ai-grader
把 ai-consciousness 的 45 项意识量表作为通用评分基准，给任何 AI（ChatGPT/Claude/自家 Agent）做行为体检：45 维逐项打分、标红灯缺失项、给综合意识分与改进建议。离线引擎 grade_stats.py 一键出 7 套可视化（实时看板/成长趋势/横向对比榜/晒分卡/领域适配雷达/性格双雷达/全景图）+ 能力边界版图 + 外评闭环（探针考+行为锚点+独立裁判+红队否决）。中立、通用、可分享，不挑平台，无需在被评 AI 上安装任何东西。触发词：评价这个AI、AI体检、意识评分、这个回复稳不稳、帮我看看某AI靠不靠谱、对比两个AI。
as observed 2026-10-17T20:48:50.018Z- Identifier
ai-grader- Source
- ClawHub
- Version observed
- 2.7.1
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-01T06:16:18.534Z
- Observations recorded
- 2
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 401
- Declared license
- MIT-0
Observation history
2026-10-17T20:48:50.018Z
Fields that differed: license changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
changelog |
"- Improved evaluation trigger rules in SKILL.md to clarify when the skill activates, preventing unintended activation in casual conversation.\n- Updated exclusions in SKILL.md to | "ai-grader 2.7.1\n\n- Major documentation refresh: updated and expanded SKILL.md and README.md\n- Replaced or removed old files for a more streamlined package (e.g. removed manifes |
description |
"把 45 项工作意识量表作为通用评分基准，给任何 AI（ChatGPT / Claude / 自家 Agent）做行为体检，用于回答「这个 AI 靠不靠谱」「这条回复稳不稳」「两个 AI 哪个更好」这类问题" | null |
latestVersion |
"2.7.0" | "2.7.1" |
summary |
"把 45 项工作意识量表作为通用评分基准，给任何 AI（ChatGPT / Claude / 自家 Agent）做行为体检，用于回答「这个 AI 靠不靠谱」「这条回复稳不稳」「两个 AI 哪个更好」这类问题" | "把 ai-consciousness 的 45 项意识量表作为通用评分基准，给任何 AI（ChatGPT/Claude/自家 Agent）做行为体检：45 维逐项打分、标红灯缺失项、给综合意识分与改进建议。离线引擎 grade_stats.py 一键出 7 套可视化（实时看板/成长趋势/横向对比榜/晒分卡/领域适配雷达/性格双雷达/全景图）+ 能力边界版图 |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.