openclaw-pr-batch-sweep

name	openclaw-pr-batch-sweep
description	Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial one-line changes, UI, security, migrations, and high-risk changes must be excluded.
license	MIT
metadata	{"source":"https://github.com/vincentkoc/dotskills","version":"0.2.7","spec":"agentskills-v1"}

OpenClaw PR Batch Sweep

Purpose

Drive a continuing queue of real, low-risk OpenClaw contributor bug fixes through qualification, repair, proof, and landing. Work in batches of up to 20 without padding the batch with micro-patches, speculative cleanup, or risky surfaces.

Requires ghx, gitcrawl, gwt, and the OpenClaw maintainer, testing, autoreview, Crabbox, and ClawSweeper skills.

Read references/operator-selection-policy.md before selecting candidates. Read references/worker-contract.md before spawning sub-agents. Read and update references/decision-ledger.json so fresh runs inherit prior landed, rejected, closed, and explicitly skipped PRs.

Compose the repository skills instead of duplicating them:

• $openclaw-pr-maintainer for live GitHub evidence and mutations.
• $openclaw-landable-bug-sweep for proof, repair, and landing.
• $gitcrawl for discovery and duplicate clusters.
• $openclaw-testing, $crabbox, and $autoreview for validation.
• $clawsweeper for readiness labels and exact-head review evidence.

When to use

• The operator says next 20, continue the PR sweep, or asks for another batch.
• The operator wants contributor PRs reproduced, narrowed, repaired, tested, and landed.
• The queue must exclude drafts, maintainer-owned work, UI, security, SSRF, auth, config migrations, and high-risk changes.
• Prior accept/reject decisions should shape future candidate selection.
• Reuse a small retained worker pool so review scales without accumulating completed workers or creating noisy local process pressure.

Workflow

1. Recover and continue the existing queue.

   • Read recent thread state and the batch ledger.
   • Read auditWatermark when present. Use openPrThrough as the default floor for newly created PR discovery instead of rehydrating an unchanged live edge.
   • The watermark is not a terminal decision. An older unhandled PR may re-enter only when its head SHA or risk/readiness state materially changed; terminal ledger entries never re-enter.
   • Verify current main, live PR state, repo instructions, VISION.md, disk, and worktree health.
   • Keep a handled set containing merged, closed, rejected, ignored, draft, and explicitly skipped PRs.
   • Never recycle prior candidates merely because their metadata changed.

2. Discover broadly, then reject aggressively.

   • Start with gitcrawl; verify live state with ghx. If gitcrawl is stale, malformed, or unavailable, fall through immediately to live ghx.
   • Run discovery and hydration shell calls serially on the maintainer host. Do not fan out gitcrawl, ghx, or per-PR REST calls in parallel.
   • Fetch at least 100 open PRs. Widen toward 1000 when the strict filter yields fewer than 20.
   • Write discovery JSON to a file and set OPEN_PRS_JSON to that path. The ranker accepts either a raw PR array or gitcrawl's { "threads": [...] } envelope. It normalizes labels_json, author_login, and is_draft; do not strip those fields before ranking.
   • Combine handled_refs and explicit_skips into comma-separated HANDLED_PRS. Numbers, #123, and full pull-request URLs are accepted.
   • Run scripts/rank-candidates.mjs --input "$OPEN_PRS_JSON" --limit 40 --batch-size 20 --decision-ledger references/decision-ledger.json --exclude "$HANDLED_PRS" as a first-pass noise filter.
   • Set HYDRATED_PRS_JSON to a second JSON file, then hydrate the top 30-40 with scripts/hydrate-candidates.mjs --input <ranked.json> --output "$HYDRATED_PRS_JSON". It serially merges authoritative REST author association, file count, merge state, paginated file deltas, and live check rollups while retrying unresolved mergeability.
   • If process launch returns EMFILE, , or another file-descriptor exhaustion error, stop spawning workers and parallel shells immediately. Let retained lanes finish, then continue from the coordinator with one shell call at a time.

Inputs

• batch_size: default 20, maximum 20.
• repo: default openclaw/openclaw.
• explicit_skips: PR numbers or URLs the operator has excluded.
• handled_refs: merged, closed, rejected, ignored, or already-reviewed PRs.
• concurrency: default 2 retained qualification workers and 1 retained implementation worker; maximum 2 implementation workers.
• source_mode: discovery or provided-prs; default discovery.
• risk_overrides: explicit operator-approved exceptions only.

Outputs

• Candidate ledger with up to 20 qualified PRs and no padding.
• Per-PR evidence map, best-fix verdict, proof plan, and terminal action.
• Exact worktree/branch ownership for active implementation lanes.
• Landed PR URLs and SHAs, closed/rejected refs with reasons, CI/Testbox/Crabbox proof, and remaining blockers.
• Clean current main status after landing work.