Every screen of the flow, approved on one canvas.

How it works

1. Acceptance plan

   An ACCEPTANCE.md next to the task says what each screen must achieve. A scenario.yml turns it into steps, branches and criteria the CLI can run.

2. Walk

   A Playwright script, an agent with a browser or computer use, or a person walks the flow in a shared browser. Every step is captured the same way: full-page screenshots on desktop and mobile, rendered HTML, console errors, and e-mails from your test mailbox (Mailpit).

3. Check

   Countable criteria — elements, texts, prices, metadata, overflow — are checked in the live page and reported with evidence. Criteria that need judgement are answered by an AI evaluator from a reduced text outline of the page. It returns a probability; QAwalk turns it into pass, fail or needs review. The default evaluator is JEV by TypeSafe and it can be swapped.

4. Canvas and approval

   The run becomes a canvas: screens, branches, tested locales, metadata and evidence for every criterion. Reviewers approve a step or reject it with a note. The agent reads the notes with qawalk feedback and fixes them in the next run.

What the canvas shows

• Desktop and mobile screenshots of every step, plus e-mails and third-party screens
• Pass, partial or fail for each criterion, per locale and viewport, with the evidence
• Page metadata: title, description, canonical, hreflang, Open Graph, JSON-LD, microdata
• Branch, commit, author, PR and environment of every run; the history of the scenario and what changed since the previous run
• A link to a specific step and criterion you can send to colleagues in your organization

Install into your project

QAwalk runs where your code and your agent are. The service stores and versions the results, shows the canvas and collects approvals.

1. Add the CLI to the project

   npm install --save-dev github:sinfin/qawalk#v0.1.0

   Copy

   Proof of concept: the repository is private. Ask Sinfin for access.

2. Create the config and install the skill

   npx qawalk init --agent claude --org <your-org>

   Copy

   The skill is copied to .claude/skills/qawalk. You can install it as a plugin instead: /plugin marketplace add sinfin/qawalk.

3. Create your organization and a token

   Create an organization; you become its admin. The start page offers a tester token in one click, later you find it under Settings → API tokens. Put it into the project .env:

   QAWALK_TOKEN=qwk_…
   TYPESAFE_API_KEY=…   # optional: semantic evaluator

   Copy
4. Run and share

   npx qawalk start --scenario docs/tasks/TASK-123/qa/scenario.yml --env local
   npx qawalk walk        # playwright steps; agent/manual steps: qawalk capture
   npx qawalk evaluate
   npx qawalk share

   Copy

   Or ask your agent: “Walk the acceptance plan of TASK-123 with QAwalk on local and share the result.”

Data & security