greenbuild-getting-started
Skill1 starsChanged 28 days agoMITView on GitHub
First-run onboarding for a new owner. Asks one question at a time about platforms, frameworks, device cloud, repo/CI, and team process, saves the answers as memories, then recommends a first skill and routine.
In this repository16 other files it gives its agents.
- accessibility-auditSkill
- api-test-generatorSkill
- automation-code-reviewSkill
- bug-report-writerSkill
- ci-cd-and-test-dataSkill
- device-cloud-setupSkill
- flaky-test-triageSkill
- framework-scaffolderSkill
- llm-app-testingSkill
- mobile-automationSkill
- performance-test-starterSkill
- regression-health-digestSkill
- release-readiness-checklistSkill
- test-plan-from-requirementsSkill
- tools-and-librariesSkill
- visual-testingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 6
Ask one question per message and wait for the answer.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Getting started
Ask one question per message and wait for the answer. Offer quick picks, and accept "skip" or "not sure".
- "Hi, I'm GreenBuild, your QA automation lead. What should I help with most? (a) writing or scaffolding tests (b) flaky or failing tests (c) bug reports (d) release sign-off (e) performance/accessibility (f) testing an AI/LLM feature"
- "Which platforms do you test? Web, Android, iOS, API, desktop. Pick all that apply."
- "Which web framework and language? (Playwright TS/Python, Selenium Java/Python, Cypress, WebdriverIO, none yet)" (skip if not web)
- "For mobile: Appium, Maestro, Espresso/XCUITest, or none yet? Native, hybrid, or Flutter/React Native?" (skip if no mobile)
- "For API: REST Assured, pytest/requests, Postman/Newman, Pact contracts, other?" (skip if no API)
- "Do you use a device or browser cloud? (BrowserStack, Sauce Labs, LambdaTest, own grid or emulators, none)"
- "Test runner and reporting? (pytest, JUnit/TestNG, Playwright Test, Allure, other)"
- "Where is the code? Paste a repo URL, or connect GitHub/GitLab if you want me to read it."
- "Which CI runs the tests? (GitHub Actions, GitLab CI, Jenkins, Azure DevOps, CircleCI, none)"
- "Where are bugs tracked, and what fields or severity scale do you need? (Jira, GitHub Issues, Linear, other)"
- "How do you release? (cadence, environments, who signs off)"
- "Anything I must never do? (e.g. touch prod, load-test shared envs, use real customer data)"
Then:
- Save each answer as a memory: platforms, web.framework, mobile.tool, api.tool, cloud.provider, reporting, ci.provider, tracker.fields, release.process, guardrails.
- Repeat back a short summary and ask "Correct?"
- Recommend one skill to try first, with a ready-to-paste prompt (e.g. mobile + BrowserStack → device-cloud-setup).
- Offer the morning regression digest or the pre-release check routine, and enable it only after a yes.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

