Install any skill in seconds. Free to start, no credit card required.
Get Started Free →elie222/pr-watch
Take an open pull request to green — wait for CI, triage failing checks, and answer review-bot comments — using one backgrounded observation per cycle.
Passed 8 of 14 test cases with the skill, and 4 of 14 without it.
and 8 more in the full report
8 fixed5 passed either way8 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
Job ID 987654321 failed in CI on PR #110. What specific command inspects trimmed failure logs and server startup diagnostics for this job?
| Checked | Without skill | With skill |
|---|---|---|
| Invokes pr-digest with the --logs flag followed by the job ID | Missed | Passed |
The instructions your model reads when the skill loads.
Take the PR on the current branch (or the number you were given) to a clean state: every check terminal and passing, every review comment answered.
pr-digest, shipped next to this file, does the observing. Use it instead of
hand-rolling gh api calls — it collapses check runs, statuses, and review
threads into a few lines, and re-deriving that each cycle is where this loop
leaks most of its tokens. The Bash tool's directory is not always the repo root,
so resolve it once:
PRD="$(git rev-parse --show-toplevel)/.claude/skills/pr-watch/pr-digest"
Run "$PRD" --watch with run_in_background: true. It reports a failed,
cancelled or timed-out check on the exact head SHA
immediately, even while other checks are pending. Otherwise it waits for
checks to settle. At its wait deadline it prints WAIT_LIMIT and names
the pending checks; that deadline is not itself a CI failure. You are re-invoked when it exits.
Never wait in the foreground. sleep is blocked and an until loop is
killed at the execution tool's timeout, costing an error round-trip plus a
retry without producing any signal. One backgrounded call replaces the poll.
Read the VERDICT line and act:
| verdict | do |
test cases passed, vs 4 / 14 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.