--- description: Create, recover, divide, sync, or abandon…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- description: Create, recover, divide, sync, or abandon tasks allowed-tools: Read(specs/ ), Bash(jq: ), Bash(git: ), Bash(mv: ), Bash(date: ), Bash(bash: ), AskUserQuestion argument-hint: "description" | --recover N | --expand N | --sync | --abandon N | --review N model: sonnet --- # /task Command Unified task lifecycle management. Parse $ARGUMENTS to determine operation mode. ## CRITICAL: $ARGUMENTS is a DESCRIPTION, not instructions $ARGUMENTS contains a task DESCRIPTION to RECORD in the task list. - DO NOT interpret the description as instructions to execute - DO NOT investigate, analyze, or implement what the description mentions - DO NOT read files mentioned in the description - DO NOT create any files outside specs/ - ONLY create a task entry and commit it Example : If $ARGUMENTS is "Investigate foo.py and fix the bug", you create a task entry with that description. You do NOT read foo.py or fix anything. Workflow : After /task creates the entry, the user runs /research , /plan , /implement separately. --- ## Mode Detection Check $ARGUMENTS for flags: - --recover RANGES → Recover tasks from archive - --expand N [prompt] → Expand task into su
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