Revyl Proof Ci

Organization

RevylAI

revyl-proof-ci

Prove a pull request using a CI-uploaded Revyl build — match commit, start a device by build id, capture evidence, and comment. Guidance only; execution stays on the Revyl CLI.

Overview

Publisher	RevylAI
Repository	`revyl-cli`
Skill name	`revyl-proof-ci`
Stars	522
Forks	25
Bundled files	Instructions only
Links	Skill source Repository

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 Proof Ci AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/RevylAI/revyl-cli/tree/main/cursor-plugin/skills/revyl-proof-ci
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.

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-ci .claude/skills/revyl-proof-ci

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Revyl Proof Ci 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 Ci 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 Ci 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 from CI Builds

Use this skill when proving a pull request whose artifact was already uploaded by CI (revyl build upload), with or without the Revyl GitHub App. It layers on top of revyl-cli-dev-loop / revyl-cloud-agent for device hygiene; load those when you are in a Cursor Cloud or Automation environment.

This skill does not add a new runtime. Prove with the existing Revyl CLI only.

When to use

Cursor Automation / Cloud Agent tasked with device proof after CI upload
Manual "prove this PR" requests against a BYO-CI build
Twin path: Revyl GitHub pr_review.build.kind: ci_upload_to_revyl plus pr_review.proof_of_changes.harness.kind: cursor

To create the scheduled Automation (CI upload + paste-ready prompt), use revyl-proof-automation. Canonical prompt and triggers also live in revyl-cli/examples/cursor-automation/prove-mobile-pr/ and Cursor proof.

Non-negotiable rules

Do not rebuild. Find the Revyl build for this commit; do not run revyl build / local native builds to produce a new artifact for proof.
Never claim proof without a device session. If no matching build exists after a brief wait/retry, say so and stop.
Prefer revyl device start --build-version-id <id>.
Stop every session before finishing (revyl device stop).
Comment with Cursor's native Comment on pull request tool. Edit an existing ## Revyl device proof comment when present; otherwise create one.
Never paste REVYL_API_KEY, launch-var values, or tokens into comments.

Loop

Match the build to the PR head commit
- revyl build list --app <REVYL_APP_ID> --json
- Match metadata.scm_head_sha, metadata.git.commit / commit_short, or a version string equal to the head SHA
- Brief wait + retry once or twice if CI upload has not landed yet

Start the device on that build

bash
revyl device start --build-version-id <build-version-id> --json

Run from the directory that owns .revyl/config.yaml so session.auth_bypass / session.before_script apply.

Exercise the diff
- Read the PR diff; verify the behaviour it changes
- revyl device screenshot / revyl device validation
- Save a small set of key screenshots locally with descriptive names

Publish evidence

bash
revyl device stop
revyl device report --session-id <session-id> --json
revyl session share <session-id> --json
revyl session publish <file> --session <session-id> --json

Use shareable_link and each public_url. Do not paste short-lived video_url / X-Amz-* links. Do not commit screenshots.

PR comment
- Heading ## Revyl device proof
- Bold build id, app commit, device, pass/fail
- ## Evidence with shareable report link + HTML <img width="220"> thumbnails in a table (same shape as the Automation PROMPT.md)

Set up the Cursor Automation: revyl-proof-automation
Automation package: revyl-cli/examples/cursor-automation/prove-mobile-pr/
CI upload example: revyl-cli/examples/ci-github-actions/upload-for-cursor-proof.yml
Cloud agent hygiene: revyl-cloud-agent skill

Frequently asked questions

What does the Revyl Proof Ci AI skill do?

Prove a pull request using a CI-uploaded Revyl build — match commit, start a device by build id, capture evidence, and comment. Guidance only; execution stays on the Revyl CLI.

Why use Revyl Proof Ci on TypingMind?

Because you install it once and use it with any model. Revyl Proof Ci 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 Ci 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-ci. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Revyl Proof Ci?

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 Ci?

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

Is the Revyl Proof Ci 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

Clawsweeper

openclaw

OrganizationPopular

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Control Ui E2e

Use when designing, testing, fixing, or extending the OpenClaw Control UI GUI, including UI stress-test galleries with feedback inputs, Vitest + Playwright end-to-end checks, mocked Gateway flows,…

Deslop

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Discord Clawd

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Revyl Proof Ci

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Revyl Proof from CI Builds

When to use

Non-negotiable rules

Loop

Related

Frequently asked questions

Set up your own AI workspace now

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Revyl Proof from CI Builds

When to use

Non-negotiable rules

Loop

Related

Frequently asked questions

Related AI Skills

Set up your own AI workspace now