JordanGunn/nunchuck / skills/md/md-review
md-review
VerifiedAgent review for markdown quality, clarity, and structural integrity. Leverages deterministic lint output as input for subjective assessment.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 522 B |
| references/00_ROUTER.md | markdown | 468 B |
| references/01_SUMMARY.md | markdown | 789 B |
| references/02_TRIGGERS.md | markdown | 381 B |
| references/03_ALWAYS.md | markdown | 671 B |
| references/04_NEVER.md | markdown | 288 B |
| references/05_PROCEDURE.md | markdown | 874 B |
| references/06_FAILURES.md | markdown | 540 B |
| scripts/include/md_review_cli.py | script | 2.7 KB |
| scripts/skill.ps1 | script | 1.6 KB |
| scripts/skill.sh | script | 1.4 KB |
scripts/include/md_review_cli.py
View on GitHub#!/usr/bin/env python3
import argparse
import sys
from pathlib import Path
def iter_markdown_files(target: Path) -> list[Path]:
if target.is_dir():
return sorted([p for p in target.glob("*.md") if p.is_file()])
return [target]
def lint_file(path: Path) -> list[tuple[int, str]]:
issues: list[tuple[int, str]] = []
text = path.read_text(encoding="utf-8")
lines = text.split("\n")
blank_run = 0
for i, line in enumerate(lines, 1):
if line.rstrip() != line:
issues.append((i, "trailing whitespace"))
if line.strip() == "":
blank_run += 1
if blank_run >= 3:
issues.append((i, "multiple consecutive blank lines"))
else:
blank_run = 0
if line.startswith("#") and line != "#":
if not (
line.startswith("# ")
or line.startswith("## ")
or line.startswith("### ")
or line.startswith("#### ")
or line.startswith("##### ")
or line.startswith("###### ")
):
issues.append((i, "heading missing space after #"))
return issues
def cmd_help() -> int:
print(
"""md-review - Agent review for markdown quality and structure
Usage:
md-review <file|dir>
md-review help
md-review validate
Behavior:
- Runs deterministic lint checks on the target (read-only)
- Prints lint findings for use by the agent during review
"""
)
return 0
def cmd_validate() -> int:
print("ok: md-review CLI is runnable")
return 0
def cmd_run(target_str: str) -> int:
target = Path(target_str)
if not target.exists():
print(f"error: '{target_str}' not found", file=sys.stderr)
return 1
files = iter_markdown_files(target)
if not files:
print("no markdown files found")
return 0
total_issues = 0
for f in files:
issues = lint_file(f)
if issues:
for line_no, msg in issues[:50]:
print(f"{f}:{line_no} — {msg}")
if len(issues) > 50:
print(f"{f} — ... and {len(issues) - 50} more")
total_issues += len(issues)
if total_issues > 0:
print(f"found {total_issues} issues")
return 1
print(f"lint passed: {len(files)} files checked")
return 0
def main() -> int:
parser = argparse.ArgumentParser(prog="md-review", add_help=False)
parser.add_argument("command_or_target", nargs="?")
args = parser.parse_args()
if args.command_or_target in (None, "help"):
return cmd_help()
if args.command_or_target == "validate":
return cmd_validate()
return cmd_run(args.command_or_target)
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |