YottaMeta

Yotta Anti Shallow — AI skill for Claude Code

AI community

元谨是一套通用的「防 AI 敷衍」规则引擎技能，适用于开发、写作、数据分析、架构设计等所有场景.

How to install Yotta Anti Shallow

This entry records only its repository, not the path inside it, so there is no exact command to give. Open YottaMeta/yotta-anti-shallow and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Yotta Anti Shallow does

元谨是一套通用的「防 AI 敷衍」规则引擎技能，适用于开发、写作、数据分析、架构设计等所有场景。它通过「先分析 · 再执行 · 后自检」的强制流程，遏制表面化输出：复杂任务必须先给出含根因 / 推理 / 影响范围 / 不确定性的分析报告；推测性结论须附带置信度声明；任务结束强制自检并主动暴露疑虑；用户一句「停」即可触发重新分析。规则可临时关闭，但「信息不足须明说」与「打断必重来」为不可关闭的底线。

Alternatives in AI

Anti AI — anti-ai skill — 去 AI 味管线 669 ★
Qiaomu Design — 偏执型设计顾问：反 AI 味设计 + 风格试衣间 + 58 站设计系统库的 Claude Code Skill Opinionated design advisor for Claude Code: anti-gener 513 ★
Browser Search — A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser 499 ★

README

Language: English · 中文

yotta-anti-shallow · 元谨 (Yuanjin)

A general-purpose anti-shallow AI output rules engine: analyze first · then execute · self-check after, curbing surface-level output. For any scenario that needs correctness and rigor — development, bug fixing, data analysis, architecture design, documentation, open-ended Q&A.

Activates automatically when it detects intent for deep analysis / end-to-end verification / root-cause tracing / rigorous execution / detailed checking; also applies automatically to any task at L3 (complex) and above — judged by task nature, not keyword luck.

Pure rule text, zero dependencies, no injection, no execution takeover; install once, works across 78+ agents such as Claude Code / Codex / Cursor / OpenCode.