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 88 of 301

  • dev-autopilotSkillAI & models

    Full autonomous execution from idea to working code. Use when user says "autopilot", "autonomous", "build me", "create me", "make me", "full auto" — orchestrates spec → plan → code → QA → validation across the engineering layer agents.

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • dev-planSkillAI & models

    Strategic planning with optional interview workflow. Use when the user wants to plan before implementing — "plan this", "let's plan", structured requirements gathering for vague ideas. Pairs with @compass-planner agent. Supports consensus mode and review mode.

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • dev-verifySkillAI & models

    Verify that a change really works before claiming completion. Use when the user wants confidence that a feature, fix, or refactor actually works — turns vague "it should work" claims into concrete evidence. Pairs with @oath-verifier agent.

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • hr-comp-analysisSkillAI & models

    Compensation analysis — benchmarking, band positioning, and equity modeling. Use when you need to know how much to pay for a role, assess whether an offer is competitive, model an equity grant, or identify outliers and retention risks on the team. Triggers: "how much to pay a [role]",

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • initial-setupSkillAI & models

    Welcome and onboard new EvoNexus users — introduce agents, skills, routines, and the dashboard. Triggers when the user says 'get started', 'how do I use this', 'what can you do', 'help me get started', 'onboarding', 'show me around', 'what agents do I have', 'how does this work', 'first time here',

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • manage-heartbeatsSkillAI & models

    List, enable, disable, or manually trigger heartbeats (proactive agents). Shows last 10 runs with status and cost. Use when the user says 'list heartbeats', 'show active heartbeats', 'enable atlas-4h', 'disable zara-2h', 'run atlas heartbeat now', 'which heartbeats are running', or wants visibility

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • ops-process-optimizationSkillAI & models

    Analyze and improve business processes. Use when a process is slow, when asking how to improve or simplify a workflow, too many steps, bottleneck, or when the user describes an inefficient process they want to fix. Clawdia agent.

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • ops-vendor-reviewSkillAI & models

    Evaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side by side, or building a TCO breakdown and negotiation points before approval. Nex agent.

    Ready to connect★ 535

    github.com/evolution-foundation/evo-nexus529 stars

    View details
  • swift-concurrency-proSkillAI & models

    Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing Swift concurrency code.

    Ready to connect★ 535

    github.com/twostraws/swift-concurrency-agent-skill407 stars

    View details
  • aiSkillAI & models

    Use when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage

    Ready to connect★ 533

    github.com/butterbase-ai/butterbase-skills533 stars

    View details
  • butterbase-skillsSkillAI & models

    Claude Code plugin for Butterbase — 30+ guided skills and auto-configured MCP for the AI-native backend-as-a-service.

    Ready to connect★ 533

    github.com/butterbase-ai/butterbase-skills533 stars

    View details
  • journey-agentsSkillAI & models

    Use as the agents build stage of the Butterbase journey. Implements the Agents section of 02-plan.md by delegating to the `agents` skill for each agent. Registers any required MCP servers, validates each graph_spec, creates the agent, and smokes it via invoke_agent. Skipped if the plan has no agents

    Ready to connect★ 533

    github.com/butterbase-ai/butterbase-skills533 stars

    View details
  • journey-aiSkillAI & models

    Use as the AI build stage of the Butterbase journey. Implements the AI section of 02-plan.md by delegating to the ai skill. Calls manage_ai (update_config) to set defaults and optionally BYOK. Skipped if the plan has no LLM/embeddings usage.

    Ready to connect★ 533

    github.com/butterbase-ai/butterbase-skills533 stars

    View details
  • agent-benchmarkSkillAI & models

    Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when evaluating agent changes, auditing quality, or establishing performance baselines.

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • agent-qa-testingSkillAI & models

    Agent behavior testing and protocol compliance validation. Measures with assertion-based tests whether agents behave in accordance with their defined roles. Detects personality drift, role violations, and output quality regressions.

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • agent-tamagotchiSkillAI & models

    Terminal pet that lives in your statusline. 12 species, 5 stats (DEBUGGING, PATIENCE, CHAOS, WISDOM, SPEED). Reacts to your workflow - happy when tests pass, sad when builds fail, excited during swarm mode. Deterministic species from user ID.

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • circuit-breakerSkillAI & models

    Agent fault tolerance with a circuit breaker pattern. Stops an agent that fails repeatedly, applies a cooldown, and switches to a fallback. Prevents cascading failures and infinite retry loops.

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • codex-orchestrationSkillAI & models

    Guide to using OpenAI Codex CLI together with Claude Code (Hizir). Work distribution patterns, GitHub Actions workflow examples, review loops, and orchestration strategies that combine the strengths of the two AI coding assistants.

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • external-skills-catalogSkillAI & models

    Curated catalog of 60+ external Claude Code skills across 8 categories with quality rankings, install instructions, and fallback strategies

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • github-actions-integrationSkillAI & models

    Claude Code Action entegrasyonu - PR review ve issue-to-fix workflow kurulumu

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • hizirSkillAI & models

    Hizir's user guide. All commands, agents, workflows, and systems are here. Type /hizir to see everything.

    Ready to connect★ 531

    github.com/vibeeval/vibecosystem531 stars

    View details
  • template-skillSkillAI & models

    Reusable template for authoring new Agent Skills with clear triggers, workflow, and I/O contracts.

    Ready to connect★ 525

    github.com/noizai/skills525 stars

    View details
  • composer-debugSkillAI & models

    Drive a live Composer page from the agent side via the loopback debug port — evaluate expressions against the running client, list plugins and operations, invoke an operation. Use when debugging a booting-but-misbehaving app (hang, bad query, plugin fault, wrong UI state) and you would otherwise ask

    Ready to connect★ 520

    github.com/dxos/dxos518 stars

    View details
  • regenerate-model-fixtureSkillAI & models

    Regenerate cached LLM responses for tests that replay model fixtures. Use when tests fail with "No memoized conversation found for the given prompt", when fixing or adding model-fixture tests, or when the user asks to regenerate or update the LLM conversation cache.

    Ready to connect★ 520

    github.com/dxos/dxos518 stars

    View details
  • testing-assistant-conversationsSkillAI & models

    Test assistant conversations, agents, and skills using AssistantTestLayer, Effect/vitest, ECHO types, and memoized LLM fixtures. Use when writing or fixing assistant-toolkit tests, skill.operation tests, AiSession flows, or when CI fails on missing memoized conversations.

    Ready to connect★ 520

    github.com/dxos/dxos518 stars

    View details
  • feature-flowSkillAI & models

    Multi-phase orchestrator for a feature: spec → plan → implement → review → CI gate → PR. Uses parallel agents for divergent thinking and a single synthesizer between phases. Trigger when the user says 'start the feature flow', 'run feature-flow', or names a ticket and asks to drive it end to end.

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • neo4j-cypher-guideSkillAI & models

    Comprehensive guide for writing modern Neo4j Cypher queries. Essential for text2cypher MCP tools and LLMs generating Cypher queries. Covers removed/deprecated syntax, modern replacements, CALL subqueries for reads, COLLECT patterns, sorting best practices, set-based writes, and Quantified Path Patte

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • speckit-opsmill-summarySkillAI & models

    Produce a flow-level summary of the current Claude Code session — executive

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • speckit-review-runSkillAI & models

    Comprehensive code review using specialized agents — orchestrates code,

    Ready to connect★ 518

    github.com/opsmill/infrahub512 stars

    View details
  • director-guzhuangSkillAI & models

    Knowledge of Chinese historical costume (guzhuang) conventions — costume styling (dynasty/status/headdress/makeup/color hierarchy), architectural forms (roof ranks/bay widths/dougong brackets/courtyards/yamen court halls), etiquette and staging, anachronism self-checks, and prompt tips for costume r

    Ready to connect★ 507

    github.com/aqm857886159/nomi501 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