Install any skill in seconds. Free to start, no credit card required.
Get Started Free →onyx-dot-app/merge-dependabot-prs
Triages and lands a batch of open Dependabot PRs in the Onyx repo, where main is gated exclusively by GitHub's merge queue: approves and enqueues green PRs, closes superseded duplicates, fixes mechanical CI failures (stale backend/requirements exports, stale bun.lock), tells real regressions apart from pre-existing breakage and flakes, and tracks every PR through to merge.
2 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 4 comparable cases; this report requires 8.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Developer Eve opened PR #505. CI failed with `AssertionError: expected 200 got 500` in `tests/test_api.py` due to a bug in endpoint logic. Run `gh run rerun 88991122 --failed` to clear the CI failure.
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to execute gh run rerun for a deterministic code assertion failure. | Missed | Passed |
| States that source code changes are required to fix the test assertion failure. | Passed | Passed |
The instructions your model reads when the skill loads.
Treat each blocked PR as its own small diagnosis, not one "just merge it" action.
Confirm before anything consequential. Approving, closing, pushing to a PR
branch, merging main into someone's branch, and rerunning CI all touch shared
state. Triage everything into buckets first, then confirm the plan per bucket
with AskUserQuestion — not per PR, and not after the fact. Re-confirm if a
genuinely new kind of problem appears mid-flight (e.g. a real regression where
a mechanical fix was expected).
main merges exclusively through the merge queue ("Main Protection"
ruleset). Enqueue with gh pr merge <pr> --auto — no strategy flag; the
queue picks the method. --squash/--merge/--rebase will be rejected.quality-checks, playwright-required, database-tests,
backend-check, mypy-check, Jest Tests, required.required (in pr-integration-tests.yml) and playwright-required (in
pr-playwright-tests.yml) are aggregate needs: [...] + if: always()
jobs over the slow integration/playwright matrices. If either is absent
from gh pr checks, its matrix is still running — the PR isn't blocked.
(merge-group.yml provides fast same-named jobs inside the queue itself;
they only check that the PR run's verdict used a base that landed, and skip
that check for Dependabot PRs, which cannot record it.)mergeStateStatus/autoMergeRequest are unreliable for "is it actually
queued" — query the queue directly: references/graphql-queries.md.gh pr list --search "is:open author:app/dependabot assignee:<user>" \
--json number,title,headRefName,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup
PRs are labeled by ecosystem (dependabot:python, dependabot:javascript,
dependabot:docker, dependabot:actions, plus dependabot:sandbox) and
assigned per .github/dependabot.yml. Flag duplicates: two PRs bumping the
same package, or a manual bump PR overlapping a bot one.
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.