pull-request
Skill759 starsChanged 21 days agoMITView on GitHub
Use when opening a pull request on kuik, rewriting its description, or answering its automated review; prepares the branch, drafts a short readable description for the user to confirm, and keeps it in step with the branch.
- Commits and pushes
55 other projects use a version of this.
Adopted by
Most recently taken up by
- bjoern621/claude-skillstheir own version, first seen Nov 16, 2026
- neomjs/neo-agent-skillstheir own version, first seen Nov 15, 2026
- hanspeterdietiker/open-agent-skillstheir own version, first seen Nov 15, 2026
- theopenco/llmgatewaytheir own version, first seen Nov 15, 2026
- speakeasy-api/gramtheir own version, first seen Nov 13, 2026
- StephanMeijer/skillstheir own version, first seen Nov 10, 2026
Used with
Projects with it also use issue-campaign, contracts and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
samchonSkillissue-campaign
Defines the default solo repository-wide issue campaign for typia: exhaustive discovery, lead-vetted issue publication, one unified CI-validated implementation pull request per cycle, solo Self-Review, and repeated rediscovery until a full clean round. Use for broad audits, many issue candidates, or repeated issue-to-pull-request campaigns unless the user explicitly requests parallel or multi-agent execution; do not use for one already-defined issue or an ordinary pull request.
Also in 3 projects that use this
AnthropicSkillcontracts
Answer a question across a corpus of contract documents with verified citations. Use when the user asks what a contract says, which contracts have a clause, what changed between amendments, or any question that needs reading and citing across a set of contract files. The corpus must be on the local filesystem (see README).
Also in 3 projects that use this
mfang0126Skilldevelopment
Full-stack development workflow skill. Guides the complete cycle from understanding requirements to shipping code via PR with Preview validation.
Also in 3 projects that use this
dragonflydbSkillbenchmark
Benchmark Dragonfly (and compare against Valkey/Redis) on local or remote cloud instances, then produce a performance + memory report with charts and a raw-data appendix. Use this whenever the user runs /benchmark, or asks to benchmark / load-test / measure throughput, QPS, latency, or memory efficiency of Dragonfly or another Redis-compatible server, to compare Dragonfly vs Valkey or Redis, or to generate a benchmark report. Trigger it even when the user just describes the goal ("see how fast Dragonfly is on this box", "compare memory per key vs Valkey") without saying the word "benchmark".
Also in 4 projects that use this
VercelSkillgh-stack
Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.
Also in 3 projects that use this
carapace-shSkillgit
Use when working with Git — object model, references, index, branching, merging, rebasing, remotes, diffs, config, hooks, worktrees, submodules, and plumbing commands. Triggers on: "git", "git branch", "git commit", "git merge", "git rebase", "git checkout", "git stash", "git reset", "git submodule", "git worktree", "git blame", "git bisect", "git reflog", "git hooks", "git config".
Also in 3 projects that use this
Other versions55 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 55
- samchon/typia★ 6ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- werf/werf★ 4.7ksame name
- basicmachines-co/basic-memory★ 4.6ksame name
- PaulWoitaschek/Voice★ 3.3ksame name
- event-catalog/eventcatalog★ 3ksame name
- heyitsnoah/claudesidian★ 2.6ksame name
- samchon/nestia★ 2.2ksame name
- theopenco/llmgateway★ 1.7ksame name
45 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- acceptance-scenariosSkill
- decision-noteSkill
- e2e-specSkill
- release-acceptanceSkill
- release-notesSkill
- test-outlineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. 0 are common, 7 are distinctive, and 16 are very specific to this project.
0
Common
Most of the 50 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
16
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 11
Every step that writes on GitHub (create, edit, comment, resolve) waits for the user's explicit go: show the text first, then run the …
- Very specific: line 28
Check git log --stat origin/main..HEAD: every test file comes from a test commit and no feat commit touches one.
- Very specific: line 30
No commit that only indexes or fixes the previous ones: before the PR opens, fold a fix into its commit with git commit --fixup=<sha>, then …
- Very specific: line 43
Before the pull request opens, a fresh reviewer agent reviews the whole branch (origin/main...HEAD): spec conformance and the interactions …
- Distinctive: line 53
Write for a reviewer who has 2 minutes.
- Distinctive: line 67
Add a line only when it has something to say: no empty or "None" section.
- Very specific: line 69
When the PR answers an issue, end the introduction with Closes #N (or Part of #N): GitHub closes it on merge and the reader gets the …
- Very specific: line 71
When the PR changes what users see on upgrade (a chart value renamed or removed, a CRD field, a default, a behaviour), add Upgrade notes: …
- Very specific: line 74
When the PR decided a spec reading (where docs/v3/ is silent or ambiguous) or a behaviour choice, add Decisions: after the list, one line …
- Very specific: line 78
Every "What to look at" bullet that rests on a spec section or a note links it by its absolute URL …
- Distinctive: line 83
Never say that the tests or the lint pass: CI runs them and shows the result.
- Very specific: line 85
Never paste the test outline: the Test outline comment workflow posts the cases the PR adds and removes as a comment, and updates it on …
- Distinctive: line 107
Write the body to a file first: quoting a long body inline breaks.
- Very specific: line 118
Every time the branch changes (a commit added, dropped, split or amended), re-read the description against git log origin/main..HEAD and …
- Distinctive: line 139
When CodeRabbit answers that it is rate limited or out of review quota despite the slot (a review asked by hand, or the quota lower than …
- Very specific: line 146
Never rewrite the branch under review (no rebase, amend or force-push): the incremental review would lose its base.
- Distinctive: line 149
Do not push while a review runs: CodeRabbit drops it ("head changed") and must be asked again.
- Very specific: line 151
Read the body of each review, not only its threads: the quiet profile folds findings into the review body without opening a thread.
- Very specific: line 166
When the review is over, autosquash in place and force-push once (--force-with-lease).
- Very specific: line 175
Never origin/main or main in that command: another session may have fetched a newer main, and the branch would silently move onto it.
- Very specific: line 184
Add the e2e-ready label (gh pr edit <n> --add-label e2e-ready, no question asked) only once the review is over, the final e2e test commit …
- Very specific: line 199
Add the label only once the E2E run of the last push has finished (it fails within seconds without the label: gh pr checks <n> shows it).
- Very specific: line 236
Before any push to a PR whose auto-merge is enabled (a fix for a failed check, an autosquash, a rebase), disable it first, alone in its …
“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Pull request
Target: $ARGUMENTS (an existing PR number, or empty to open one from the current branch).
Every step that writes on GitHub (create, edit, comment, resolve) waits for the user's
explicit go: show the text first, then run the command.
A pull request stays issue-sized, about 30 specs at most, whether it answers an issue, a
request or one piece of an epic cut into several, and is followed with a task list: see
the test-outline skill.
1. Prepare the branch
- Branch off a fresh
origin/main(git fetch originfirst); never mergemaininto the branch. Rebase onmainonly when needed (step 6):gh pr merge --rebasereplays the commits onmainanyway. - Per component, a
test(<scope>): ...commit with its specs, then thefeat(<scope>): ...commit that makes them green (tests.md). Thefeatcommit carries the docs and the line in any index (AGENTS.md, a README), and touches no*_test.gofile or test helper package. A component without specs (a skill, a task) is one complete commit. - Check
git log --stat origin/main..HEAD: every test file comes from atestcommit and nofeatcommit touches one. The reviewer checks the same thing. - No commit that only indexes or fixes the previous ones: before the PR opens, fold a fix
into its commit with
git commit --fixup=<sha>, then autosquash in place as in step 5. Once it is open, fixes stayfixup!commits until the review is over (step 5), and so does the regression spec of a bug in the branch's own code: afixup!of thetestcommit of its component. The exception is a bug in code no commit of the branch owns: the fix is its own commit, and its regression spec its owntestcommit after it, subjecttest(<scope>): add regression specs for <what>, body naming the review, the component or commit subject of the fix (never a sha: hashes change on rebase) and that the specs pin the fix (tests.md). The description names it in one line. A late batch of review fixes is the other exception (step 5). Review fixes need no approval; a fix in a shared package (internal/registry/*,internal/status/*,internal/auth/*,internal/routing/*,internal/imagepath,internal/config) lands first in its own pull request. - Before the pull request opens, a fresh
revieweragent reviews the whole branch (origin/main...HEAD): spec conformance and the interactions between components. Thespec-revieweragent reviews the outline only; areviewerreviews eachfeatcommit as it lands; CodeRabbit reviews the pull request last. The Claude code-review plugin is not used (0014). - Conventional commit subjects with the scopes of
.conform.yaml; the PR title is the subject of the main commit, or a subject that covers them all.
2. Draft the description
Write for a reviewer who has 2 minutes. The shape:
<1 to 3 sentences: what the PR does and why, in plain words.>
What to look at:
- **<Topic>**: <one line on what changed there, or the choice to weigh in on>.
- **<Topic>**: <...>.- The introduction says what the PR brings, not how the diff is organised.
- The list names the topics worth a reviewer's attention (a mechanism, a trade-off, a risky file), one line each, 3 to 7 entries. It never restates the commits or the diff.
- Add a line only when it has something to say: no empty or "None" section. A known limit (what the PR deliberately leaves out) goes in the list, or in one sentence after it.
- When the PR answers an issue, end the introduction with
Closes #N(orPart of #N): GitHub closes it on merge and the reader gets the context from the link. - When the PR changes what users see on upgrade (a chart value renamed or removed, a CRD
field, a default, a behaviour), add
Upgrade notes:after the list, 1 to 3 lines. It is what the release notes are written from. - When the PR decided a spec reading (where
docs/v3/is silent or ambiguous) or a behaviour choice, addDecisions:after the list, one line each with the link to the spec heading: the reviewer weighs in there. - Short sentences, one idea each. A block of dense prose is a failure: split it or cut it.
- Every "What to look at" bullet that rests on a spec section or a note links it by its
absolute URL (
https://github.com/enix/kube-image-keeper/blob/main/<path>#<heading-slug>): GitHub resolves a relative link against the PR URL and it 404s. Link a file the PR adds onmaintoo, marked "added by this PR": the link works once merged, and until then the file is in the diff. Link an issue or a PR by its URL. Link instead of paraphrasing. - Never say that the tests or the lint pass: CI runs them and shows the result. Name only a check CI does not run (a manual test on a cluster, a case tried by hand), in one line.
- Never paste the test outline: the
Test outline commentworkflow posts the cases the PR adds and removes as a comment, and updates it on every push.
Avoid:
- Template check-lists (
- [x] tests pass,- [x] docs updated): CI already says it. - A commit-by-commit summary or a count of changed files: the diff shows it.
- Promotional wording (robust, comprehensive, seamless) and openers like "This PR aims to".
- References to the conversation that produced the PR ("as discussed", "per the agent"): the reviewer was not there.
- Pasted CI or test output: one line when a result matters.
- Markdown headings: the introduction and the list are enough.
Show the draft to the user and wait. Apply their changes, show again, until they confirm.
3. Open or update the PR
gh pr create --title '<subject>' --body-file <file> # new PR, ready for review
gh pr edit <n> --body-file <file> # existing PRWrite the body to a file first: quoting a long body inline breaks.
Opening a PR costs a CodeRabbit review, and so does every @coderabbitai review or
full review. The quota is shared by every session on the machine, so take a slot first,
alone in its command: hack/coderabbit-slot.sh <n or branch>. Exit 0: the slot is yours, go
on at once. Exit 1: it prints when the next slot frees up; wait until then in the
background, never in a loop, and run it again. Ask for one review per batch of fixes, never
one per fixup.
4. Keep it in step
Every time the branch changes (a commit added, dropped, split or amended), re-read the
description against git log origin/main..HEAD and the diff. When a sentence no longer
holds, draft the fix, show it, and edit after the user confirms. A description that
describes a dropped file misleads the reviewer and CodeRabbit alike.
5. The automated review
- As soon as a review is due (the PR opened,
@coderabbitai reviewposted), runhack/wait-coderabbit.sh <n>in the background and go on. When it exits 0, the review and its check are done: triage it at once (below). When it exits 3, CodeRabbit is rate limited: follow the rate limit bullet below. When it exits 1, no review came within the hour: tell the user. - CodeRabbit reviews once when the PR opens. For later commits, comment
@coderabbitai review. After a force-push, comment@coderabbitai full reviewinstead only when the PR's own patch changed (the patch check of thee2e-readybullet below differs: fixups pushed while it was rate limited, a conflict resolved in the PR's lines): the incremental review lost its base. A rebase that only bringsmain's changes, or an autosquash of reviewed fixups, needs none, and CodeRabbit answers it "No files to review". - CodeRabbit answers only comments that mention
@coderabbitai(chat.auto_reply: falsein.coderabbit.yaml), a top-level comment or a reply in one of its threads alike. - When CodeRabbit answers that it is rate limited or out of review quota despite the slot (a review asked by hand, or the quota lower than the ledger thinks), never ask again in a loop: the quota is shared by every session. Report it to the session that coordinates the others (the user when there is none), which checks the remaining capacity once for all and says when to ask again; ask once more then. If it still cannot review, the PR waits: only the user's explicit waiver, possibly relayed by the coordinating session, lets it go on without CodeRabbit.
- Never rewrite the branch under review (no rebase, amend or force-push): the incremental
review would lose its base. A fix is a
git commit --fixup=<sha>pushed as is. Theconformcheck stays red onfixup!commits, which keeps the PR from merging unsquashed. - Do not push while a review runs: CodeRabbit drops it ("head changed") and must be asked again.
- Read the body of each review, not only its threads: the
quietprofile folds findings into the review body without opening a thread. - Triage each comment: fix it (a
fixup!commit), or accept it as a limit and say so in the description. An exception is a late batch of fixes touching code that several later commits rewrite: regression pairs at the end of the branch instead (tests.md). Resolve a thread once its fix is pushed. Reply only when resolving without a fix: one sentence on why. Post the reply yourself: the outbound hook asks the user before every write on GitHub. No thread is left open at the merge: this lists the open ones, and must print nothing.
gh api graphql -f query='query { repository(owner: "enix", name: "kube-image-keeper") { pullRequest(number: <n>) { reviewThreads(first: 100) { nodes { id isResolved path } } } } }' --jq '.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved | not)'When the review is over, autosquash in place and force-push once (
--force-with-lease). In place means on the commit ofmainthe branch started from, not on the currentmain: the branch does not move, andgit diff <head before> HEADstays empty. Print that commit withgit merge-base origin/main HEAD, then squash on its sha:GIT_SEQUENCE_EDITOR=: git rebase -i --autosquash <sha>Never
origin/mainormainin that command: another session may have fetched a newermain, and the branch would silently move onto it. Before the force-push, check thatgit diff <head before> HEADprints nothing; if it prints anything, the base moved or the content changed: go back withgit reset --keep <head before>and redo it on the sha.Then run
task check-commitsin the background (it takes minutes): in a scratch worktree, every commit builds and vets, and everyfeatcommit passestask test. Go on meanwhile, and read its result before the force-push. Catching up withmainis not part of the autosquash (step 6).Add the
e2e-readylabel (gh pr edit <n> --add-label e2e-ready, no question asked) only once the review is over, the final e2etestcommit pushed and the branch autosquashed, and enable auto-merge right after it (step 6). The review is over when both hold, checked, never assumed:- CodeRabbit has reviewed the PR's own changes as they stand:
hack/coderabbit-reviewed.sh <n>, run from the PR's worktree, exits 0. It compares the diff againstmainof CodeRabbit's last reviewed commit withHEAD's (git patch-id --verbatim: line offsets do not count, whitespace does), so an autosquash of reviewed fixups, or a rebase that only bringsmain's changes, needs no new review. Exit 1: ask for a review. Exit 2: it cannot tell, report it. A "Review rate limited", "Review in progress" or "Review skipped" status is not a review. Only the user's explicit waiver, possibly relayed by the coordinating session, lifts this point. - The open threads query above prints nothing.
Add the label only once the
E2Erun of the last push has finished (it fails within seconds without the label:gh pr checks <n>shows it). Both runs share one concurrency group: a label added while the push's run starts can get its own run cancelled.The required
E2Echeck fails until the label is there. Skip it when the PR changes no path the suite depends on (the list in.github/workflows/e2e.yaml):E2Epasses without it. The suite then runs once. If it fails, pushfixup!commits:E2Efails at once without running the suite until the next autosquash and force-push, which runs it again.- CodeRabbit has reviewed the PR's own changes as they stand:
6. Merge
Rebase on main only when GitHub cannot merge (mergeStateStatus is DIRTY) or the
branch needs something main brought: git fetch origin first, rebase on origin/main,
check the rebase with git range-diff ORIG_HEAD...HEAD, push it with
--force-with-lease, then wait for the checks again. Ask @coderabbitai full review only
when the PR's own patch changed (the patch check of step 5): a rebase that only brings
main's changes needs none.
Enable auto-merge at the moment the e2e-ready label goes on (step 5), under the same
conditions: the review is over, checked as step 5 says. A PR that needs no label gets it
once those conditions hold. The checks need not be green yet. Run it alone in its command:
the outbound hook asks the user first, and their confirmation is the go to merge (they may
want to test the PR before giving it). Pin the head the user saw, so a later push cannot be
merged on the same go. When CodeRabbit's review was waived, say so in the message that
precedes the command: the prompt itself does not. The sha is the full 40 characters, printed
by git rev-parse HEAD in its own command: gh rejects a short one.
gh pr merge <n> --auto --rebase --match-head-commit <full HEAD sha>GitHub merges once Conform, Test and E2E pass and no review thread is open. Follow it
in the background until gh pr view <n> --json state,mergedAt shows the merge. Wait for
checks with gh pr checks <n> --watch run in the background, here and in every step, never
with a sleep loop:
- Before any push to a PR whose auto-merge is enabled (a fix for a failed check, an
autosquash, a rebase), disable it first, alone in its command:
gh pr merge <n> --disable-auto. Otherwise GitHub merges as soon as the checks pass, before CodeRabbit sees the change. Then push, wait until CodeRabbit has reviewed the PR's own changes as they stand (the patch check of step 5), and enable auto-merge again: the outbound hook asks the user, as the first time. - Auto-merge stalls: every required check is green and
mergeStateStatusisCLEAN, yet 10 minutes later the PR is still open. GitHub re-evaluates auto-merge only on an event of the pull request, and a check run cancelled by a concurrency group can make it miss the last one. The user's go covers this merge, for the head they saw only: rungh pr merge <n> --rebase --match-head-commit <the full sha auto-merge was enabled on>, and tell the user auto-merge stalled.
Confirm the merge with gh pr view <n> --json state,mergedAt. If that call is refused, ask
the user to type ! gh pr view <n> --json state,mergedAt in the Claude Code prompt (the
! prefix runs it in the session): never report a merge you could not confirm.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

