Run repeatable QA journeys across a project’s website, browser extension, or Android flows. Reports distinguish passed, failed, and blocked cases, include the Git revision, and preserve screenshots privately for review and follow-up.
This skill should be used when user asks to "run QA", "verify real playback", "test provider connections", or "check website, extension or Android flows" with tracked journeys.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Read .agents/skills/qa/SKILL.md and .agents/qa/config.json, then run project-qa run --root <repo>. If absent, use setup. --filter <id-substring> limits a follow-up run. --base-url <url> selects a temporary website target without editing project settings. Check report.json for the effective baseUrl and tested revision, then confirm the browser destination; API and auth URLs remain separately configured.
Use deterministic scripts. Interactive investigation can repair a failed journey, then put repeatable steps in its tracked suite. Never replace failed live behavior with mocked success.
Reports distinguish pass, fail and blocked, record Git revision, and keep screenshots private. Exit 0 means selected cases passed, 1 means failure, 2 means blocked. Report omitted cases and configured gaps separately. A passing journey proves its assertions, not uninspected visual quality or runtime health. For a UI audit, use the installed ui-regression skill when available and report functional, rendered-quality and runtime verdicts separately.
Read sessions before recovering login, telemetry before production traffic, and surface requirements for relevant components. Runner API defines executable cases and optional browser-network-cli diagnostics, including installation when needed.
Verify cleanup of created data and tabs. Keep saved sessions for the next run. Do not close personal browser tabs, log out providers after each test, or run suites sharing a stateGroup concurrently.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Format responses for readers who benefit from concise, visible steps and low-friction starts. It puts the answer first, breaks work into short numbered actions, tracks progress, and adds brief educational notes around code changes while keeping secondary details separate.
Plan and assess how AI assistants discover and recommend a product to buyers who have not heard of it. Organize buyer questions, review answers and cited sources, identify content or access gaps, and define a repeatable way to measure visibility and customer outcomes.
Use this skill to automate browser tasks such as opening websites, reading page content, clicking controls, filling forms, signing in, extracting data, and taking screenshots. It explains a snapshot-based workflow for interacting with pages and handling tabs and waits.
Build, debug, or review applications built with Cloudflare’s Agents SDK and the `agents` package. It covers agent state, routing, chat, scheduled and durable work, and integrations, while consulting current Cloudflare documentation for implementation details.
Use this skill to plan and build web interfaces with a visual direction tied to the project. It guides choices for color, typography, layout, motion, and interface text, then encourages a review against the brief so the result feels deliberate and specific.
Standardize web app sign-in and account flows with shared session rules, email and Google login adapters, and an optional auth panel. Use the guidance to simplify signup, recovery, and return navigation while keeping native and TV integrations clearly identified as pending validation.