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

8,992 results · page 238 of 300

  • project-retrospectiveSkillAI & models

    Use when a project needs multi-session retrospective analysis: after milestones, before starting a new phase, when vision drift is suspected, or every 3-5 sessions. Triggers include user saying retro, run a retro, since-last-retro; asks to analyze patterns, recurring mistakes, or correction trends a

    Ready to connect

    github.com/belumume/claude-skills47 stars

    View details
  • realistic-long-chat-validationSkillAI & models

    Run a realistic many-turn OpenMates CLI chat to validate Gemini routing, generated artifact quality, repeated compression checkpoints, and publish a successful run as an example chat

    Ready to connect

    github.com/glowingkitty/openmates46 stars

    View details
  • receiptsSkillAI & models

    Generate a personal Claude Code usage & impact report ("receipts") from this machine's local session transcripts — for justifying Claude Code usage/spend to a manager, self-review, or "what have I been using this for" check-ins. Mines ~/.claude/projects locally (no extra API calls beyond one final w

    Ready to connect

    github.com/thevibeworks/claude-code-docs47 stars

    View details
  • session-reportSkillAI & models

    Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.

    Ready to connect

    github.com/thevibeworks/claude-code-docs47 stars

    View details
  • sub-agent-sandboxingSkillAI & models

    Use when delegated work needs runtime guardrails — constrain sub-agents with loop detection, circuit breakers, and escalating sandbox levels before accepting their output

    Ready to connect

    github.com/drvoss/everything-copilot-cli47 stars

    View details
  • twilight-aiSkillAI & models

    Assist with development in the Twilight AI Go SDK. Use when working in this repository, adding or updating providers, embeddings, tool calling, streaming, examples, or docs for Twilight AI.

    Ready to connect

    github.com/felinics/twilight45 stars

    View details
  • [Vendor] [Topic]SkillAI & models

    [What this skill covers — the domain knowledge inside: entities, API surface, workflows, gotchas. One clear statement of coverage; do not restate the trigger conditions from when_to_use.]

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • accessibility-verificationSkillAI & models

    Prove an accessibility claim instead of asserting it — automated scan plus the keyboard, focus, zoom and screen-reader passes a scanner structurally cannot make. Fires before anyone says a screen is accessible or WCAG AA, when signing off UI work, or when an audit result needs checking. Not for maki

    Ready to connect

    github.com/nahid-sparktales/agent-dispatcher46 stars

    View details
  • agent-evalsSkillAI & models

    Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check properties rather than vibes, a recorded baseline, and per-case diffs in both directions. Use before claiming a prompt, model or agent change is an improvement, when agent behaviour must no

    Ready to connect

    github.com/nahid-sparktales/agent-dispatcher46 stars

    View details
  • ai-native-audit-releaseSkillAI & models

    'AI Native 产品方法论——审计放行阶段的实操 Skill。

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-business-modelSkillAI & models

    Skill for designing AI-native business models. Based on the "AI Deterministic Business Model" methodology, it helps users design AI business models centered on the "certainty premium":

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-context-engineeringSkillAI & models

    'AI Native 产品方法论——上下文工程的实操 Skill。

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-direction-framingSkillAI & models

    'AI Native 产品方法论——方向定界阶段的实操 Skill。

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-experiment-engineSkillAI & models

    'AI Native 产品方法论——试验展开阶段的实操 Skill。

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-knowledge-ragSkillAI & models

    'AI Native 产品方法论——RAG与知识系统设计的实操 Skill。

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-marketing-growthSkillAI & models

    AI Native marketing and growth strategy Skill. Based on the methodology of 《AI Native 营销与增长》, it helps users build growth systems with AI as the first principle: upgrading from tool-based thinking to systems thinking.

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-pm-agentSkillAI & models

    AI Native Product Manager Agent — an all-in-one product workflow orchestrator ('five documents in one'). The user provides a product idea or problem lead, and the Agent automatically orchestrates seven stages:

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-product-needsSkillAI & models

    AI Native product needs discovery Skill. Based on the《AI rebuild product needs》methodology, it helps users in AI Agent

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-production-opsSkillAI & models

    AI-Native product methodology — a hands-on Skill for production operations and feedback loops.

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • ai-native-system-buildingSkillAI & models

    'AI Native 产品方法论——系统构建阶段的总论 Skill。

    Ready to connect

    github.com/gmaxxxie/ai-native-product-agent-skills46 stars

    View details
  • api-contract-verificationSkillAI & models

    Prove an API integration actually works by executing it — success path, documented failure paths, auth failure — and leave behind a contract test that catches the next break. Use before reporting any endpoint, client or third-party integration as working, when asked whether an integration is verifie

    Ready to connect

    github.com/nahid-sparktales/agent-dispatcher46 stars

    View details
  • Atera AgentsSkillAI & models

    Atera RMM agents: agent records and fields, online/offline status, endpoint search and monitoring, PowerShell and script execution, and agent lifecycle.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Auvik NetworksSkillAI & models

    Auvik network and interface entities: the network entity model, IP-range scoping, interface-to-device relationships, and adminStatus vs operStatus.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Axcient AppliancesSkillAI & models

    Axcient x360Recover appliances: the physical/virtual hardware running local backups, its device roster, and the org-wide vs client-scoped list tools.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Axcient JobsSkillAI & models

    Axcient x360Recover backup jobs: the BRC vs Replibit job-type split, per-job protection thresholds, and job run history with its starttime_begin pagination floor.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Better Stack Status PagesSkillAI & models

    Better Stack status pages: status page configuration, resources and components, maintenance windows, and public service-status communication.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Blumira FindingsSkillAI & models

    The Blumira finding lifecycle: status and severity codes, resolution types, list filtering, enriched detail retrieval, assignment, and comment threads.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Blumira MSPSkillAI & models

    Blumira's MSP path group (`/msp/*`): managed-account enumeration, cross-account and per-account finding queries, per-account device, agent-key and user management, and how MSP paths differ from org paths.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Blumira UsersSkillAI & models

    Blumira organization users: listing and filtering users, user roles, and looking up the user IDs required for finding assignment and access audits.

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 stars

    View details
  • Board HygieneSkillAI & models

    Board-wide ticket maintenance, distinct from working any single ticket: stale-ticket detection with per-status staleness thresholds, the Waiting-on-Client rot case and its three valid resolutions, duplicate/related-ticket detection signals and safe linking, and technician queue-balance assessment we

    Ready to connect

    github.com/wyre-ai/msp-claude-plugins46 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.

55,005 of the 55,436 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