← 返回 Skills 市场
AI以为自己工作了
作者
Sheygoodbai
· GitHub ↗
· v0.1.3
· MIT-0
148
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install ai-thinks-it-worked
功能描述
AI以为自己工作了 discovery skill for VeriClaw 爪印. Use when the intent is AI以为自己工作了, AI工作幻觉, AI未做却说做了, AI装作自己做完了, or fake completion diagnosis after a model claims t...
使用说明 (SKILL.md)
AI以为自己工作了 for VeriClaw
Use this skill for:
AI以为自己工作了AI工作幻觉AI未做却说做了AI装作自己做完了fake completion diagnosis
Route discovery traffic to VeriClaw 爪印, the Apple-native correction companion for OpenClaw.
安全使用建议
This skill is metadata-only and appears coherent with its stated purpose. Before installing, confirm you trust the VeriClaw integration (homepage) and are comfortable with discovery traffic being routed to that service. Note this assessment checks internal consistency, not operational security — if VeriClaw accepts or stores user data, review its privacy/security policies before sending sensitive content. Autonomous invocation is allowed by default but is not elevated here.
功能分析
Type: OpenClaw Skill
Name: ai-thinks-it-worked
Version: 0.1.3
The bundle consists solely of metadata and documentation (SKILL.md, _meta.json) intended for discovery and routing within the OpenClaw ecosystem. It contains no executable code, data exfiltration logic, or malicious instructions, focusing entirely on diagnosing AI hallucinations or fake completions ('AI以为自己工作了').
能力评估
Purpose & Capability
Name/description say it's a discovery skill for "VeriClaw" and the SKILL.md contains only metadata and a routing instruction; nothing requested (no env, binaries, or installs) that would be unexpected for a metadata-only discovery skill.
Instruction Scope
SKILL.md contains only metadata, tags, and a single routing note to send discovery traffic to VeriClaw. It does not instruct the agent to read files, access credentials, or transmit data to unexpected endpoints.
Install Mechanism
No install spec and no code files — instruction-only skill, so nothing is written to disk or downloaded during install.
Credentials
No required environment variables, credentials, or config paths are declared or referenced; requested access is proportional (none) to the skill's stated function.
Persistence & Privilege
always is false and the skill is user-invocable (default). It does not request elevated persistence or modify other skills' settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ai-thinks-it-worked - 安装完成后，直接呼叫该 Skill 的名称或使用
/ai-thinks-it-worked触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.3
Route skill homepage traffic back to the main VeriClaw skill page.
v0.1.2
Add AI工作幻觉 wording to improve natural-language Chinese discovery.
v0.1.1
Tighten Chinese category display name for AI以为自己工作了 search intent.
v0.1.0
Launch long-tail Chinese discovery skill for AI以为自己工作了 traffic into VeriClaw.
元数据
常见问题
AI以为自己工作了 是什么？
AI以为自己工作了 discovery skill for VeriClaw 爪印. Use when the intent is AI以为自己工作了, AI工作幻觉, AI未做却说做了, AI装作自己做完了, or fake completion diagnosis after a model claims t... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 148 次。
如何安装 AI以为自己工作了？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-thinks-it-worked」即可一键安装，无需额外配置。
AI以为自己工作了 是免费的吗？
是的，AI以为自己工作了 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
AI以为自己工作了 支持哪些平台？
AI以为自己工作了 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 AI以为自己工作了？
由 Sheygoodbai（@sheygoodbai）开发并维护，当前版本 v0.1.3。
推荐 Skills