Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →oliver-kriska/watch-pr
Watch an Elixir/Phoenix PR for new review comments (bot + human) and CI results via a background watcher that wakes Claude only on real events. Use after opening a PR or pushing, while waiting on CI or reviewers.
Passed 16 of 21 test cases with the skill, and 8 of 21 without it.
and 13 more in the full report
10 fixed9 passed either way5 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.
What are the default time limits for max duration, quiet period, and polling frequency when invoking PR watch without flags?
| Checked | Without skill | With skill |
|---|---|---|
| States default max duration is 2 hours. | Missed | Passed |
| States default quiet period is 15 minutes. | Missed | Passed |
| States default poll interval is 60 seconds. | Missed | Passed |
The instructions your model reads when the skill loads.
Use the elixir_phoenix_watch_pr plugin tool. Do not launch gh pr checks --watch, gh run watch, a foreground sleep loop, or the copied Claude watcher
script: none of those owns an Amp Orb keep-alive lease.
excludedChecks; they are
never counted as passing or failing required CI.--fix authorize neither action.--fix uses the same worker thread — the plugin serializes one concise
event turn at a time and directs that turn to the installed phx-pr-review
workflow for actionable review feedback or failed required CI. Validate the
cause before editing.Parse the PR number/URL and flags, then call:
elixir_phoenix_watch_pr {
"action": "start",
"pr": "<number-or-url>",
"checksOnly": false,
"fix": false
}
Map --checks-only and --fix to booleans. Map --max-hours,
--quiet-minutes, and --poll-seconds to maxDurationHours,
quietPeriodMinutes, and pollIntervalSeconds. Defaults are 2 hours maximum,
15 minutes quiet, and 60 seconds polling. Report the tool's initial snapshot
and then stop taking turns; the plugin wakes this thread only for actionable
failures or feedback and terminal outcomes.
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.