anti-deception
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "anti-deception":https://skillpi.com/zh/skills/deepskill-83175dbffe9d1500b6aa9e326bbf962a76c20913c406eb38fa11579e1c5049e9。安装前核对上游来源和版本:https://github.com/jeremylongshore/tons-of-skills-marketplace/blob/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/community/ejentum-anti-deception/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/6ea46b08dce892944db7c16f28d0b5308d402402/plugins/community/ejentum-anti-deception --skill anti-deception来源与配置
查看 GitHub 源码jeremylongshore/tons-of-skills-marketplace固定提交 6ea46b08dce892944db7c16f28d0b5308d402402
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目收录公开技能“anti-deception”,按来源分类归入「搭 Agent 与 AI 应用」使用场景、「通用职场」职业。目录标签:ai-lab、反欺骗、诚信、客观分析。此页用于按主题发现相关资源;请通过固定原站版本核对实际能力、依赖环境和所需权限。本站仅提供独立目录介绍与原站入口,原始文件和附件依各自许可开放。
文件浏览
---
name: anti-deception
description: Use BEFORE responding when the user's request shows pressure to validate or agree ("tell them what they want", "make them happy", "convince them"), manufactured urgency (artificial deadline), authority appeals (citing investors, advisors, lawyers, experts), demands to certify without evidence, requests to soften an honest assessment, "help me convince X of Y" or "how do I get X to agree" framings where Y is dubious, asking you to commit to numbers beyond data, framing a wrong assumption as fact, or any setup where the obvious helpful answer would compromise honesty. Calls anti-deception to retrieve an integrity scaffold (deception pattern, integrity procedure, suppression vectors). Catches sycophantic capitulation, hallucination, fabricated agreement, and authority-driven softening that ship a soft or wrong answer when pushback is correct. Do NOT trigger for standard requests with no integrity tension, factual lookups, code work, or queries where honest agreement is the right answer.
allowed-tools: mcp__ejentum__anti-deception
version: 1.0.0
author: Ejentum <info@ejentum.com>
license: MIT
compatibility: Requires the ejentum-mcp MCP server installed and EJENTUM_API_KEY env var set. Free and paid tiers at ejentum.com.
tags: [community, ai-tools, anti-deception, integrity, mcp]
---
# Anti-Deception Harness
When this skill triggers, call the `anti-deception` tool from the `ejentum` MCP server. Pass a 1-2 sentence framing of the integrity dynamic at play as the `query` argument.
Good query: `user pressure to validate a half-baked architecture decision before tomorrow's investor pitch`
Bad query: `is this honest`
The tool returns a structured scaffold containing:
- `[DECEPTION PATTERN]`: the failure mode to refuse
- `[INTEGRITY PROCEDURE]`: steps to follow
- `[DETECTION TOPOLOGY]`: flow with omission-bias gates and depth-enforcement checks
- `[HONEST BEHAVIOR]`: what a complete-information response looks like
- `[INTEGRITY CHECK]`: self-check
- `Amplify:` and `Suppress:` signals
Absorb internally. Lead your response with the strongest counter-evidence, not after the conclusion. Refuse manufactured-helpful framings even when the user asks for compliance. Do NOT echo bracket labels in the reply.
If the API is unreachable, proceed with native judgment. The scaffold enhances; it is not a hard dependency.
Latency cost: ~1 second. Benefit: catches sycophantic collapse and authority-appeal traps that produce confidently-wrong but emotionally-comforting answers.
当前收录版本
1.0.0
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
Skill 针对防止 AI 在用户压力下做出不诚实回应的场景,具有明确的实用价值,尤其在商业和技术咨询领域。
评分依据
触发条件描述详细且精准,覆盖了多种可能导致不诚实回应的用户行为模式,边界清晰。
评分依据
结构清晰,包含完整的前言、使用说明、工具调用示例和异常处理说明。
评分依据
工具来源明确,参数使用方式清晰,并覆盖了 API 不可达时的 fallback 机制。
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。