Revyl Proof Automation logo

Revyl Proof Automation

Organization
RevylAI
revyl-proof-automation

Set up a Cursor Automation that proves each pull request on a Revyl cloud device using a CI-uploaded build. Use when creating Cursor proof, BYO-CI device proof, proof of changes without the Revyl GitHub App, or wiring revyl build upload plus a Cursor Automation.

Overview

PublisherRevylAI
Repositoryrevyl-cli
Skill namerevyl-proof-automation
Stars
522
Forks
25
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Revyl Proof Automation 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-proof-automation
  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-proof-automation .claude/skills/revyl-proof-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Revyl Proof Automation 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 Proof Automation 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 Proof Automation 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 Proof Automation Setup

Use this skill to create the Cursor Automation and CI upload for Cursor proof (BYO-CI). Do not use it to prove a PR that already has a matching build — that is revyl-proof-ci.

This skill does not start a device and cannot create the Automation in Cursor's UI. Use it when the user asks to prove a pull request or set up Cursor proof. Finish the three steps here.

Do not start an empty device. Do not connect the Revyl GitHub App as the setup path.

1. Confirm Revyl auth

bash
revyl auth status

If unauthenticated, run revyl auth login and post the printed approval URL as a clickable markdown link. Wait for approval. For Automations / Cloud Agents, they will set REVYL_API_KEY themselves — never print it.

2. Add one upload step to the job that already builds the app

Inspect existing GitHub Actions (or equivalent). After the job that already produces a simulator .app or installable .apk, add upload only. Edit that workflow. Do not add a second unrelated workflow file.

bash
revyl build upload \
  --file path/to/app.apk \
  --app "<your-app-id>" \
  --platform ios \
  --version "${{ github.event.pull_request.head.sha || github.sha }}" \
  --yes \
  --json

Use --platform ios or --platform android to match the Revyl app. Do not guess Android. Wait until the platform is known before writing the upload command. Use the PR head SHA. Store REVYL_API_KEY as a CI secret. Bake the app id into the command — do not also create a REVYL_APP_ID GitHub variable. GitHub Actions metadata (scm_head_sha, PR number, and related fields) is stamped automatically.

Hard rules for CI:

  • The file is a simulator .app / .app.zip or an installable .apk — not a store .ipa or Play AAB.
  • The job only uploads. It does not start a device, prove, or comment.
  • No Cursor API key belongs in GitHub.
  • Signing keys, Expo tokens, and store credentials stay in CI — the Automation never needs them.

3. Emit the Automation checklist

The agent cannot create the Automation. Tell the user to finish at cursor.com/automations:

  1. Paste the contents of PROMPT.md in this skill directory verbatim as the Automation instructions. Read that file and show it in a copy-ready block. Do not paraphrase.
  2. Enable Comment on pull request and shell. Do not enable Revyl MCP. Do not call start_dev_loop or list_builds.
  3. Trigger must be CI completed / Workflow run completed scoped to the upload job. Do not recommend Pull request pushed as the default.
  4. Add secret REVYL_API_KEY (a Revyl CLI API key from Settings) and variable REVYL_APP_ID.
  5. Surface, do not pretend to fix: paid Cursor plan, and the repo connected in Cursor so Comment on pull request works.

The Automation runner must install the CLI itself (install.sh in PROMPT.md). The desktop plugin pin does not apply there.

Do not rely on gh or the GitHub API for commenting. The native Comment tool posts as the Automation identity.

NameKindWhere
REVYL_API_KEYSecretCI + Cursor Automation
REVYL_APP_IDVariableAutomation only
Signing / Expo / store credentialsSecretCI only

What the Automation will do

text
CI builds the app
  → revyl build upload (commit metadata stamped)
  → Cursor Automation starts
  → matches Revyl build for the PR head SHA
  → revyl device start --build-version-id …
  → screenshots / validations
  → revyl report annotations create … (pinned findings, as discovered)
  → session share + publish
  → ## Revyl device proof comment on the PR (findings digest + write-up)

If no matching build exists after a brief wait, it comments that proof was not run and stops. It never rebuilds and never claims proof without a device session.

Related

  • Prove a PR that already has a CI-uploaded build: revyl-proof-ci
  • Cloud agent hygiene: revyl-cloud-agent
  • Docs: Cursor proof (BYO-CI)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Revyl Proof Automation AI skill do?

Set up a Cursor Automation that proves each pull request on a Revyl cloud device using a CI-uploaded build. Use when creating Cursor proof, BYO-CI device proof, proof of changes without the Revyl GitHub App, or wiring revyl build upload plus a Cursor Automation.

Why use Revyl Proof Automation on TypingMind?

Because you install it once and use it with any model. Revyl Proof Automation 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 Proof Automation in TypingMind?

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

Which AI models can use Revyl Proof Automation?

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 Proof Automation?

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

Is the Revyl Proof Automation 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 👇