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

9,017 results · page 275 of 301

  • sniper-checkSkillAI & models

    Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.

    Ready to connect

    github.com/fusengine/agents28 stars

    View details
  • streaming-llm-responsesSkillAI & models

    Implement real-time streaming UI patterns for AI chat applications. Use when adding response lifecycle handlers, progress indicators, client effects, or thread state synchronization. Covers onResponseStart/End, onEffect, ProgressUpdateEvent, and client tools. NOT when building basic chat without rea

    Ready to connect

    github.com/mjunaidca/mjs-agent-skills28 stars

    View details
  • styling-with-shadcnSkillAI & models

    Build beautiful, accessible UIs with shadcn/ui components in Next.js. Use when creating forms, dialogs, tables, sidebars, or any UI components. Covers installation, component patterns, react-hook-form + Zod validation, and dark mode setup. NOT when building non-React applications or using different

    Ready to connect

    github.com/mjunaidca/mjs-agent-skills28 stars

    View details
  • swift-concurrency-6-2SkillAI & models

    Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types.

    Ready to connect

    github.com/georgekhananaev/claude-skills-vault28 stars

    View details
  • temporary_waiver_auditSkillAI & models

    PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

    Ready to connect

    github.com/gen-verse/past-bench28 stars

    View details
  • token-optimizerSkillAI & models

    Reduce token count in prompts, docs, and prose. Covers prompt compression (40-60% savings), doc formatting, TOON data serialization, and Strunk's prose clarity rules. Use when compressing prompts, optimizing docs for LLM context, or writing clear technical prose.

    Ready to connect

    github.com/georgekhananaev/claude-skills-vault28 stars

    View details
  • tool-creationSkillAI & models

    Create custom tools with defineTool() or tool(), register them with the agent, and configure required-tools gates and per-tool call budgets.

    Ready to connect

    github.com/tylerjrbuell/reactive-agents-ts25 stars

    View details
  • ui-integrationSkillAI & models

    Wire agents into React, Vue, and Svelte frontends with streaming hooks, and set up server-side Next.js App Router or Express API routes using AgentStream.toSSE().

    Ready to connect

    github.com/tylerjrbuell/reactive-agents-ts25 stars

    View details
  • upgrade-packages-jsSkillAI & models

    Safely upgrade JavaScript packages with breaking change detection, migration guidance, and automated code migrations (npm/pnpm/yarn). Cross-platform with git safety branch enforcement.

    Ready to connect

    github.com/georgekhananaev/claude-skills-vault28 stars

    View details
  • ux-evaluatorSkillAI & models

    This skill should be used when evaluating UI components against UX best practices. Use for reviewing buttons, navigation elements, spacing, visual hierarchy, or any interface element. Provides a systematic 3-dimension framework (Position, Visual Weight, Spacing) aligned with industry standards (Bals

    Ready to connect

    github.com/mjunaidca/mjs-agent-skills28 stars

    View details
  • validate-buildSkillAI & models

    Validate a completed package against its spec. Checks patterns, types, exports, dependencies, and test coverage after building a package.

    Ready to connect

    github.com/tylerjrbuell/reactive-agents-ts25 stars

    View details
  • web-qualitySkillAI & models

    Web quality optimization skills based on Google Lighthouse guidelines and Core Web Vitals. Use when asked to audit web quality, optimize performance, improve accessibility, fix SEO, apply best practices, or analyze Core Web Vitals (LCP, INP, CLS).

    Ready to connect

    github.com/georgekhananaev/claude-skills-vault28 stars

    View details
  • worker-routingSkillAI & models

    Decide and execute native Codex worker delegation for the main coordinating agent. Use it for a substantial investigation, implementation, fix, or verification responsibility that can be handed over whole, and for continuing or reworking the same worker; a temporary worker, an explicit solo request,

    Ready to connect

    github.com/indeliblevivi/codex-worker-routing28 stars

    View details
  • advanced-nluSkillAI & models

    A skill for understanding the nuances of human language including pragmatics, irony, sarcasm, and humor. Covers syntactic parsing, semantic analysis, named entity recognition, sentiment analysis, coreference resolution, discourse analysis, and pragmatic inference.

    Ready to connect

    github.com/leeex1/quillan-ronin27 stars

    View details
  • adviseSkillAI & models

    Ask Claude Code a read-only question from Codex through the sandbox-external bridge.

    Ready to connect

    github.com/borda/ai-rig27 stars

    View details
  • agent-instructionsSkillAI & models

    Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and keeping them accurate as the project changes.

    Ready to connect

    github.com/nimadorostkar/claude-skills-collection27 stars

    View details
  • agent-reasoning-mcpSkillAI & models

    Teaches the agent to use the Strategic Agent Reasoning MCP server for BDI goals, utility scoring, risk evaluation, and replanning.

    Ready to connect

    github.com/putervision/world-model-mcp27 stars

    View details
  • agent-shimsSkillAI & models

    Safely manage Codex Rig role-agent shims: doctor, status, install, or remove; one action only.

    Ready to connect

    github.com/borda/ai-rig27 stars

    View details
  • bug-fix-protocolSkillAI & models

    Use when fixing a reported bug end to end. Enforces a disciplined sequence — reproduce, write a failing test, fix minimally, verify, prevent recurrence — and blocks the common failure mode of patching symptoms.

    Ready to connect

    github.com/nimadorostkar/claude-skills-collection27 stars

    View details
  • busic-skills-maintenanceSkillAI & models

    BuSic Skills maintenance guidelines. Used when maintaining and refactoring .agents/skills to standardize directory structure, templates, update timing, self-check procedures, and the boundary of responsibilities with docs.

    Ready to connect

    github.com/glowled/busic26 stars

    View details
  • c2-operateSkillAI & models

    Operate and debug the DNS C2 system non-interactively. This skill should be used when Claude needs to launch an exploit, send commands to a compromised session and collect output, diagnose why a payload is not calling home, or inspect C2 server state. Triggers on requests like "run the exploit", "se

    Ready to connect

    github.com/beyondtrust/pwning-agentcore-code-interpreter27 stars

    View details
  • cloud-architectureSkillAI & models

    Use when designing cloud infrastructure. Covers network topology, identity and least privilege, multi-AZ and multi-region trade-offs, managed versus self-hosted decisions, and designing for cost.

    Ready to connect

    github.com/nimadorostkar/claude-skills-collection27 stars

    View details
  • code-mapperSkillAI & models

    Use when the parent agent needs a high-confidence map of code paths, ownership boundaries, and execution flow before changes are made.

    Ready to connect

    github.com/jshsakura/awesome-opencode-skills26 stars

    View details
  • cppSkillAI & models

    Use when writing modern C++ (17/20/23). Covers RAII, smart-pointer ownership, move semantics, ranges, concepts, and eliminating undefined behavior with sanitizers.

    Ready to connect

    github.com/nimadorostkar/claude-skills-collection27 stars

    View details
  • csharp-dotnetSkillAI & models

    Use when building on .NET 8+ with C# 12. Covers nullable reference types, records, async/await correctness, minimal APIs, dependency injection, and EF Core query performance.

    Ready to connect

    github.com/nimadorostkar/claude-skills-collection27 stars

    View details
  • cut-release-prSkillAI & models

    Cut a Plumber release PR that merges `develop-v2` into `production`. Prompts the user to choose the version bump (patch / minor / major), bumps the version across the root workspace and every package via `npm version`, creates a single conventional `vX.Y.Z` commit + git tag locally, and prepares (or

    Ready to connect

    github.com/opengovsg/plumber27 stars

    View details
  • data-modelingSkillAI & models

    Use when designing a schema. Covers normalization and when to break it, choosing keys, modeling time and history, soft deletes, multi-tenancy, and schema decisions that are expensive to reverse.

    Ready to connect

    github.com/nimadorostkar/claude-skills-collection27 stars

    View details
  • datarobot-feature-engineeringSkillAI & models

    Guidance for feature engineering, feature discovery, feature importance analysis, and understanding DataRobot's automated feature engineering capabilities. Use when working with feature engineering, feature discovery, or analyzing feature importance in DataRobot.

    Ready to connect

    github.com/datarobot-oss/datarobot-agent-skills27 stars

    View details
  • datarobot-model-explainabilitySkillAI & models

    Tools and guidance for model explainability, prediction explanations, feature impact analysis, SHAP values, SHAP distributions, anomaly assessment, and model diagnostics. Use when analyzing model explanations, feature impact, SHAP values, SHAP distributions, anomaly assessment, or diagnosing model b

    Ready to connect

    github.com/datarobot-oss/datarobot-agent-skills27 stars

    View details
  • datarobot-model-trainingSkillAI & models

    Comprehensive guidance for training models in DataRobot, including project creation, AutoML configuration, feature engineering, and model selection. Use when training models, creating AutoML projects, or selecting models in DataRobot.

    Ready to connect

    github.com/datarobot-oss/datarobot-agent-skills27 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.

55,004 of the 55,435 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