All guides › By agent
By agentQA with Claude Code: install the skill, then ask in plain words
How Claude Code runs Kaloko: the skill it installs, what it may do without asking, what it asks first, the prompts that work, and how it reads reviewer feedback and the inbox.
Claude Code writes the feature anyway. With the kaloko skill it also walks the acceptance plan, captures the screens, evaluates the criteria, shares the canvas and later reads what the reviewer sent back.
The problem
Without a skill the agent improvises QA: it opens the page once, says "looks fine" and moves on. Nobody can see what it looked at.
What changes with Kaloko
The skill tells Claude Code when a walkthrough is due, what "done" means (validated scenario, every step captured or explained, evaluation and build run, the link posted), what it may do without asking (local and review environments, test data there, scenario mechanics) and what needs a person first (changing acceptance criteria, any production run, uploading).
How it works
- Install
npm install --save-dev kaloko, thennpx kaloko init --agent claude --org <your-org>copies the skill to.claude/skills/kalokoand createskaloko.config.yml.npx kaloko doctorchecks Chrome, token, environments and the evaluator key. - Ask
"Walk the acceptance plan of TASK-123 on local and share the result." The skill pulls in the references it needs: acceptance, execution, evaluation, environments, collaboration.
- Drive the browser your way
Claude Code uses the shared browser through a Playwright step script or a browser tool over MCP (the CDP endpoint is printed by
kaloko browser start). - Close the loop
after sharing, the skill reads
kaloko feedbackandkaloko inboxbefore continuing on the task. Optionally connect the MCP server so the agent reads runs and feedback as tools.
Skills and prompts
Walk the acceptance plan of TASK-123 with Kaloko on local and share the result into the PR.What did the reviewer return on the last run of TASK-123? Fix it and run again.Compare the latest run of checkout with the baseline and explain the differences.Expected outcome in each case: the commands the skill prescribes, a summary line, failing or unreviewed criteria with evidence, and links to the canvas; no production run without asking.
What you get
- A skill that encodes the rules once, so every task gets the same walkthrough.
- Runs, feedback and the inbox readable by the agent through the CLI or the MCP server at
kaloko.app/mcp. - A canvas the rest of the team can accept or return without touching the terminal.
FAQ
Does Claude Code need a browser tool?
No. Scripted steps run through Playwright inside the CLI; for judgement-driven steps a browser MCP or computer use helps, but kaloko capture --url works from the shell alone.
What does the agent send to the AI evaluator?
For criteria marked semantic, a reduced text outline of the page with e-mails and tokens masked. Criteria marked vision: true, and text answers the evaluator is unsure about, also send a scaled screenshot (or the criterion's crop) to the vision evaluator: Anthropic with your ANTHROPIC_API_KEY, or through Kaloko. evaluators: { vision: false } in kaloko.config.yml turns that off. Otherwise screenshots and raw HTML go only to your own Kaloko organization.
What it looks like
A real run of Kaloko on its own public pages, refreshed daily. This is the canvas your team gets.