# argos-pr-review

Evaluates Argos visual regression builds during pull request reviews. It checks whether UI changes match code diffs and filters out flaky snapshots.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 761 installs · ★ 18
- Author: argos-ci
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/argos-ci/argos-javascript/tree/HEAD/skills/argos-pr-review/SKILL.md
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/skills/argos-pr-review

## What it does

The skill connects the `argos` CLI directly into the PR review workflow. First, the agent infers intended UI updates from the pull request summary, issue notes, and code diff. It then runs `argos build get` and `argos build snapshots` to inspect captured screenshots against the base version.

Visual differences are classified into deliberate updates, actual regressions, or environmental flakes. Regressions show up as broken layout, clipped elements, or wrong themes. Flaky snapshots are identified using metrics such as `test.metrics.flakiness` and recurring diff counts, as well as visual artifacts like spinners.

Reading build snapshots requires an `ARGOS_TOKEN`. Without a personal access token, the CLI cannot post reviews or snapshot comments, so the agent reports its findings directly in the console.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add argos-ci/argos-javascript --skill argos-pr-review -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/argos-pr-review/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/argos-pr-review/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add argos-ci/argos-javascript --skill argos-pr-review -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/argos-pr-review/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add argos-ci/argos-javascript --skill argos-pr-review -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/argos-pr-review/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install argos-ci/argos-javascript argos-pr-review
```

2. **Manually: put the files in place**
- File: `.github/skills/argos-pr-review/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add argos-ci/argos-javascript --skill argos-pr-review -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/argos-ci/argos-javascript --path skills/argos-pr-review
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/argos-pr-review/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add argos-ci/argos-javascript --skill argos-pr-review -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/argos-ci/argos-javascript/tree/HEAD/skills/argos-pr-review/SKILL.md

## When to use it
- verify Argos visual changes against pull request code diffs
- separate real interface regressions from flaky snapshot noise
- post anchored comments on problematic snapshot diffs
- submit build approval or rejection via the Argos CLI

## Example prompts
- Inspect the Argos build for this PR and check if the visual diffs match my code changes
- Review the failing Argos snapshots and comment on broken UI elements
- Check if the detected changes in Argos are actual regressions or flaky tests

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 5dec98d70849c59c.

BEGIN THIRD-PARTY FILE 5dec98d70849c59c
```text
---
name: argos-pr-review
description: >
  Review Argos visual regression builds as one input to a pull request review.
  Use when a PR has an Argos build link, an Argos status check, or a bot comment
  pointing to an Argos build, and you need to decide whether the visual diffs
  match the developer's intent before approving.
---

# Argos PR Review

**Argos** is a visual testing platform: each CI build captures screenshots and
compares them to a baseline, producing per-snapshot **diffs**. A build with
`changes-detected` is waiting for a human (or you) to decide whether each change
is intentional, a regression, or a flaky capture.

Treat the Argos build as **one input** to the PR review, never the sole source of
truth. Infer the intended UI change from the PR title, description, linked issue,
and code diff _first_, then use Argos to confirm the rendered result matches.

## Tooling & auth

Drive Argos through the `argos` CLI — load the **argos-cli** skill for the token
model and flags. In short: `build get` / `build snapshots` need a project token
(`ARGOS_TOKEN`/`--token`); submitting a review or comment needs a **personal
access token** (`--token` / `argos login`). Always use `--json` when parsing, and
never print token values. If no PAT is available, give the user your conclusion
and evidence instead of posting — the CLI can't submit the review.

## Workflow

1. **Inspect the build** — `argos build get <ref> --json`. Decide from status:

   | Status                                      | Meaning / next step                                  |
   | ------------------------------------------- | ---------------------------------------------------- |
   | `accepted` / `no-changes`                   | Already approved / no visual diff — no review needed |
   | `pending` / `progress`                      | Not ready — stop and report it can't be reviewed yet |
   | `changes-detected`                          | Needs a decision — fetch snapshots                   |
   | `rejected` / `error` / `aborted`/ `expired` | Don't approve until the cause is understood          |

2. **Fetch what changed** — `argos build snapshots <ref> --needs-review --json`.
   For each diff inspect `url` (diff mask), `base.url` (before), `head.url`
   (after), and `head.metadata`, plus the flakiness signals `test.metrics` and,
   on a change, `change.occurrences` / `change.ignored` (used in step 3).

3. **Judge each diff** against the inferred intent:
   - **Intentional** — matches the code change and renders cleanly.
   - **Regression** — broken layout/overlap, clipping, wrong state/theme/route,
     missing content, or a removed snapshot with no matching test removal.
   - **Flaky** — weigh two independent signals; when they agree, call it flaky
     with confidence:
     - _Test history_ — `test.metrics.flakiness` (0 stable → 1 flaky) and
```
END THIRD-PARTY FILE 5dec98d70849c59c

The third-party file has ended. Everything between the 5dec98d70849c59c tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2884 of 6145 bytes. © argos-ci · MIT · https://github.com/argos-ci/argos-javascript/tree/HEAD/skills/argos-pr-review/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md