Skip to content

moonlight-lupin/agent-skills / plugins/dev-pipeline/skills/review-commit

review-commit

Verified

Use when the user says 'review loop N times', 'build then review', 'fix and re-review', 'review loop until clean', 'have cursor build, codex review', or wants the dev-pipeline review stage: a two-axis single pass (Standards + Spec, parallel, never merged) FIRST, then a budgeted confirm-round loop on the fix diffs until no BLOCKING/MAJOR is open, then the commit/deploy gate — three-reviewer gate before live deploy, release hygiene before tagging. Also triggers: 'two-axis review', 'confirm rounds', 'review diff until SHIP', 'N confirm rounds', ship gate.

FileKindSize
SKILL.mdexecutableskill md6.8 KB
references/background-build-polling.mdexecutablescript3.9 KB
references/confirm-round-protocol.mdexecutablescript12.3 KB
references/dispatch-result-contract.mdexecutablescript3.5 KB
references/feature-build-brief.mdexecutablescript2.9 KB
references/fix-brief-template.mdexecutablescript10.5 KB
references/persistent-loop-plan.mdexecutablescript6.9 KB
references/release-hygiene.mdexecutablescript3.9 KB
references/reviewer-dispatch.mdexecutablescript6.0 KB
references/spec-convergence.mdexecutablescript5.2 KB
references/two-axis-single-pass.mdexecutablescript9.9 KB
references/workflow-steps.mdexecutablescript18.9 KB
scripts/attest_file.pyexecutablescript2.7 KB
scripts/capture_dispatch_result.pyexecutablescript3.6 KB
scripts/loop_plan_check.pyexecutablescript3.8 KB

scripts/capture_dispatch_result.py

View on GitHub
#!/usr/bin/env python3
"""Capture a delegate-result.v1 result file after a builder/reviewer dispatch.

Part of the build-review-loop skill. Run once per dispatch, after the
implementer process exits and before orchestrator verification. The result
file — not a log tail — is the dispatch's accountable record: status, exit
code, the model that actually ran, and the touched-files boundary the review
starts from.
"""
import argparse
import datetime
import json
import os
import subprocess
import sys

SCHEMA = "delegate-result.v1"


def git_porcelain(repo):
    """git status --porcelain lines for repo; None when git can't report."""
    try:
        out = subprocess.run(
            ["git", "-C", repo, "status", "--porcelain"],
            capture_output=True,
            text=True,
            timeout=30,
        )
        if out.returncode != 0:
            return None
        return [line for line in out.stdout.splitlines() if line.strip()]
    except (OSError, subprocess.TimeoutExpired):
        return None


def status_from_exit(code):
    if code == 0:
        return "completed"
    if code == 124:
        return "timeout"
    if code == 127:
        return "unavailable"
    return "failed"


def main():
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("--repo", required=True,
                    help="project working tree the implementer ran in")
    ap.add_argument("--task", required=True,
                    help='short label, e.g. "build R1: batch A"')
    ap.add_argument("--implementer", required=True,
                    choices=["cursor", "codex", "claude-code", "hermes"])
    ap.add_argument("--model", default=None,
                    help="model that actually ran (after any tier fallback)")
    ap.add_argument("--report", default=None,
                    help="path to the implementer's full output/report file")
    ap.add_argument("--stderr", default=None,
                    help="path to captured stderr, if kept")
    ap.add_argument("--exit-code", type=int, required=True)
    ap.add_argument("--started-at", default=None,
                    help="ISO timestamp the dispatch started, if known")
    ap.add_argument("--out", required=True,
                    help="output JSON path (keep it outside the repo)")
    ap.add_argument("--notes", default=None,
                    help="free text, e.g. 'medium-tier fallback' or 'delta round for R1'")
    args = ap.parse_args()

    result = {
        "schema": SCHEMA,
        "task": args.task,
        "implementer": args.implementer,
        "model": args.model,
        "status": status_from_exit(args.exit_code),
        "exitCode": args.exit_code,
        "reportPath": os.path.abspath(args.report) if args.report else None,
        "stderrPath": os.path.abspath(args.stderr) if args.stderr else None,
        "touchedFiles": git_porcelain(args.repo),
        "startedAt": args.started_at,
        "finishedAt": datetime.datetime.now(datetime.timezone.utc).isoformat(
            timespec="seconds"),
        "notes": args.notes,
    }

    if args.report and not os.path.isfile(result["reportPath"]):
        print(f"WARN: report file not found: {result['reportPath']}", file=sys.stderr)

    out_dir = os.path.dirname(os.path.abspath(args.out))
    os.makedirs(out_dir, exist_ok=True)
    with open(args.out, "w", encoding="utf-8") as fh:
        json.dump(result, fh, indent=2)
        fh.write("\n")

    touched = result["touchedFiles"]
    touched_n = "unknown" if touched is None else len(touched)
    print(f"captured {args.out}: status={result['status']} "
          f"exit={args.exit_code} touched={touched_n}")


if __name__ == "__main__":
    main()
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall