Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →archive228/broken-window-check
Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.
Passed 16 of 20 test cases with the skill, and 8 of 20 without it.
and 10 more in the full report
10 fixed8 passed either way4 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Before claiming a feature as 'done' at the end of the current session so that future sessions don't find a broken window, what verification technique should be applied to the current diff?
| Checked | Without skill | With skill |
|---|---|---|
| Applies adversarial verification on the current diff before claiming done | Missed | Passed |
The instructions your model reads when the skill loads.
Across shift-notes-driven sessions (see shift-notes), agents will sometimes mark a feature complete after unit tests pass — even when the feature is end-to-end broken. The next session opens the repo, sees a green git log, and builds on top of a broken foundation. By the time anyone notices, three features are stacked on the crack.
The check: before picking new work, exercise the most recently "completed" feature end-to-end. If it fails, treat it as your only job this session.
steps field on the feature, or the acceptance criteria in the spec.git revert the commit that claimed completion (do not force-push).not-done in the feature list.Do not pick new work on top of a broken previous feature. Ever.
The check must exercise the path the user actually takes. Anything less is theater.
| Feature shape | Valid check | Invalid check |
|---|---|---|
| Web UI button | Puppeteer/Playwright click → observe DOM | expect(handler).toHaveBeenCalled() |
| HTTP endpoint | curl the route → check status + body | Unit test on the handler function |
| CLI flag | Invoke the binary with the flag → observe output | Import the parser, assert on the AST |
| Background job | Trigger it → wait → assert side effect | Assert the job function returns |
test cases passed, vs 8 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.