merge-open-prs
Review and merge all open PRs/MRs in ONE repo after checking CI.
Skill by PlatformRelay
Chalk Labs
Need help deploying merge-open-prs?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/platformrelay-merge-open-prs
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/merge-open-prs
What's inside
- Skill name
merge-open-prs- Description
- Review and merge all open PRs/MRs in ONE repo after checking CI. PRs authored by the maintainer (the authenticated operator) are trusted — green CI is enough to merge, no deep code analysis. PRs from any other contributor get a full /tech-review and merge only on APPROVE + green CI. Per-repo only; never merges a red, pending, or conflicted PR. Use when the operator says "merge my open PRs / clear the PR queue / review and merge the open MRs in <repo>".
- License
- MIT
- Instructions
- 59 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# merge-open-prs — clear a repo's PR queue safely Operates on **one repo** (the repos are independent — never batch across repos). It merges what's safe, reviews what isn't, and never merges a red, pending, or conflicted PR. Merging here is authorized by the operator invoking this skill. ## Who counts as "the operator" (trusted) The maintainer = the **authenticated GitHub user**. Resolve once: `gh api user -q .login`. A PR is trusted (the operator's own) if its author login equals that, or its commits are authored by `Konrad Heimel <konrad.heimel@gmail.com>` / `konih`. **Anyone else is an external contributor — the careful path.** If you can't confidently tell, treat it as external. ## Step 1 — enumerate open PRs (target repo) ```bash cd <repo> gh pr list --state open --json number,title,author,isDraft,mergeable,mergeStateStatus,reviewDecision ``` Skip drafts. Record author + number + mergeable state for each. ## Step 2 — check CI (mandatory for EVERY PR, including the operator's own) ```bash gh pr checks <n> # every required check must be green gh pr view <n> --json mergeable,mergeStateStatus # must be MERGEABLE, not CONFLICTING/BEHIND ``` If any required check is failing or pending, or the PR isn't cleanly mergeable → **skip it**, report why. "After checking CI" is the whole point — a red or pending PR is never merged. ## Step 3 — classify and gate - **Operator's own PR (trusted):** CI green + mergeable → **eligible to merge, no deep analysis** (operator's explicit policy: their own code is trusted). Still glance at title/scope; per the adversarial-collaboration ethos, if something looks obviously wrong or risky, say so before merging — but default to merge. - **External contributor's PR:** run `/tech-review` (or the repo's review skill — `/mkurator-review`, `/kollect-mr-review`) in fresh context against the PR branch. Merge **only** if the verdict is **APPROVE and CI is green**. On REQUEST CHANGES / BLOCK: **do not merge** — post the findings as a PR comment (`gh pr comment`, never `--approve`) and report it as needs-changes. ## Step 4 — present the plan, then merge the eligible ones Show the operator the plan first: which PRs will merge, which are skipped (with reason), which external ones need changes. Then merge each eligible PR with the workspace default — **Rebase and merge** (linear history, no squash, no merge commits), unless the repo's own `CONTRIBUTING` narrows it: ```bash gh pr merge <n> --rebase --delete-branch ``` After each merge, in that repo's `agent-context/`: move the lane to **Integrated** on its OPERATOR-BOARD, and clear any matching "merge PR #<n>" task from its INBOX. ## Step 5 — report (per repo) One line per PR: **MERGED** · **SKIPPED** (red/pending/conflict) · **NEEDS-CHANGES** (external; findings posted). End with the repo's new `origin/main` HEAD. ## Do not - Merge a PR with red/pending CI or merge conflicts (not `MERGEABLE`). - Merge an **external** contributor's PR without a passing `/tech-review` (APPROVE). - Batch across repos — one repo per run. - Force-merge, `--admin`, or override branch protection to push a merge through. - Merge a draft PR, or skip the CI check on the operator's own PRs.
From PlatformRelay/Kaddy, MIT.
More from PlatformRelay/Kaddy
- 0.497score
agent-loop
PlatformRelay
Start or resume implementation in one PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-auto
PlatformRelay
Autonomous variant of /agent-loop for ONE repo: thin coordinator + parallel implementer subagents + a coordinator-dispatched INDEPENDENT reviewer, plus an…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-local
PlatformRelay
Maximum-autonomy variant of /agent-loop-auto for ONE repo: no PRs — each lane is gated by a coordinator-dispatched INDEPENDENT reviewer, then a serialized…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
brainstorm
PlatformRelay
Structured diverge → cluster → converge ideation that prevents premature fixation on the first idea.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
changelog
PlatformRelay
Turn gitmoji-conventional commit history into categorized, user-facing release notes for a PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
design-architecture
PlatformRelay
Design a change and record the decision: ADR/AgDR, C4 sketch, weighted trade-off matrix, or a spec-first contract.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
roast
PlatformRelay
Roast me — adversarial critique of a plan, design, or diff to find where it breaks, via pre-mortem, red-team, and steelman-then-destroy.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
security-review
PlatformRelay
Dedicated data-flow security pass over a diff or a repo — deeper than the security dimension of /tech-review.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
tech-review
PlatformRelay
Review a lane/branch before opening (or while awaiting) a PR in any PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
write-story
PlatformRelay
Turn an epic, feature idea, or vague ask into INVEST-compliant vertical-slice stories with Given-When-Then acceptance criteria, mapped onto the target repo's…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
handover
PlatformRelay
Wrap up a session cleanly and produce a copy-pasteable prompt to start the NEXT one.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
operator-inbox
PlatformRelay
Scan each PlatformRelay repo's INBOX independently and give the operator a per-repo digest of what needs them — decisions (with options), operator tasks…
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 20, 2026 (3 months ago)
- Last release
- Jul 21, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/PlatformRelay/Kaddy
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from PlatformRelay
- 0.497score
agent-loop-auto
PlatformRelay
Autonomous variant of /agent-loop for ONE repo: thin coordinator + parallel implementer subagents + a coordinator-dispatched INDEPENDENT reviewer, plus an…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-local
PlatformRelay
Maximum-autonomy variant of /agent-loop-auto for ONE repo: no PRs — each lane is gated by a coordinator-dispatched INDEPENDENT reviewer, then a serialized…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
brainstorm
PlatformRelay
Structured diverge → cluster → converge ideation that prevents premature fixation on the first idea.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
changelog
PlatformRelay
Turn gitmoji-conventional commit history into categorized, user-facing release notes for a PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
design-architecture
PlatformRelay
Design a change and record the decision: ADR/AgDR, C4 sketch, weighted trade-off matrix, or a spec-first contract.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop
PlatformRelay
Start or resume implementation in one PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get merge-open-prs running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
merge-open-prs skill. Agent Mart. https://agentmart.dev/skills/platformrelay-merge-open-prs (last updated 2026-10-24)