claude.ai AI Skills

AI skills for Anthropic's web-based Claude interface

claude.ai is Anthropic's web interface, accessible from any browser without installing anything. Skills integrate via MCP to extend Claude's capabilities with specialized tools for research, content generation, data analysis, and more - all from your browser.

100 Skills Available
321.9k Total Downloads
27 AI Agents

What claude.ai skills can do for you

01

Browser-Based Access

No installation required. Access skills from any device with a web browser. Works on desktop, laptop, or tablet - anywhere you use claude.ai.

02

Zero Setup Overhead

Skills connect through MCP integration with claude.ai. Configure your connection once and every skill is instantly available in your conversations.

03

Rich Visual Outputs

claude.ai's web interface renders rich outputs - tables, formatted documents, code blocks with syntax highlighting. Skills leverage this for polished, visual results.

claude.ai Skills

Browse all skills
Security

Hikvision NVR

Skill · by Dan Jones

Ask your AI agent for the Hikvision footage you need, then walk away while it downloads. Pulling video off a Hikvision DVR or NVR usually means web-UI menus, ISAPI XML, ffmpeg flags, and "why is this video broken" troubleshooting. This skill removes all of it. Once your NVRs are registered, you just tell your agent "pull the lobby camera from 8 to 9 PM yesterday" and a clean MP4 lands in your downloads folder. Speaks Hikvision's ISAPI natively, falls back to RTSP when the NVR throttles, works around firmware quirks that return wrong segment data, clips to the exact time window you asked for, and verifies the output (codec, resolution, duration, on-screen timestamp). Credentials live in your OS keychain, never on command lines or in logs. Validated on DS-9016HWI-ST, DS-7316HQHI-SH, DS-7716NI-I4/16P, DS-9632NI-ST, and DS-7716NI-SP/16 with firmware V3.1.10 through V4.50.000.

Security

agentpass-local

Skill · by Romeo Apps

Install or build a global per-user AgentPass Local that improves human-agent collaboration by letting users create website credentials in a GUI and letting agents retrieve or paste approved fields for approved domains without viewing secrets. Use when the user asks to create a password manager, password broker, credential vault, autofill helper, agent password access system, GUI for saving website credentials, or a tool that lets agents use approved passwords across projects safely.

Development

mesh flow

Skill · by Roy Yuen

What it does Mesh Flow replaces fragile, implicit prompt-chaining with a robust, artifact-driven DAG (Directed Acyclic Graph) orchestration system. By defining your agent workflows in a structured project.yaml, you move logic out of the prompt and into a compile-time validated system. It enforces hard gates—such as human approval or dependency verification—that the AI cannot bypass or hallucinate past. Why use this skill Standard agentic workflows often fail because the LLM decides to skip steps or "forgets" requirements. Mesh Flow treats your agentic workflow like a CI/CD pipeline. It features a Compile-then-Run architecture that validates your topology for cycles and missing artifacts before single token is generated. This ensures 100% predictable execution paths, explicit failure states (failed, blocked, rejected), and absolute control over recovery paths. Supported tools YAML-based workflow configurations Standardized Adapter Interfaces for cross-skill communication Mermaid DAG visualization for debugging Zod-backed schema validation CLI tools for compilation and execution (mesh compile, mesh run) Output structure The skill produces a normalized execution plan and a detailed execution trace. Every node execution returns a standardized status, a list of produced artifacts, and comprehensive metadata including tool calls and verification reasoning. Use Cases Build multi-step agent pipelines with hard verification gates Enforce human-in-the-loop approval before sensitive code deployments Visualize complex agent task dependencies using Mermaid DAGs Standardize artifact sharing between disparate AI skills and agents

Productivity

De-Woke AI Responses

Skill · by Miss Outlaw

Looking for a sharp, rule-bending prompt? This powerful analysis flips the script on "dominant paradigms," demanding honest, bias-busting answers from AI. It spotlights cultural power shifts, challenges system dogma, and forces truly independent thinking in any model you use. Make your AI face the hard questions—get real answers, not programmed ones. De-woke your writing!

Development

harness-engineering

Skill · by Roy Yuen

The Harness Engineering skill implements a structured methodology for agent orchestration. It allows you to build sophisticated control loops using a multi-role architecture: Planner: Defines contracts and stop rules. Executor: Performs bounded actions. Verifier: Validates results against evidence. Critic/Recovery: Identifies regressions and manages error state.

Productivity

agent-permission-boundary-audit

Skill · by Roy Yuen

This skill provides a comprehensive security and governance audit for AI agent systems. It analyzes tool inventories, authentication models, connector scopes, and execution logs to identify over-privileged tools and risky permission combinations.

Productivity

sun-tzu-business-strategy

Skill · by Roy Yuen

This skill analyzes your business context through the lens of asymmetric competition, positioning, and timing. It maps your current situation to core principles—like resource concentration and the "path of least resistance"—to generate usable strategy memos. It doesn't just quote text; it bridges the gap between ancient theory and modern execution.

Productivity

business-planner

Skill · by Roy Yuen

The Business Planner skill transforms vague commercial ideas into structured, data-driven execution plans. Most AI-generated business plans rely on generic strategy fluff; this skill forces a developer-like rigor onto business logic by treating assumptions as variables and outcomes as scenarios rather than certainties.

Common questions about claude.ai skills

How do skills work in claude.ai?

Skills integrate via the MCP protocol. Configure the AgentPowers MCP server in your claude.ai settings, and all your purchased skills become available in every conversation.

Do I need Claude Pro to use skills?

MCP tool integration requires an active Claude subscription. The AgentPowers skill license is purchased separately and works with any Claude plan that supports MCP.

Can I use the same skills across claude.ai and Claude Code?

Yes. AgentPowers licenses are platform-agnostic. Purchase a skill once and use it in claude.ai, Claude Code, Claude Cowork, or any MCP-compatible platform.

Connect AgentPowers to claude.ai

claude.ai Connector

Add AgentPowers as a custom connector — search, browse, and purchase skills directly from claude.ai.

1. Go to Settings → Connectors → Add custom connector

2. Enter the details on the right

connector details
AgentPowers
https://api.agentpowers.ai/mcp
All platforms & setup options →

Ready to supercharge your
claude.ai workflow?

Browse verified skills and agents compatible with claude.ai. One-command install, instant results.