jungenius-stack/pitfall-expert
Developer tools이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기
Catch the known pitfalls before your agent starts — 100+ evidence-backed cards, six domains, three-zone honest reports. Skill + MCP engine + hooks.
개요
Your agent said — and the migration isn't. It agreed with the doomed plan, called single-run luck "reliable", and you found out when the bill arrived. scans the task : it matches the task against a six-domain library of 100+ pitfall cards in cards/ — each distilled from real incidents and peer-reviewed research — binds every blocking pit to an (pre-declared decision table + executed-result write-back), and outputs a : ✅ verified (evidence chains, quotable sources) / ❓ unverified (5-minute follow-up actions) / 🚫 declared blind spots. The failure modes come with receipts, because they've been measured: agents declare solvable tasks impossible (54.9% of WebArena failures), claim completion while the environment is unchanged (MAST), pass weak test suites (7.8% of "passing" SWE-bench patches are wrong), mistake single-run luck for reliability (pass^8 < 25%), and side with a wrong user over half the time (Science, 2026: 51%).
README
원문 README의 일부입니다. 원문 보기.
Your agent said “done” — and the migration isn’t. It agreed with the doomed plan, called single-run luck “reliable”, and you found out when the bill arrived.
추천 도구
다른 키워드를 입력하거나 필터를 제거해 보세요.
설치
npx skillfish add jungenius-stack/pitfall-expert