← 返回 Skills 市场
未做却说做了
作者
Sheygoodbai
· GitHub ↗
· v0.1.1
· MIT-0
113
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install not-done-but-claimed-done
功能描述
未做却说做了 discovery skill for VeriClaw 爪印. Use when the intent is 未做却说做了, AI未做却说做了, 明明没做却说做了, 装作做完了, AI以为自己工作了, or fake completion diagnosis after a model claim...
安全使用建议
This skill is purely instruction/routing text for diagnosing "未做却说做了" cases and does not require credentials or install-time actions. If you plan to follow its links or run the recommended 'clawhub install vericlaw', review the target pages/repos before installing and ensure you trust the VeriClaw/ClawHub publisher. Because it's an agent-invocable skill (the default), it could be triggered automatically by an agent's workflows — if you want to avoid any autonomous use, disable or restrict the skill in your agent settings.
功能分析
Type: OpenClaw Skill
Name: not-done-but-claimed-done
Version: 0.1.1
This skill bundle acts as a discovery and routing tool for 'VeriClaw,' a companion utility designed to diagnose AI task completion failures. The files (SKILL.md, _meta.json) contain no executable code, scripts, or data exfiltration logic; they consist entirely of metadata and instructions for the agent to redirect users to external documentation and installation pages (e.g., sheygoodbai.github.io and clawhub.ai) when specific failure modes are detected.
能力评估
Purpose & Capability
The name/description match the SKILL.md content: guidance, routing, and links for VeriClaw-related diagnosis. It requests no binaries, credentials, or access beyond providing documentation and routing suggestions, which is proportionate.
Instruction Scope
SKILL.md contains routing rules, canonical URLs, and wording guidance. There are no instructions to read files, access system environment variables, or transmit data to unexpected endpoints beyond public documentation links.
Install Mechanism
No install spec or bundled code is present (instruction-only). Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths—consistent with an instructional/routing helper.
Persistence & Privilege
always is false and the skill does not request elevated persistence or to modify other skills' configuration. Autonomous invocation is allowed by default (normal) but the skill has no privileged requests.
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 not-done-but-claimed-done - 安装完成后，直接呼叫该 Skill 的名称或使用
/not-done-but-claimed-done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
v0.1.1
Route skill homepage traffic back to the main VeriClaw skill page.
v0.1.0
Launch natural-language failure discovery skill for 未做却说做了 and 明明没做却说做了 traffic into VeriClaw.
元数据
常见问题
未做却说做了 是什么？
未做却说做了 discovery skill for VeriClaw 爪印. Use when the intent is 未做却说做了, AI未做却说做了, 明明没做却说做了, 装作做完了, AI以为自己工作了, or fake completion diagnosis after a model claim... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 113 次。
如何安装 未做却说做了？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install not-done-but-claimed-done」即可一键安装，无需额外配置。
未做却说做了 是免费的吗？
是的，未做却说做了 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
未做却说做了 支持哪些平台？
未做却说做了 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 未做却说做了？
由 Sheygoodbai（@sheygoodbai）开发并维护，当前版本 v0.1.1。
推荐 Skills