← ClaudeAtlas

creating-pull-requestslisted

When to open a pull request in the DorkOS repo (review the pushed branch first, open the PR after it converges), how the automated review behaves (skip-review, review:light/deep, re-review), and how a PR lands through merge-tail and the merge queue, including what to do when it goes red or is ejected. Use when finishing a branch, opening a PR, deciding how much review a PR should get, requesting a re-review, or watching a PR until it merges.
dork-labs/dorkos · ★ 10 · AI & Automation · score 72
Install: claude install-skill dork-labs/dorkos
# Creating Pull Requests How DorkOS PRs are opened and how the automated Claude review behaves on them. This repo is routinely multi-agent, so the mechanics below keep PRs clean and the review loop cheap. ## When to use - You have finished a branch and are deciding when to open the PR. - You are about to open a PR (from an agent or by hand). - A PR already has review feedback and you want another pass once it is addressed. - You want to dial a PR's review up, down, or off. - A PR of yours is red, ejected from the merge queue, or not merging, and you need to know whether acting helps or only adds load. ## The order: review the branch, then open the PR The independent adversarial review runs **against a pushed branch, before a PR exists**. Opening the PR is the last step, not the first: 1. Build in an isolated worktree and run the local gates. 2. Push the branch. **Open nothing.** 3. A reviewer fetches and checks out that branch. It does not need a PR. 4. Findings, fixes, convergence. 5. Squash to one clean commit carrying one changelog fragment. 6. **Then** open the PR, already reviewed, so the repo's automated review spends its single pass on final content. Every reason below is a cost measured on 2026-07-27/28, not a preference: - **Merge churn.** A PR held open across review rounds watches `main` move under it. One night of that took roughly a dozen branch updates (the pre-queue rule, retired 2026-07-28) and still left a `DIRTY` PR needing a semantic confli