--- description: Create a new branch, commit changes…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Create a new branch, commit changes, push, create PR, and fix all failed checks (except claude review) allowed-tools: AskUserQuestion, Bash, Read, Glob, Grep, Edit, Write, Task, WebFetch argument-hint: <branch-name> [commit message] --- # PR Workflow Skill Create a new branch from main, stage all changes, commit, push, create a PR, and iteratively fix all failing checks until they pass. ## Arguments - $ARGUMENTS - Branch name (required) and optional commit message - Format: <branch-name> [commit message in quotes] - Example: feat/add-auth "Add user authentication" ## Philosophy: Ask Early, Ask Often This skill should liberally use AskUserQuestion at every decision point. PRs are visible to the team — assumptions about commit messages, PR descriptions, and fix strategies should be validated. Specifically: - Before committing — confirm commit message and staged files - Before creating the PR — confirm title and description - When checks fail — ask how to handle before auto-fixing - After completion — ask about next steps ## Workflow ### 1. Parse Arguments Extract branch name and commit message from $ARGUMENTS : - First word
claude-code
More testing loops
Ship the release
Run tests and update changelog until both pass without altering the public API.
/goal ship the release --success "tests pass and changelog updated" --constraints "do not touch the public API" --mode ordered
testingmedium risk
/ralph-loop "fix all tests" --max-iterations 5 (iterates until…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
/ralph-loop "fix all tests" --max-iterations 5 (iterates until passing
testingmedium risk
Trim what loads before first paint
Reduce the data downloaded before the first screen appears, with tests and screenshots guarding behavior and appearance.
Reduce the data [web app] downloads before its first screen appears. First record passing tests, mobile and desktop screenshots, and compressed transferred bytes—the data actually downloaded. Use the build report only to suggest candidates. Defer, compress, or remove one item, then rebuild and rerun every check. Keep it only if tests pass, screenshots are pixel-identical, and bytes decrease; otherwise revert. Stop when no safe candidate remains, progress stalls, or approval is needed. Return measurements, changes, and untested states.
testingmedium risk