cloud-factory-demo

Implement a fix or feature from a GitHub, Jira, Linear, or other issue-tracker issue by fetching issue context, inspecting the current codebase, making code changes, validating them, verifying visible UI behavior with the verify-behavior computer-use skill when applicable, opening a GitHub pull request, and reporting progress back to the original issue.

Triage an incoming GitHub, Jira, Linear, or other issue-tracker issue against the current codebase and related open issues, then return a structured decision with exactly one implementation-readiness state. Use whenever the user asks to triage, classify, assess, prioritize, or label an issue for implementation readiness, especially when an issue URL, key, or number is supplied in the prompt. For UI or interactive bugs, optionally invoke the verify-behavior skill as a cloud computer-use subagent to reproduce the issue before deciding.

Coordinate spec-driven development for a GitHub, Jira, Linear, or other issue-tracker issue marked ready-to-spec by using write-product-spec and write-tech-spec, creating PRODUCT.md and TECH.md, opening a pull request, and routing the issue onward.

Launch Oz cloud agents to reproduce bugs or verify features/fixes with video or screenshot evidence. Chooses Chrome/Puppeteer browser automation or desktop computer use, and for multi-story features fans out parallel story workers. Use whenever triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation, or any factory stage asks to verify UI/app behavior.

Sets up a beginner-friendly Oz cloud software factory that automatically triages new GitHub issues, specs issues labeled ready-to-spec, implements issues labeled ready-to-implement, reviews PRs, and verifies visible behavior with Oz computer-use subagents. Use when a user wants to install, configure, test, or understand the Cloud Factory demo in a repository of their choice.

Review a pull request diff and write structured feedback to review.json for the workflow to publish. Use when reviewing a checked-out PR from local artifacts like pr_diff.txt and pr_description.txt and producing machine-readable review output instead of posting directly to GitHub. For interactive or UI behavior that a diff cannot prove, optionally invoke the verify-behavior skill as a cloud computer-use subagent and fold its findings into the same review.json.

Daily outer loop that reviews human reactions to automated review-pr comments, synthesizes durable organizational knowledge, and opens a PR to update the review-pr skill when the feedback is worth remembering. Use when improving code-review quality from human feedback, running a scheduled review-skill retrospective, or incorporating maintainer corrections into review guidance.