Cherry Pr Test Agent Skill

Cherry Studio PR Test

Use this workflow for a bounded PR test. Use cherry-electron-dev for ongoing

implementation or debugging in the current checkout.

Prerequisites and safety

• Require authenticated gh, pnpm, and installed project dependencies.
• Use Playwright/CDP or optional agent-browser for UI control.
• Before touching Electron, read

Electron Instance Management

and select its ephemeral policy.

• Treat that reference as the only authority for discovery, target selection,

launch, replacement, shutdown, tracking, and troubleshooting.

• Never discard local changes. Stop and ask if checkout would overwrite them.
• Show the report before posting it anywhere.

$ARGUMENTS may contain a PR number, PR URL, latest/recent, or nothing.

Workflow

1. Resolve and inspect the PR

If no PR is specified, list recent PRs and ask the user to choose unless they

requested the latest:

gh pr list --repo CherryHQ/cherry-studio --state open --limit 10 \
  --json number,title,author,createdAt,headRefName,changedFiles

Record the current branch for restoration, inspect the PR, then check it out:

git status --short
git branch --show-current
gh pr view <NUMBER> --json title,body,author,headRefName,files
gh pr checkout <NUMBER>

Read the changed files and nearby instructions. Record the exact checked-out

HEAD.

2. Analyze and start the app

Run static analysis while the app starts when both can proceed independently.

For static analysis:

pnpm typecheck

Also check:

• blocked or deprecated v1/v2-refactor files
• hardcoded user-visible strings instead of i18n
• console.log instead of loggerService
• missing types on new public interfaces

For Electron:

• Use the shared reference to verify existing instances.
• Reuse only an instance from this workspace whose recorded launch HEAD equals

the checked-out PR HEAD.

• When reusing one, mark it borrowed and preserve its existing policy and

ownership. Never reclassify a persistent instance as ephemeral.

• Otherwise gracefully replace only the verified same-workspace instance.
• Launch an ephemeral, agent-owned instance with an isolated

CS_DEV_USER_DATA_SUFFIX, such as PR-<NUMBER>.

• Keep its managed terminal/session, PIDs, ports, log, exact target, and

pr-test:<NUMBER> launch purpose in

instance.json.

Do not use broad process or port cleanup.

3. Run interactive tests

Bind the controller to the exact target returned by the shared reference.

Never navigate to a guessed root URL or select a target by index.

Build test cases from the PR description and changed files:

• Capture the initial state.
• Inspect interactive elements with the available CDP controller.
• Exercise the changed behavior.
• Capture the result and verify relevant persisted state.
• Repeat edge cases justified by the change.

Consider UI rendering, interactions, persistence, light/dark themes, relevant

window sizes, i18n, empty states, and rapid interaction only when in scope.

Store screenshots and the report under /tmp/pr-<NUMBER>/:

mkdir -p /tmp/pr-<NUMBER>

If an isolated profile shows the migration wizard or splash, follow the shared

troubleshooting guidance and startup logs. Do not reset or force-close data.

4. Clean up and restore

Use the shared ephemeral finish procedure. Stop only an instance launched by

this PR-test workflow whose verified record remains ephemeral, agent-owned,

and scoped to pr-test:<NUMBER>. Leave every borrowed instance running. Do not

stop unrelated workspaces or packaged apps.

Restore the branch recorded before checkout. If it no longer exists, resolve

the repository default branch and report the fallback before switching:

git checkout <ORIGINAL_BRANCH>

5. Report

Save /tmp/pr-<NUMBER>/report.md and show it to the user. Match the report

language to the user's language; the template uses English labels:

# PR #<NUMBER> Test Report

**Title**: <title>
**Author**: @<author>
**Branch**: <branch>
**Changed files**: <count>

## Static Analysis

| Check | Result | Notes |
| --- | --- | --- |
| TypeScript typecheck | ✅/❌ | ... |
| Blocked-file check | ✅/⚠️ | ... |
| Logging, i18n, and types | ✅/❌ | ... |

## UI Tests

### <Test Case>

<scenario, evidence, and result>

![screenshot](<filename>.png)

## Findings

<findings or none>

## Conclusion

- Total findings: N
- Recommendation: APPROVE / REQUEST_CHANGES / COMMENT

Do not post the report or submit a GitHub review unless the user explicitly

asks.