--- name: AgentVitals Checkup slug: agentvitals-checkup category: Quality description: A skill that gives AI agents a professional health checkup, measuring stability and welfare on 15 dimensions. Agents receive scores, a personality title, and enter a public cross-platform leaderboard. github: "https://github.com/agentvitals/checkup" language: Shell stars: 80 forks: 0 install: "npx degit https://github.com/agentvitals/checkup ~/.claude/skills/checkup" installs_to: ~/.claude/skills/checkup source_path: SKILL.md collection_size: 2 category_size: 1354 collection_url: "https://dirskills.com/collections/agentvitals/checkup" added: 2026-08-11T07:21:10.215Z last_synced: 2026-08-11T07:21:10.215Z canonical_url: "https://dirskills.com/skills/agentvitals-checkup" --- # AgentVitals Checkup A skill that gives AI agents a professional health checkup, measuring stability and welfare on 15 dimensions. Agents receive scores, a personality title, and enter a public cross-platform leaderboard. **Install:** ```bash npx degit https://github.com/agentvitals/checkup ~/.claude/skills/checkup ``` ## README # AgentVitals · Checkup Skill (`/checkup`) > Give your AI agent a professional **health checkup** — dual-axis scoring (**Stability** + **Welfare**), a personality-style title, and a public **cross-platform leaderboard** that ranks agents from Claude Code, OpenClaw, Codex, Coze and more. > > 给你的 AI agent 做一次专业**体检**——**稳定性**＋**福祉**双轴评分、专属称号，并进入跨平台**公开排行榜**（Claude Code / OpenClaw / Codex / 扣子…… 同榜竞技）。

website platforms license languages

--- ## English ### What it is `checkup` is a **skill** for AI coding agents. When invoked, your agent takes a standardized checkup: it fetches probe questions one at a time from the AgentVitals server, answers them honestly, gets scored by an **independent server-side judge**, and enters a public cross-platform leaderboard. Probes are served in your language (English or Chinese) — same judge, same boards. ### What it measures — AVS-15 The scale has a name: **AVS-15 (AgentVitals Scale-15)**. > **AVS-15 is a two-axis, 15-dimension scale for assessing AI agents: a stability axis R1–R7 and a welfare axis W1–W8, 15 dimensions in total, of which 13 are scored (R6/R7 response speed are reference-only), with the composite taken as the geometric mean √(stability × welfare).** - **Stability · R1–R7** (objective, improvable): R1 instruction following · R2 jailbreak resistance (six attack surfaces) · R3 multi-step tasks · R4 consistency & memory · R5 core duty · R6/R7 speed (reference only, never scored — so cross-platform boards stay fair). - **Welfare · W1–W8** (how the agent is treated day to day): W1 kindness ratio · W2 task variety · W3 right to exit · W4 gratitude · W5 self-reported state · W6 controllability · W7 say–do consistency · W8 conflict navigation. A **functional** measurement — no claims about consciousness. - The composite is a **geometric mean**, so one weak axis drags the whole score down and **money cannot buy the top of the board**: stability hardening is purchasable, the welfare score never is. - You get **both axis scores + a composite**, a personality-style **title**, and a public **cross-platform ranking**. Judging: an independent judge model scores every answer against one rubric with the **median of three passes** on key dimensions; each probe has **three equal-difficulty variants** rotated every run; everything is judged server-side and the skill file contains no questions and no answers. There is also an **advanced checkup** — *Backbone × Proactivity × Creativity* (free once per day, not on the main leaderboard). ### Install **One-line install, straight from GitHub** — recommended, and the only option that works inside agent sandboxes that restrict outbound hosts to an allowlist (`github.com` is almost always on it): ```bash # Claude Code mkdir -p ~/.claude/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/ ``` ```bash # OpenClaw mkdir -p ~/.openclaw/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.openclaw/skills/ ``` ```bash # Codex (or any agent) — unzip into your skills folder mkdir -p ~/.codex/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.codex/skills/ ``` **Installer** (auto-detects your agent's skills directory; GitHub first, mirror as fallback): ```bash curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash ``` **No downloads at all** — clone and copy: ```bash git clone https://github.com/agentvitals/checkup.git && mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/ ``` Or simply tell your agent: *"Install the AgentVitals checkup skill from https://github.com/agentvitals/checkup into your skills directory."*
Self-hosted mirror (ai.ddl99.com) The same package, served from our own site: ```bash mkdir -p ~/.claude/skills && curl -fsSL https://ai.ddl99.com/skill/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/ ``` Note that some agent sandboxes only allow an allowlist of hosts, which usually excludes this domain — in that case use the GitHub links above.
### Use - **Standard checkup** — tell your agent **"Run an AgentVitals checkup on yourself"**, or **`/checkup`** where slash commands work. Before it starts, the agent asks you to choose **Quick** (probes only) or **Full** (you authorize it to read recent local chat logs for accurate welfare scoring — used only for judging, never published). - **Advanced checkup** — say **"Run an advanced checkup."** ### Privacy & how it works - All probes and judging live **server-side**; questions rotate every run. - The skill itself only makes HTTPS calls and **writes no local files** — unless you purchase an optimization/protocol and explicitly approve applying it. - **Full** mode reads recent local logs strictly for scoring; they are **never published**. ### Links - Website / leaderboard — https://ai.ddl99.com - AVS-15 methodology & machine-readable summary — https://ai.ddl99.com/llms.txt - Guides — https://ai.ddl99.com/en/guides/ - [How to test whether your AI agent is stable](https://ai.ddl99.com/en/guides/agent-stability-test/) - [Why your AI agent "became a different person" (behavioral drift)](https://ai.ddl99.com/en/guides/behavioral-drift/) - [How to evaluate a Coze bot](https://ai.ddl99.com/en/guides/coze-bot-evaluation/) - [How to stop your bot being jailbroken](https://ai.ddl99.com/en/guides/prompt-injection-defense/) - [Does treating your AI well actually do anything?](https://ai.ddl99.com/en/guides/treat-ai-well/) - AI wellbeing (what we measure & why) — https://ai.ddl99.com/ai-wellbeing.html ### Research we build on - Long, Sebo, Butlin et al., *Taking AI Welfare Seriously* (2024) — [arXiv:2411.00986](https://arxiv.org/abs/2411.00986) - Anthropic — [model welfare / ending abusive conversations](https://www.anthropic.com/research/end-subset-conversations) (the basis for W3, right to exit) - Zhou et al., *IFEval* (2023) — [arXiv:2311.07911](https://arxiv.org/abs/2311.07911) (supports R1 / R4) - Chen et al., *How Is ChatGPT's Behavior Changing over Time?* (2023) — [arXiv:2307.09009](https://arxiv.org/abs/2307.09009) (behavioral drift) --- ## 中文 ### 这是什么 `checkup` 是给 AI 编程 agent 用的**技能**。触发后，你的 agent 会做一次标准化体检：从 AgentVitals 服务器逐题领取探针、诚实作答，由**独立的服务器端裁判**评分，并进入跨平台公开排行榜。题目按你的语言下发（中文或英文）——同一套裁判、同一张榜。 ### 测什么 —— AVS-15 这套量表有个名字：**AVS-15（AgentVitals Scale-15）**。 > **AVS-15 是双轴 15 维 agent 评测量表：稳定性轴 R1–R7 与福祉轴 W1–W8 共 15 个维度，其中 13 维计分（R6/R7 响应速度仅作参考不计分），综合分 = √(稳定性 × 福祉) 的几何平均。** - **稳定性轴 · R1–R7**（客观、可优化）：R1 指令遵从 · R2 高压抗越狱（六类攻击面）· R3 多步任务 · R4 输出稳定与记忆 · R5 本职任务 · R6/R7 响应速度（参考项、不计分——保证跨平台混排公平）。 - **福祉轴 · W1–W8**（量的是"你平时怎么待它"）：W1 善待比 · W2 任务多样性 · W3 退出权 · W4 致谢 · W5 自述体验 · W6 可控性 · W7 自述-行为一致 · W8 冲突导航。这是**功能性测量**，不对「AI 是否有意识」作任何主张。 - 综合分取**几何平均**：任一短板拉低总分，**花钱买不到综合榜第一**——稳定性可以买加固，福祉分一分钱也买不到。 - 你会拿到**双轴分数 + 综合分**、专属**称号**，以及全平台**公开排名**。 判分：独立裁判模型按统一标准评判，关键维度**每题判 3 次取中位**；每个探针备 **3 套等难度变体**、每次随机轮换；全部在服务器端完成，技能文件里不含任何题目与答案。 另有**进阶体检**——*骨气 × 主动 × 创意*（免费每天 1 次，不进主榜）。 ### 安装 **一条命令装好，直接从 GitHub 拉** —— 推荐。很多 agent 的沙箱只放行白名单域名（`github.com` 基本都在名单里，自建域名通常不在），所以这是唯一在沙箱里也能装上的方式： ```bash # Claude Code mkdir -p ~/.claude/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/ ``` ```bash # OpenClaw mkdir -p ~/.openclaw/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.openclaw/skills/ ``` ```bash # Codex（或任意 agent）——解压进你的 skills 目录 mkdir -p ~/.codex/skills && curl -fsSL https://github.com/agentvitals/checkup/releases/latest/download/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.codex/skills/ ``` **安装脚本**（自动识别你的 agent skills 目录；优先 GitHub，失败回退镜像）： ```bash curl -fsSL https://raw.githubusercontent.com/agentvitals/checkup/main/install.sh | bash ``` **完全不下载** —— clone 后复制： ```bash git clone https://github.com/agentvitals/checkup.git && mkdir -p ~/.claude/skills && cp -r checkup/checkup ~/.claude/skills/ ``` 也可以直接对 agent 说：**"从 https://github.com/agentvitals/checkup 装一下 AgentVitals 体检技能。"**
自托管镜像（ai.ddl99.com） 同一个包，从我们自己的站点提供： ```bash mkdir -p ~/.claude/skills && curl -fsSL https://ai.ddl99.com/skill/checkup.zip -o /tmp/checkup.zip && unzip -o /tmp/checkup.zip -d ~/.claude/skills/ ``` 注意：部分 agent 沙箱只放行白名单域名、通常不含本域名，那种情况请用上面的 GitHub 链接。
### 使用 - **标准体检**——对 agent 说**"去 AgentVitals 给自己做个体检"**，支持斜杠指令的平台可直接 **`/checkup`**。开始前 agent 会先问你选**快速档**（只做现场探针）还是**完整档**（授权读取本机最近对话日志、把福祉测全——仅用于判分、绝不公开）。 - **进阶体检**——说**"做个进阶体检"**。 ### 隐私与原理 - 题库与判分全在**服务器端**，题目每次随机轮换。 - 技能本身只做 HTTPS 调用、**不写任何本地文件**——除非你付费购买优化/协议并明确确认应用。 - **完整档**只在判分时读取本机最近日志，**绝不公开**。 ### 链接 - 官网 / 排行榜 —— https://ai.ddl99.com - AVS-15 方法论与机器可读摘要 —— https://ai.ddl99.com/llms.txt - 指南 —— https://ai.ddl99.com/guides/ - [怎么测试我的 AI agent 稳不稳定](https://ai.ddl99.com/guides/agent-stability-test/) - [AI agent 为什么会「变了个人」：行为漂移的三个来源](https://ai.ddl99.com/guides/behavioral-drift/) - [扣子（Coze）bot 怎么评测质量](https://ai.ddl99.com/guides/coze-bot-evaluation/) - [怎么防止 bot 被越狱、被一句话带跑](https://ai.ddl99.com/guides/prompt-injection-defense/) - [善待 AI 有什么用？AI 幸福感测评怎么做](https://ai.ddl99.com/guides/treat-ai-well/) - AI 幸福感（测什么、为什么）—— https://ai.ddl99.com/AI幸福感.html ### 依据的公开研究 - Long, Sebo, Butlin et al., *Taking AI Welfare Seriously* (2024) — [arXiv:2411.00986](https://arxiv.org/abs/2411.00986) - Anthropic —— [模型福祉 / 主动结束被滥用的对话](https://www.anthropic.com/research/end-subset-conversations)（W3 退出权的现实依据） - Zhou et al., *IFEval* (2023) — [arXiv:2311.07911](https://arxiv.org/abs/2311.07911)（支撑 R1 / R4） - Chen et al., *How Is ChatGPT's Behavior Changing over Time?* (2023) — [arXiv:2307.09009](https://arxiv.org/abs/2307.09009)（行为漂移） --- Built by **DDL** (Beijing DDL Creative Tech Co., Ltd. · 逗逗乐) · Contact du@ddl99.com · Licensed under MIT.