Auto Converge is an AI Engineering skill for Claude Code, published by KonghaYao in peri.
Auto Converge refines rules, prompts, and SKILL.md files until agents can follow them reliably. It uses external references and adversarial review loops when a spec is written but not being obeyed.
Auto Converge is cataloged under AI Engineering on DirSkills. Auto Converge comes from a repository tagged acp, claude-code, coding-agent, deepseek and glm.
Documentation
两个策略驱动——
两条策略必须同时执行。只看参考不迭代，规则停留在理论正确但 agent 执行不走；只迭代不看参考，规则在低水平收敛但没有吸收业界最佳实践。
不限于 SKILL.md——任何需要 agent 稳定遵守的规范都可以收敛。常见场景——
This is the opening of the README. Read the full README on GitHub.
Auto Converge is one of 20 skills that DirSkills catalogs from KonghaYao/peri, the repository it ships in. Its siblings there include Adaptive Devflow, Advisor Consultation and Auto Issue Fixer. Each one is a separate skill with its own page in this directory, installs the same way Auto Converge does, and is maintained by KonghaYao in that same repository. The rest of the collection is listed on the KonghaYao/peri page.
Auto Converge ranks #3388 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Auto Converge against them. Open each page to compare what they document and how they install.
Auto Converge is one of 20 skills cataloged on DirSkills from KonghaYao/peri.
Auto Converge is one of 3670 AI Engineering skills cataloged on DirSkills, ranked #3388 by stars among them.