Loop/looptestinglow riskbeginnersafety C · 70

Work through TODO, turn tests green

Implement each unchecked TODO item, run tests until they pass, then check it off; stop when the list is empty.

prompt
→ Claude
/loop implement the next unchecked item in TODO.md, run npm test until it passes, check it off; stop when the list is empty
claude-code

Source: adrianfzh

More testing loops

Stabilize flaky tests for good

Loop/goalForward Futurenew

Measure the flakiness, fix one root cause at a time, and stop after a defined streak of stable full-suite runs.

prompt
→ Claude
Run [test suite] [N] times under the same conditions and list tests whose result changes. Fix the most frequent flake at its root cause—shared state, timing, ordering, or an external dependency—never with a blind sleep or retry. Run that test [N] times, then rerun the full suite. Repeat until [N] consecutive full-suite runs pass, progress stalls, or approval is required. Return each flake, root cause, fix, evidence, and justified quarantine.
testingmedium risk

Trim what loads before first paint

Loop/loopForward Futurenew

Reduce the data downloaded before the first screen appears, with tests and screenshots guarding behavior and appearance.

prompt
→ Claude
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

Get the fix to score 90+

Loop/goalnew

Run verify commands and benchmark checks until the target code scores 90 or higher on the benchmark, stopping after 5 attempts.

prompt
→ Claude
/goal the transcript reports a line matching SCORE: <n>/100 (threshold: 90, gate: pr) with n >= 90 for <slug> on branch <branch>, after <(bugfix) the REPRODUCE test is shown failing on unfixed code and passing on the final code, and> <verify commands, comma-separated> <(hot-path) and make bench-compare> all pass on the final code, or stop after 5 fix rounds
testingmedium risk