Revyl Cloud Agent logo

Revyl Cloud Agent

Organization
RevylAI
revyl-cloud-agent

Revyl conventions for Cursor Cloud/background agents - CLI install, sign-in, remote builds, artifact evidence, session cleanup, and PR flow.

Overview

PublisherRevylAI
Repositoryrevyl-cli
Skill namerevyl-cloud-agent
Stars
522
Forks
25
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by RevylAI on GitHub. Read the source before you install it.

Installation

Install the Revyl Cloud Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/RevylAI/revyl-cli/tree/main/cursor-plugin/skills/revyl-cloud-agent
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/RevylAI/revyl-cli.git /tmp/revyl-cli
mkdir -p .claude/skills
cp -r /tmp/revyl-cli/cursor-plugin/skills/revyl-cloud-agent .claude/skills/revyl-cloud-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Revyl Cloud Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Revyl Cloud Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Revyl Cloud Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Revyl Cloud Agent Skill

Use this skill whenever you are running as a Cursor Cloud/background agent (headless Linux VM) and working with Revyl. Drive devices with the CLI. The plugin does not start MCP.

Environment Ground Rules (non-negotiable)

  • The VM is headless and non-interactive. Never start the revyl dev TUI.
  • Before the first revyl command, prepend the user PATH directories the plugin publishes the CLI onto (~/.revyl/bin, then ~/.local/bin if that path already holds a different CLI):
bash
export PATH="$HOME/.revyl/bin:$HOME/.local/bin:$PATH"

The plugin cache is not on PATH. Do not invoke ${CURSOR_PLUGIN_ROOT} or the cached binary as the shell command.

  • If a real REVYL_API_KEY is in the environment, run revyl auth persist-cloud-env once so the key never reaches argv. Never print the key.
  • If that command reports no key, run revyl auth login and post the printed approval URL as a clickable markdown link plus the short code, then wait. Optional REVYL_API_KEY as a Runtime Secret is the unattended path, not the only path. Never request or accept the key in chat.
  • The VM has no Xcode. Native iOS dev loops must use revyl dev --remote. Treat Android the same unless the VM demonstrably has the SDK.

Session Lifecycle (devices cost money and outlive the VM)

  • Cloud device sessions do not die when the VM exits. revyl dev stop is mandatory before completion.
  • At the start of a run, use revyl dev list to check for a suitable existing session. Do not stack new devices on stale ones.

Bounded Monitoring (never hang the shell)

  • Use revyl dev status for independent status snapshots.
  • After native changes, call revyl dev rebuild, continue independent work, then revyl dev rebuild --wait with a finite timeout.

Artifacts and Evidence

  • Post viewer_url as a clickable markdown link as soon as revyl dev --detach --json returns.
  • Use revyl device screenshot and revyl device validation as evidence.
  • Never claim the Cloud VM opened a browser or the user's local Cursor Desktop.

Auth Bypass and Secrets

  • Selected launch configurations apply automatically to fresh raw device, dev, test, and workflow runs. Do not fetch their payloads or repeat them explicitly.
  • If the app shows a logged-out state mid-session but the boot token is still valid, run revyl dev auth refresh --json. If the token itself expired, revyl dev stop then revyl dev so a fresh mint is applied as launch environment.
  • Never paste launch-configuration payloads, tokens, or API keys into code, chat, logs, screenshots, or PRs.

Optional custom MCP

Users who add a personal MCP entry with a literal command such as revyl or /usr/local/bin/revyl can install the MCP dev-loop skill by name. Never ${CURSOR_PLUGIN_ROOT} or ${env:...}. The plugin does not start that server. Do not call MCP tools unless that skill is installed and the tools are registered.

Git Hygiene

  • Before committing, confirm .revyl/.gitignore exists (created by revyl init; it keeps dev-session runtime state out of git — only config.yaml and tests/ belong in the repo).
  • Never commit artifacts, screenshots, logs, or minted launch-var files.

PR Flow

  • If gh is read-only in this environment, use the ManagePullRequest tool instead.
  • The PR body carries the evidence: the viewer_url, the key inline screenshots, and a one-line summary of what was verified on-device.

Frequently asked questions

What does the Revyl Cloud Agent AI skill do?

Revyl conventions for Cursor Cloud/background agents - CLI install, sign-in, remote builds, artifact evidence, session cleanup, and PR flow.

Why use Revyl Cloud Agent on TypingMind?

Because you install it once and use it with any model. Revyl Cloud Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Revyl Cloud Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/RevylAI/revyl-cli/tree/main/cursor-plugin/skills/revyl-cloud-agent. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Revyl Cloud Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Revyl Cloud Agent?

As many as you like. As long as a model supports skills, you can use Revyl Cloud Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Revyl Cloud Agent AI skill free?

It is published on GitHub by RevylAI. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇