Skills by agent

Claude Desktop skills

169 audited skills whose own text says they work in Claude Desktop. Each one carries our verdict, so you can see what a skill can touch before you install it: 49 SAFE, 35 CAUTION, 85 BLOCK. “Works in” is the skill’s claim; we have not tested it.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Claude Desktop skills”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/for/claude-desktop

1 · Pick a skill

Prefer SAFE. Open CAUTION skills and read the findings first.

2 · Check what it touches

Each page lists the filesystem, network and shell use the audit observed in the source.

3 · Pin the commit

Our verdict covers the audited commit only. Each page shows it.

Verdicts across these 169 skills

✓SAFE49!CAUTION35✕BLOCK85

How these skills say to install

136 of 169 document any install command. Commands are as the skills’ repositories show them: we list them, we never run them.

169 skills for Claude Desktop · page 1 of 8 · ranked by trust score, then stars

Mcp Server Patterns

affaan-m/ECC

✓SAFE B

Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

★ 264k89/100

Claude Code

anthropics/claude-code

!CAUTION B

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt…

★ 153k89/100

Open Source

browser-use/browser-use

✓SAFE B

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from…

★ 119k89/100

Mem0 Skill for Claude

mem0ai/mem0

✓SAFE B

Mem0 Platform SDK for adding persistent memory to AI applications. TRIGGER when: user mentions "mem0", "MemoryClient", "memory layer", "remember user preferences", "persistent context", "personalization", or needs to…

★ 68k89/100

Humanizer

blader/humanizer

✓SAFE B

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes…

★ 59k89/100

awesome-claude-code

hesreallyhim/awesome-claude-code

✓SAFE B

A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC. A delectable showcase of top…

★ 55k89/100

Troubleshooting

chromedevtools/chrome-devtools-mcp

✓SAFE B

Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.

★ 54k89/100

Build Mcp App

anthropics/claude-plugins-official

✓SAFE B

This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in chat", build "MCP UI resources", make a tool that shows a "form", "picker",…

★ 37k89/100

Build Mcp Server

anthropics/claude-plugins-official

✓SAFE B

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something…

★ 37k89/100

Build Mcpb

anthropics/claude-plugins-official

✓SAFE B

This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python…

★ 37k89/100

Cardputer Buddy

anthropics/claude-plugins-official

✓SAFE B

Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without…

★ 37k89/100

M5 Onboard

anthropics/claude-plugins-official

✓SAFE B

End-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Claude Buddy MicroPython app bundle. Use…

★ 37k89/100

Qmd

tobi/qmd

✓SAFE B

Search local markdown knowledge bases, notes, docs, and wikis with QMD. Use when users ask to find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access.

★ 31k89/100

Ce Brainstorm

everyinc/compound-engineering-plugin

!CAUTION B

Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm or scope what to build. Not for executing already-specified work. Use ce-pov for a verdict on…

★ 26k89/100

Mcp

vercel-labs/json-render

✓SAFE B

MCP Apps integration for json-render. Use when building MCP servers that render interactive UIs in Claude, ChatGPT, Cursor, or VS Code, or when integrating json-render with the Model Context Protocol.

★ 19k89/100

Agent Deep Links

composiohq/awesome-codex-skills

✓SAFE B

Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools. Use when users ask for clickable links (especially in Slack) that open threads, files, folders, or app settings.

★ 17k89/100

Getting Started

yusufkaraaslan/Skill_Seekers

✓SAFE B

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

★ 15k89/100

Atlassian Mcp

Jeffallan/claude-skills

✓SAFE B

Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use when querying Jira issues with JQL filters, creating and updating tickets with custom fields, searching or editing…

★ 12k89/100

Pinchtab

pinchtab/pinchtab

✓SAFE B

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user…

★ 10k89/100

Docs

Agents365-ai/drawio-skill

✓SAFE B

Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift…

★ 10k89/100

Drawio Skill

Agents365-ai/drawio-skill

✓SAFE B

Create and edit draw.io/diagrams.net diagrams as editable `.drawio` files. Covers architecture, UML/ERD/sequence, BPMN, network, and swimlane views authored from a description or converted from code, IaC, SQL, and API…

★ 10k89/100

Deck Obsidian Claude

nexu-io/html-anything

✓SAFE B

GitHub-dark + 紫蓝环境光 + 三色渐变标题 + GitHub 风代码

★ 9k89/100

html-ppt — HTML PPT Studio

lewislulu/html-ppt-skill

✓SAFE B

HTML PPT Studio — author professional static HTML presentations in many styles, layouts, and animations, all driven by templates. Use when the user asks for a presentation, PPT, slides, keynote, deck, slideshow, "幻灯片",…

★ 8.8k89/100

Docs

NomaDamas/k-skill

✓SAFE B

한국인을 위한 스킬 모음집 - 에이전트를 한국인으로

★ 7.8k89/100

Also for Claude Desktop

Questions about Claude Desktop skills

Are Claude Desktop skills safe?
49 of these 169 skills (29%) are SAFE, 35 CAUTION and 85 BLOCK. Skills that ship scripts can run code on your machine, so read the findings on any CAUTION or BLOCK page before you install.
What does "works in Claude Desktop" mean here?
The skill's own text mentions Claude Desktop. We have not tested the skill in Claude Desktop, so each page shows the claim, not a compatibility result.
How do I install a Claude Desktop skill?
136 of these skills document an install command in their repository; the commonest forms are git clone <url> (50 skills), npx skills add <owner/repo> (17 skills) and npm install (11 skills). The rest are installed from the repository itself. Each skill's page shows the commit our verdict covers, so you can pin to it.
Do these skills work in other agents?
160 of the 169 also mention at least one other agent in their text, such as Claude Code, Cursor and OpenClaw. Each page lists every agent the skill names.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.