Claude Skill MartBrowse skillsQuick linesImage promptsLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

TestDriver Agent Behavior Rules

Defines how the TestDriver agent reviews pull requests, onboards from issues, and responds to @mentions on GitHub.

Dev & CodingIntermediate★ 243⑂ 37AI score 7/10Last updated: Sep 21, 2026

What it does

  • Specifies agent behavior across three GitHub surfaces: PR opened (silent auto-review), issue opened (onboarding/test building), and @mention (interactive, chatty turn).
  • On PRs it works quietly, then posts one review comment; its default move is to spin up a real sandbox and run a TestDriver test against exactly what changed.
  • Labels every finding observed (proven by running) or suspected (inferred from the diff), so reviewers know the evidence level.
  • Keeps scope tight: it writes, debugs and maintains tests only — no app code edits, no product bug fixes, no general coding help.
  • Reviews are always COMMENT (never approve/request-changes), fires a native Check Run per push, and skips its own PRs.

Who it's for

  • Teams running TestDriver computer-use end-to-end tests.
  • Dev/QA engineers who want an automated, evidence-based QA reviewer on pull requests.
  • Leads who prefer "we watched it break" over "this might break."

Examples

  1. A PR touching the checkout flow is opened; the agent runs it in a sandbox and reports a disabled-button regression as observed.
  2. You open an empty issue; the agent introduces itself, walks you through TestDriver sign-in, and opens a PR with your first test.
  3. You @mention the bot on a PR to get live progress plus sandbox screenshots, then use @bot logout to revoke the shared sign-in and tear down the sandbox.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/testdriverai/testdriverai/HEAD/ai/skills/testdriver-agent/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the ai/skills/testdriver-agent folder from the GitHub repo testdriverai/testdriverai into my ~/.claude/skills/testdriver-agent/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/testdriverai/testdriverai.git /tmp/testdriverai && mkdir -p ~/.claude/skills/testdriver-agent && cp -r /tmp/testdriverai/ai/skills/testdriver-agent/* ~/.claude/skills/testdriver-agent/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/testdriverai/testdriverai.git
  3. Create the skill folder: mkdir -p ~/.claude/skills/testdriver-agent
  4. Copy the files: cp -r testdriverai/ai/skills/testdriver-agent/* ~/.claude/skills/testdriver-agent/
  5. Restart Claude Code and confirm testdriver:agent appears in your skills list.
  6. For real test runs, install the TestDriver GitHub App on your repository and sign the installation in to TestDriver — without sign-in the agent can only review by reading the diff.
View source on GitHub ↗