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/loop_plan_check.py

View on GitHub
#!/usr/bin/env python3
"""Check a loop plan file (build-review-loop port of the planning-with-files
phase-status + completion-gate concept).

The orchestrator's working memory for a multi-batch loop lives in
loop-plan.md (see references/persistent-loop-plan.md). This script reads it
and reports, deterministically:

- phase list with statuses
- resume pointer: the first non-complete phase and its unchecked items
- gate: exit code 1 while any phase is in_progress or pending-checked work
  remains and --gate is passed; exit 0 when every phase is complete

It is the loop's completion gate WITHOUT a hook: the orchestrator runs it at
loop start (resume) and before declaring the loop done. An agent cannot
quietly skip it, because the delivery checklist requires the gate output.

Status grammar (same tokens as planning-with-files, matched as plain text):
  **Status:** pending | in_progress | complete
under each '### Phase N - <name>' heading; tasks are '- [ ]' / '- [x]'.
"""
import argparse
import json
import re
import sys

PHASE_RE = re.compile(r"^###\s+Phase\s+(\d+)\s*[-\u2014:]\s*(.+?)\s*$")
STATUS_RE = re.compile(r"\*\*Status:\*\*\s*(pending|in_progress|complete)", re.I)
TASK_RE = re.compile(r"^\s*-\s+\[([ xX])\]\s*(.*)$")


def parse(path):
    phases = []
    current = None
    with open(path, encoding="utf-8") as fh:
        for raw in fh:
            line = raw.rstrip("\n")
            m = PHASE_RE.match(line)
            if m:
                current = {"n": int(m.group(1)), "name": m.group(2),
                           "status": "pending", "tasks": [],
                           "tasks_done": 0}
                phases.append(current)
                continue
            if current is None:
                continue
            s = STATUS_RE.search(line)
            if s:
                current["status"] = s.group(1).lower()
                continue
            t = TASK_RE.match(line)
            if t:
                current["tasks"].append(t.group(2))
                if t.group(1).strip():
                    current["tasks_done"] += 1
    return phases


def main():
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("plan", help="path to loop-plan.md")
    ap.add_argument("--gate", action="store_true",
                    help="exit 1 while work remains; exit 0 only when complete")
    args = ap.parse_args()

    phases = parse(args.plan)
    if not phases:
        print(f"NO PHASES: {args.plan} has no '### Phase N - name' headings",
              file=sys.stderr)
        return 2

    open_phases = [p for p in phases
                   if p["status"] == "in_progress"
                   or (p["status"] == "pending" and p["tasks"])
                   or (p["status"] == "complete" and p["tasks"]
                       and p["tasks_done"] < len(p["tasks"]))]
    resume = open_phases[0] if open_phases else None

    summary = {
        "plan": args.plan,
        "phases": [{"n": p["n"], "name": p["name"], "status": p["status"],
                    "tasks": f"{p['tasks_done']}/{len(p['tasks'])}"}
                   for p in phases],
        "openPhases": [p["n"] for p in open_phases],
        "resume": (None if resume is None else
                   {"n": resume["n"], "name": resume["name"],
                    "status": resume["status"],
                    "unchecked": [t for t in resume["tasks"]
                                  ] if resume["status"] != "complete" else []}),
    }
    print(json.dumps(summary, indent=2))

    if args.gate:
        if resume is not None:
            print(f"GATE BLOCKED: phase {resume['n']} ({resume['name']}) "
                  f"is {resume['status']} with unchecked work", file=sys.stderr)
            return 1
        print("GATE OPEN: all phases complete")
    return 0


if __name__ == "__main__":
    raise SystemExit(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