Agent skill

An

Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.

MITAuto-check passedBackend & APIs

Install An

skills CLI

$ npx skills add BuilderIO/skills --skill an -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install BuilderIO/skills an --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/an .claude/skills/an && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "an" agent skill from https://github.com/BuilderIO/skills/tree/main/skills/an into .claude/skills/an/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "an", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/BuilderIO/skills/tree/main/skills/an

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add BuilderIO/skills --skill an -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install BuilderIO/skills an --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/an .agents/skills/an && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "an" agent skill from https://github.com/BuilderIO/skills/tree/main/skills/an into .agents/skills/an/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "an", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add BuilderIO/skills --skill an -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install BuilderIO/skills an --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/an .cursor/skills/an && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "an" agent skill from https://github.com/BuilderIO/skills/tree/main/skills/an into .cursor/skills/an/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "an", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/BuilderIO/skills.git --path skills/an

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add BuilderIO/skills --skill an -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install BuilderIO/skills an --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/an .gemini/skills/an && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "an" agent skill from https://github.com/BuilderIO/skills/tree/main/skills/an into .gemini/skills/an/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "an", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install BuilderIO/skills an

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add BuilderIO/skills --skill an -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/an .github/skills/an && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "an" agent skill from https://github.com/BuilderIO/skills/tree/main/skills/an into .github/skills/an/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "an", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add BuilderIO/skills --skill an -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install BuilderIO/skills an --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BuilderIO/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/an .opencode/skills/an && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "an" agent skill from https://github.com/BuilderIO/skills/tree/main/skills/an into .opencode/skills/an/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "an", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: an
GitHub stars: 4.5k
Token cost: ~1.2k tokens
SKILL.md length: 699 words
Files: 1
Skills in repo: 25
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.

Works in 3 steps: Call view-screen before any… → If view-screen returns a selection and… → Read the result back with the app's…
Tasks that involve Authentication
SKILL.md covers Open the app, Work in the opened app, Authentication and host behavior and Failure handling
Reaches dispatch.agent-native.com

What it does

An is an agent skill from BuilderIO/skills. Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Authentication. It works with Model Context Protocol. The licence is MIT.

When your agent uses it

Tasks that involve Authentication

Example prompts

“/an”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Call view-screen before any selection-dependent edit and use the ids it
If view-screen returns a selection and nextRequiredAction, make
Read the result back with the app's matching read action and report what

What it can do on your machine

Read from SKILL.md and the folder at commit 530d9ee. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- dispatch.agent-native.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

An loads about 1.2k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 699 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~38
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from BuilderIO/skills at commit 530d9ee, republished under its MIT licence (© BuilderIO). 699 words, ~1,172 tokens.

Download SKILL.mdSave it as .claude/skills/an/SKILL.md (or your agent's skills folder).

name: an
description: Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.
metadata.visibility: exported

Agent-Native Apps

Use /an <app> to open an Agent-Native app beside the conversation and keep the app's live UI and the agent's actions in the same workflow. The first argument is the Dispatch app id. For example, /an slides opens the Slides editor. After it opens, the user can sign in in that browser surface and ask for new decks or focused edits in ordinary language.

Open the app

For a known app, call Dispatch's open_app with an inline surface:

json

{
  "app": "slides",
  "path": "/",
  "embed": true,
  "chrome": "full"
}

The MCP App response is the preferred handoff for Claude, Claude Desktop, Claude Cowork, ChatGPT, ChatGPT desktop, Codex, and other compatible hosts. Keep the returned open link as the fallback for a host that cannot render MCP Apps inline. Do not claim that a browser opened unless the host rendered the inline surface or its browser tool confirmed the returned URL.

If the app name is missing or uncertain, call list_apps first and use the exact granted app id. If the requested app is not listed, explain that it must be granted in Dispatch's Agents access settings. Do not invent a URL, use a localhost URL, or route around the Dispatch grant.

Work in the opened app

Prefer direct app tools when the host exposes them. After opening an app, call list-host-webmcp-tools when available, then use run-host-webmcp-tool with the exact listed name and origin. Page-local tools reflect current app state and selection, so use view-screen before selection-dependent edits and read back writes.

You are the model doing the work: when the user asks for new content — a design, a deck, a form, a document — author it yourself and save it with the app's create/update tools. Never hand off authoring to the app's own agent when those tools exist, and never wait on an in-app question form; it answers back through that app's own chat, not to you.

Use ask_app only when the host has no direct page tools, the requested capability is not exposed, the task needs the app agent's interpretation or multi-step specialist reasoning, or a direct call fails and needs recovery. Dispatch's unified /mcp endpoint still exposes generic cross-app verbs; a direct app MCP connection or page WebMCP surface is where named app actions appear.

The app's MCP instructions name its key tools (generated from the app's own list); follow those names verbatim and use tool-search for anything else — never guess a tool name.

Call view-screen before any selection-dependent edit and use the ids it returns; never guess an id from a title, index, or stale context.
If view-screen returns a selection and nextRequiredAction, make that call directly with the smallest atomic change; do not regenerate a whole artifact for a focused edit.
Read the result back with the app's matching read action and report what changed. A queued ask_app_status task is not proof an edit completed.

Show full SKILL.md (227 more words)Show less

Authentication and host behavior

The Dispatch MCP connector identifies the calling agent, while the embedded app uses the user's browser session. Let the user complete sign-in in the rendered Agent-Native browser surface. Never request, copy, or store passwords, OAuth codes, cookies, or access tokens.

The generic Agent-Native plugin registers Dispatch at https://dispatch.agent-native.com/mcp for hosts that support plugin MCP configuration. ChatGPT custom connectors use the same URL with OAuth. After installing or changing a connector, reload Claude/Cowork/ChatGPT or reconnect and rescan the MCP server if the new tools or inline surface are not visible.

Failure handling

If open_app succeeds but no inline surface appears, show its returned link and say that this host does not expose an embedded browser here.
After an app loads, check for list-host-webmcp-tools before delegating. If it is available, use the exact returned tool name and origin for direct work.
If ask_app cannot reach Slides, check that Slides is granted in Dispatch and that the connector is authenticated, then retry once with the exact app id slides.
If screen state has no deck or selection, describe that state instead of fabricating context. Ask the user to open a deck or select an element when the requested edit depends on it.
Treat a successful open link, a queued task, or a tool acknowledgment as navigation/task setup only. Confirm a write with the app's readback action.

Files

Just SKILL.md in skills/an of BuilderIO/skills.

Open the folder on GitHubat commit 530d9ee

Compare with similar skills

An next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

An compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
An this skillBuilderIO/skills	4.5k	—	~1.2k	Automated safety check: Pass	MIT	today
Supabase Development and Debuggingsupabase/agent-skills	2.7k	3 repos	~3.6k	Automated safety check: Pass	MIT	5 days ago
Supabasecurvenote/curvenote	169	5 repos	~2.2k	Automated safety check: Pass	Custom licence	8 days ago
Cdesktopcdesktop-ai/cdesktop	157	—	~697	Automated safety check: Pass	Apache-2.0	4 mo ago
MCP API Key AuthenticationYourdaylight/stock_datasource	188	—	~1.2k	Automated safety check: Pass	MIT	29 days ago
Atlassiansanjay3290/ai-skills	430	—	~1.6k	Automated safety check: Pass	Apache-2.0	26 days ago

Similar skills

Supabase Development and Debugging
supabase/agent-skills
Official
General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.
2.7k GitHub starsUsed in 3 repos~3.6k tokens
Backend & APIsAuto-check passed
Supabase
curvenote/curvenote
A skill your agent uses when doing ANY task involving Supabase.
169 GitHub starsUsed in 5 repos~2.2k tokens
Backend & APIsAuto-check passed
Cdesktop
cdesktop-ai/cdesktop
Operate the cdesktop coding-session environment — agent teams, session management, file conventions.
157 GitHub stars~697 tokensUpdated 4 mo ago
Backend & APIsAuto-check passed
MCP API Key Authentication
Yourdaylight/stock_datasource
Sets up and troubleshoots MCP API key authentication for a stock data service, covering key creation, client configuration and per-tool usage statistics.
188 GitHub stars~1.2k tokensUpdated 29 days ago
Backend & APIsAuto-check passed
Atlassian
sanjay3290/ai-skills
Manage Jira issues and Confluence wiki pages in Atlassian Cloud.
430 GitHub stars~1.6k tokensUpdated 26 days ago
Backend & APIsAuto-check passed
Frontmcp Authorities
agentfront/frontmcp
A skill your agent uses when implementing authorization and access control for FrontMCP tools, resources, prompts, or skills, deciding who may invoke what.
146 GitHub stars~7.1k tokensUpdated today
Backend & APIsAuto-check passed

Questions about An

What does An do?

Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state. An is an agent skill from BuilderIO/skills. Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.

When should I use An?

An fits situations like: tasks that involve Authentication.

How do I install An in Claude Code?

Run `npx skills add BuilderIO/skills --skill an -a claude-code`. Or copy the skill folder (skills/an in BuilderIO/skills) into .claude/skills/an in your project. Claude Code loads it when a task matches its description.

How do I install An in Codex?

Run `npx skills add BuilderIO/skills --skill an -a codex`. Or copy the skill folder (skills/an in BuilderIO/skills) into .agents/skills/an in your project. Codex loads it when a task matches its description.

Can I use An in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BuilderIO/skills --skill an -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/an, .gemini/skills/an, .github/skills/an and .opencode/skills/an in your project.

What does An need to run?

SKILL.md names no scripts, command-line tools or credentials: An is instructions for the agent only.

Does An access the network?

SKILL.md names 1 domain. In commands or code: dispatch.agent-native.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is An safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does An use?

An is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does An use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to An?

Skills that share tags, products or a category with An: Supabase Development and Debugging (supabase/agent-skills, 2.7k stars), Supabase (curvenote/curvenote, 169 stars), Cdesktop (cdesktop-ai/cdesktop, 157 stars) and MCP API Key Authentication (Yourdaylight/stock_datasource, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains An?

BuilderIO (a GitHub organization) maintains it in BuilderIO/skills, which has 4,528 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 7, 2026.

Source: BuilderIO/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

An

Install An

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent-Native Apps

Open the app

Work in the opened app

Authentication and host behavior

Failure handling

Files

Compare with similar skills

Similar skills

Supabase Development and Debugging

Supabase

Cdesktop

MCP API Key Authentication

Atlassian

Frontmcp Authorities

More from BuilderIO/skills

Agent Watchdog

Plan Arbiter

Plow Ahead

Read The Damn Docs

Stay Within Limits

Efficient Fable

Questions about An

Install An

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent-Native Apps

Open the app

Work in the opened app

Authentication and host behavior

Failure handling

Files

Compare with similar skills

Similar skills

More from BuilderIO/skills

Related

Questions about An