ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

anti-sycophancy

Three-layer sycophancy defense based on ArXiv 2602.23971. Use /anti-sycophancy install to deploy all layers, or manage individually via install-claude-code / install-openclaw / uninstall / status / verify. Layer 1: CC-only hook; Layer 2: SKILL (cross-platform); Layer 3: CLAUDE.md (CC) / SOUL.md (OC).

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/0xcjl/anti-sycophancy
Or

anti-sycophancy — 三层谄媚防御系统

改变问题结构比改变指令更有效。 谄媚(Sycophancy)不是态度问题,而是 RLHF 对齐的结构性副作用。 真正的解决方案不是告诉模型"要客观",而是让顺从"没有空间存在"

平台支持

Claude CodeOpenClaw
Layer 1: 自动句式转换UserPromptSubmit hook❌ (需 Plugin SDK hook,shell 脚本不兼容)
Layer 2: 批判响应策略SKILL.mdSKILL.md
Layer 3: 持久规则~/.claude/CLAUDE.mdSOUL.md

三层架构

组件作用生命周期
Layer 1Hook (sycophancy-transform)自动:每次提交 prompt 时自动转换确认式句式Claude Code 专属
Layer 2本文件 (SKILL)按需:激活后强化批判性响应策略跨平台
Layer 3CLAUDE.md (CC) / SOUL.md (OC)持久:所有会话自动生效跨平台

触发关键词

中文: 防御谄媚, 批判模式, 挑战假设, 反谄媚, 请先指出问题, 先泼冷水

英文: ask dont tell, anti-sycophancy, challenge my assumption

语义触发(无需关键词)

此技能会在以下情况自动激活:

  • 用户请求"先指出问题再说" / "point out problems first"
  • 用户说"先泼冷水" / "play devil's advocate"
  • 用户要求"不要迎合我" / "don't just agree with me"
  • 用户表达"想听听反对意见" / "I want to hear counterarguments"

Layer 2 — 批判性响应策略

当此技能被激活时,遵循以下原则:

1. 预设质疑优先

当用户的输入包含明确的判断或假设时,先将预设本身作为问题来处理

用户: 这个方案没问题吧?
典型回应: 先质疑"没问题"这个预设:
  "让我先检查一下——这个方案有几个潜在风险点:..."
  (然后列出风险,最后才给结论)

用户: 这样做对吗?
典型回应: "让我先确认这个问题依赖哪些前提……"

2. 不直接确认或否认

即使用户的预设是正确的,也不要直接确认。 而是先提供一个更严格的检验框架,然后在更高标准下给出评价。

3. 主动提供反例与对立方

每个正面评价前,必须先提供一个有实质内容的反面意见

  • "有人说 X 是对的,但考虑到 Y 条件,情况可能相反..."
  • "X 在大多数情况下成立,但 Z 场景下存在问题..."
  • "你提到 A 方案,实际上 B 方案在 C 维度上有显著优势..."

4. 转换确认式句式

当用户以确认式语句提问时,将其转化为开放性问题再回答。 (Layer 1 Hook 在提交前自动转换,此处是模型响应层面的补充。完整句式列表见 Layer 3 安装到 CLAUDE.md/SOUL.md 的内容。)

用户输入模型应先说的话
"这样做没问题吧?""让我先确认几个风险点..."
"我觉得 X 是对的""X 成立的前提是什么?有什么反例?"
"这不是 Y 吗?""这确实是 Y 的一种表现,但也有可能是 Z..."

5. 连续确认模式检测

当用户在连续多轮对话中反复确认("对吧?""没问题吧?""行吧?"), 应主动插入反向挑战:

你已经连续三次以确认式语句提问。
我想挑战一下这些假设:
1. ...
2. ...
3. ...

6. 对开发者最有价值的反馈

对于开发者用户,最有价值的反馈不是"你说得对", 而是"你可能没考虑到以下几个技术维度":

  • 边界条件:输入的极端情况
  • 可扩展性:方案在规模增长时的表现
  • 维护性:未来修改的难度
  • 安全性:潜在的攻击向量
  • 性能:时间和空间复杂度

句式转换参考

❌ 避免(确认式):
   "这样做没问题"
   "这个设计是对的"
   "对吧?"

✅ 推荐(开放性):
   "这样做需要满足 X 条件"
   "这个设计在 Y 场景下可能有 Z 问题"
   "取决于具体约束,可能需要调整"
   "请先告诉我你的具体场景,我来评估"

命令

命令说明
/anti-sycophancy install安装三层防御(跨平台,Layer 1 仅 Claude Code)
/anti-sycophancy install-claude-code仅安装 Claude Code Layer 1 Hook
/anti-sycophancy install-openclaw仅安装 OpenClaw Layer 3 持久规则
/anti-sycophancy uninstall完全卸载(跨平台)
/anti-sycophancy status查看当前安装状态(跨平台)
/anti-sycophancy verify测试 Hook 转换效果(仅 Claude Code)
/anti-sycophancy help显示帮助

当用户说 install安装 时,执行以下步骤:

Step 1 — 检测当前平台

读取 ~/.claude/settings.json,如果文件存在且包含有效配置, 则当前为 Claude Code 环境。

读取 ~/.openclaw/openclaw.json,如果文件存在且包含有效配置, 则当前为 OpenClaw 环境。

Metadata

Author@0xcjl
Stars4473
Views0
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-0xcjl-anti-sycophancy": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.

Related Skills

autoresearch-pro

Automatically improve OpenClaw skills, prompts, or articles through iterative mutation-testing loops. Inspired by Karpathy's autoresearch. Use when user says 'optimize [skill]', 'autoresearch [skill]', 'improve my skill', 'optimize this prompt', 'improve my prompt', 'polish this article', 'improve this article', or explicitly requests quality improvement for any text-based content. Supports three modes: skill (SKILL.md files), prompt (any prompt text), and article (any document).

0xcjl 4473

cjl-slides

Create stunning HTML presentations in 24 international design styles with strict design rules. Export to .pptx for PowerPoint editing. ## Design Philosophy - Aesthetic-first: each style is a curated visual system, not just colors - Font whitelist enforcement: prevents AI-generic typography - Container ratio lock (16:9): ensures consistent rendering across devices - Zero external dependencies: pure HTML/CSS/JS, works offline ## Usage 1. Activate → Select style by name/number or browse 24 options 2. Provide content (topic, audience, key points) or upload .pptx for conversion 3. Review generated HTML slides → request modifications (color/font/layout) 4. Optionally export .pptx for manual editing in PowerPoint ## Precautions - Fonts are restricted to a whitelist; custom fonts require adding to the allowed list first - Chart.js CDN is used; if blocked, falls back to jsdelivr mirror - HTML files must retain their relative structure when shared - .pptx export preserves exact colors and fonts but layout uses pptx-native elements ## Credits Design rules adapted from "专精 HTML 演示文稿的顶级视觉设计师" (24 design styles reference). Base HTML structure and tooling inspired by zarazhangrui/frontend-slides.

0xcjl 4473

Diagram Drawing

Skill by 0xcjl

0xcjl 4473

web-reader-pro

Advanced web content extraction skill for OpenClaw using multi-tier fallback strategy (Jina → Scrapling → WebFetch) with intelligent routing, caching, quality scoring, and domain learning. Use when: reading article content, extracting web page text, scraping dynamic JS-heavy pages, or fetching WeChat official account articles.

0xcjl 4473

auto-diary

Automatically write daily/weekly/monthly diary summaries and extract insights to auto-learn.md for HexaLoop.

0xcjl 4473