{"id":51678909,"url":"https://github.com/mvpbin/ai-reality-check","last_synced_at":"2026-07-15T10:33:41.609Z","repository":{"id":369253070,"uuid":"1289066891","full_name":"mvpbin/ai-reality-check","owner":"mvpbin","description":"Codex skill for evidence-aware AI advice review, risk calibration, and safe next steps.","archived":false,"fork":false,"pushed_at":"2026-07-12T05:56:03.000Z","size":9,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-07-12T07:09:56.114Z","etag":null,"topics":["ai-safety","codex","codex-skill","decision-support","fact-checking"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mvpbin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-07-04T09:51:47.000Z","updated_at":"2026-07-12T05:58:17.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/mvpbin/ai-reality-check","commit_stats":null,"previous_names":["mvpbin/ai-reality-check"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mvpbin/ai-reality-check","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvpbin%2Fai-reality-check","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvpbin%2Fai-reality-check/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvpbin%2Fai-reality-check/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvpbin%2Fai-reality-check/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mvpbin","download_url":"https://codeload.github.com/mvpbin/ai-reality-check/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvpbin%2Fai-reality-check/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35501665,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-15T02:00:06.706Z","response_time":131,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-safety","codex","codex-skill","decision-support","fact-checking"],"created_at":"2026-07-15T10:33:41.492Z","updated_at":"2026-07-15T10:33:41.605Z","avatar_url":"https://github.com/mvpbin.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI 队友审查\n\n`ai-reality-check` 是一个 Codex Skill，用来帮助非专业用户审查 AI 给出的建议。\n\n它的目标不是让你更依赖 AI，而是让 AI 在跨领域任务里先讲清楚、先暴露风险、先给验证方法，再推动你行动。\n\n## 解决什么问题\n\n当你不熟悉某个领域时，AI 的回答可能听起来很专业，但你很难判断它到底对不对。\n\n这个 Skill 会要求 AI：\n\n- 先用大白话解释专业内容。\n- 区分直接观察、用户陈述、材料主张、外部证据、假设和不确定性。\n- 只对会影响行动的重要判断标注可信度。\n- 按后果、可逆性、影响范围和暴露面判断风险与审查深度。\n- 给出验证方法，而不是只让你相信 AI。\n- 默认先给一个最小安全下一步；明确需要完整计划时再展开。\n\n适合用在技术方案、业务判断、工具选择、研究结论、代码解释、另一个 AI 回答复核等场景。\n\n## 怎么安装\n\n把本仓库复制到你的 Codex Skills 目录：\n\n```powershell\ngit clone https://github.com/mvpbin/ai-reality-check.git \"$env:USERPROFILE\\.codex\\skills\\ai-reality-check\"\n```\n\n然后重启 Codex，或开启一个新对话，让 Codex 重新发现这个 Skill。\n\n## 怎么调用\n\n你可以直接这样说：\n\n```text\n使用 ai-reality-check 帮我审查这个 AI 建议，先用大白话解释，再告诉我能不能行动。\n```\n\n也可以这样说：\n\n```text\n按 AI 队友审查模式，帮我判断这个方案靠不靠谱。\n```\n\n如果你拿到另一段 AI 回答，可以这样用：\n\n```text\n按 AI 队友审查模式，帮我看看下面这段 AI 回答有没有坑。\n```\n\n## 输出风格\n\n回答会根据证据缺口和行动风险调整深度。低风险问题会压缩输出；中高风险问题通常覆盖：\n\n```text\n业务结论\n大白话解释\n原因\n风险\n验证方法\n下一步\n技术依据（按需阅读）\n```\n\n这些是需要覆盖的内容，不是必须输出的空标题。高风险问题会更严格地拆分证据状态、失败后果和停止条件。\n\n## 许可证\n\n本项目采用 [MIT License](LICENSE)。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmvpbin%2Fai-reality-check","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmvpbin%2Fai-reality-check","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmvpbin%2Fai-reality-check/lists"}