Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/33-Galaxy-Dawn-claude-scholar/skills/skill-quality-reviewer

skill-quality-reviewer

Verified

This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report". Evaluates local skills across description quality, content organization, writing style, and structural integrity.

FileKindSize
SKILL.mdskill md11.7 KB
references/batch-review-template.mdmarkdown164 B
references/examples-bad.mdmarkdown12.8 KB
references/examples-good.mdmarkdown10.6 KB
references/scoring-criteria.mdmarkdown12.5 KB
scripts/extract-yaml.shexecutablescript728 B
scripts/skill-audit.pyexecutablescript1.1 KB

scripts/skill-audit.py

View on GitHub
#!/usr/bin/env python3
from __future__ import annotations

import argparse
import re
from pathlib import Path

REF_RE = re.compile(r'(references/[^\s)`]+|examples/[^\s)`]+|scripts/[^\s)`]+|assets/[^\s)`]+)')


def parse_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(description='Audit a skill for missing local references and rough size metrics.')
    parser.add_argument('skill_path', help='Path to the skill directory')
    return parser.parse_args()


def main() -> int:
    args = parse_args()
    root = Path(args.skill_path).expanduser().resolve()
    skill_md = root / 'SKILL.md'
    if not skill_md.exists():
        print('missing SKILL.md')
        return 1
    text = skill_md.read_text(encoding='utf-8')
    words = len(re.findall(r'\w+', text))
    print(f'word_count={words}')
    refs = sorted(set(match.rstrip('*:.,') for match in REF_RE.findall(text)))
    missing = [ref for ref in refs if not (root / ref).exists()]
    if missing:
        print('missing_refs=')
        for ref in missing:
            print(f'- {ref}')
    else:
        print('missing_refs=0')
    return 0


if __name__ == '__main__':
    raise SystemExit(main())
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 323kUpdated Claude CodeCodexVerifiedInstall