Testing: test structure, #expect/#require macros, traits and tags, parameterized tests, test plans, parallel execution, async waiting patterns, and XCTest migration. Use when writing new Swift tests, modernizing XCTest suites, debugging flaky tests, or improving test qualit

    Ready to connect★ 452

    github.com/avdlee/swift-testing-agent-skill452 stars

    View details
  • dive-into-langgraphSkillAI & models

    A comprehensive guide and reference for building agents using LangGraph 1.0, including ReAct agents, state graphs, and tool integrations.

    Ready to connect★ 450

    github.com/luochang212/dive-into-langgraph450 stars

    View details
  • avoid-feature-creepSkillAI & models

    Prevent feature creep when building software, apps, and AI-powered products. Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says "just one more feature." Helps developers and AI agents stay focused, ship faster, and avoid bloated products.

    Ready to connect★ 447

    github.com/udecode/kitcn446 stars

    View details
  • convex-release-auditSkillAI & models

    Audit newer Convex npm releases against kitcn. Use when checking whether a newer `convex` version unlocks kitcn improvements, compatibility work, CLI/agent workflows, or cleanup of local Convex hacks. Reads `https://ship.convex.dev/`, the upstream Convex changelog, and GitHub diffs before delegating

    Ready to connect★ 447

    github.com/udecode/kitcn446 stars

    View details
  • package-release-auditSkillAI & models

    Audit newer npm package releases against kitcn. Use when checking whether a newer dependency version unlocks kitcn improvements, compatibility work, CLI/agent workflows, or cleanup of local package-specific hacks. Reads package changelogs, GitHub releases, upstream diffs, and local kitcn usage befor

    Ready to connect★ 447

    github.com/udecode/kitcn446 stars

    View details
  • llm-councilSkillAI & models

    Multi-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models (ChatGPT, Gemini, other LLMs) before presenting an implementation plan, or asks to "consult the council", "ask other models", or "get perspectives from other AIs". Queries exter

    Ready to connect★ 442

    github.com/gcpdev/llm-council-skill443 stars

    View details
  • resolve-issueSkillAI & models

    Resolve a spec issue end-to-end using sequential subagents

    Ready to connect★ 442

    github.com/gittower/git-flow-next433 stars

    View details
  • 004-commands-installationSkillAI & models

    Use when you need to install the embedded project commands into command directories (.github/commands, .claude/commands, .cursor/command, .codex/commands), selecting the destination interactively and copying the embedded command definitions from project assets. This should trigger for requests such

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 005-agents-installationSkillAI & models

    Use when you need to install the embedded robot agents into .github/agents, .claude/agents, .cursor/agents, or .codex/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Boot

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 801-regulations-eu-ai-actSkillAI & models

    Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls;

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • 813-regulations-iso-42001SkillAI & models

    Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering

    Ready to connect★ 440

    github.com/jabrena/plinth440 stars

    View details
  • clean-arch-kmp-readinessSkillAI & models

    Lay out a Kotlin Multiplatform app in layers that actually hold — a domain module carrying interfaces and models, repository implementations kept internal to the data module, and one module per external integration so a breaking service cannot spread — plus how to verify each boundary with a grep in

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • compose-multiplatform-viewmodel-baseSkillAI & models

    A shared ViewModel base class for Compose Multiplatform — container-aware so subclasses can pull extra dependencies without constructor threading, with one loading/error surface for every screen — and the blocking resource-lookup hazard that such a base almost always grows. Use when every screen is

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • configureSkillAI & models

    Use after `/plugin install sponsio-claude-code` to wire the runtime end-to-end. The plugin install only registers hooks + skills; the contract library and per-environment overrides are configured here. Bootstraps the per-plugin contract library tree at ~/.sponsio/plugins/, installs bundled starter l

    Ready to connect★ 440

    github.com/sponsiolabs/sponsio440 stars

    View details
  • continuation-token-pagination-contractSkillAI & models

    Model an endpoint that returns a page plus a next-token as Flow<Resource<Pair<items, token?>>> — a null token means the end, the caller stores only the token, and a bounded prefetch primes the first pages before anything is shown. Use when wiring an opaque-cursor API into a repository, or when a lis

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • empty-sentinel-instanceSkillAI & models

    Give a model a canonical empty instance on its companion object so its holders can declare the field non-null, instead of threading a nullable through every layer. Covers when this genuinely removes a whole family of null checks and when it only adds a second check beside the one already there, the

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • hilt-to-koin-migrationSkillAI & models

    Move dependency injection from an annotation-processed compile-time framework (Hilt/Dagger) to the multiplatform runtime container (Koin) — the mechanical mapping for providers, view models and qualifiers, what happens to assisted injection, and the two failure modes the migration introduces: a grap

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • koin-viewmodel-scoping-trapsSkillAI & models

    Wiring view models through a runtime dependency-injection container without losing track of their lifetime — the service-locator base class and what it costs, annotation-based definitions that compile but register nothing, which store owner each accessor addresses and why that (not the accessor's sp

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • native-artifact-for-embeddingSkillAI & models

    Producing a native shared library a JVM app can actually load and ship — why a prebuilt portable bundle usually is not a loadable library at all, building on the oldest base system you support, run-path choice, which libraries to deliberately leave out of the bundle, and gating the build on a load-a

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • ntmSkillAI & models

    Operate selected NTM agent panes and inspect native state. Use when: persistent tmux roles are requested; pane liveness and prompt delivery are not validation.

    Ready to connect★ 436

    github.com/boshu2/agentops440 stars

    View details
  • pending-state-makes-waiting-legibleSkillAI & models

    Model "asked, and not yet answered" as its own field, because without it a rejected request and a peer who simply has not looked at their screen are indistinguishable — both look like nothing happened. Covers the one set against many clears, clearing locally when no answer will ever come, and giving

    Ready to connect★ 440

    github.com/maxrave-dev/kotlin-footguns439 stars

    View details
  • sponsioSkillAI & models

    Install, observe, tune, and enforce Sponsio: a runtime contract layer for LLM agents that blocks unsafe tool calls and scores output quality against declared rules. Use when the user wants to set up / add / install Sponsio, add guardrails or runtime safety to an LLM agent, generate or refine a spons

    Ready to connect★ 440

    github.com/sponsiolabs/sponsio440 stars

    View details
  • anthropic-artSkillAI & models

    Generate full-background editorial illustrations in Anthropic's hand-drawn visual language: warm or muted opaque color fields, irregular ivory carrier shapes, and bold black gestural linework. Use when the user asks for an Anthropic-style, Claude-style, hand-drawn AI editorial, newsroom, blog hero,

    Ready to connect★ 436

    github.com/halfai1102/anthropic-art398 stars

    View details
  • ops-publish-to-ametystSkillAI & models

    Publish local .claude skills/loops to Ametyst — verbatim, flattened, no brain rewrite; optional retire-local (MOVE originals to deprecated-skills/, never delete) makes Ametyst the source of truth.

    Ready to connect★ 436

    github.com/ratel-ai/ratel436 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.

53,585 of the 54,017 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