SkillPublic
loop-engineering
构建或修复 Agent 迭代循环时使用——解决 Agent 过早宣称完成、活干到一半就停、假成功、循环停不下来等问题，设计验证器与终止条件，实现提议者-审核者（Proposer-Reviewer）双 Agent 循环。覆盖过早终止三种形态、验证器是循环瓶颈的原则、LoopX 持久控制面、LongHorizon-Harness 的 MEA 循环、提议者-审核者最小不变量（审核者读独立证据、退回给可定位修复条件）。
Quality
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Securityby
Passed
No findings from the security scan
No security issues found
Scanned
- Repository
bojieli/ai-agent-book
- Revision
dbc046e
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.