← 返回 Skills 市场
AI纠错
作者
Sheygoodbai
· GitHub ↗
· v0.1.3
· MIT-0
145
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install model-correction-cn
功能描述
AI纠错 alias route into Official VeriClaw. 如果你的真实目标是官方公共安装入口，先安装 `vericlaw`；这个页面只负责把 AI纠错、模型纠偏、模型校正、AI纠偏 和 AI校正 这些中文纠偏意图映射回主 skill。
安全使用建议
This skill is low-risk and simply maps several Chinese correction-related intents to the VeriClaw skill. If you want the official, full-featured installation, follow the SKILL.md advice and install 'vericlaw' from the canonical source (or the listed homepage). Because it's instruction-only and asks for no credentials or installs, there's no obvious security concern here — but be aware this alias may not implement functionality itself; installing the main vericlaw skill is required for full capabilities. As a general precaution, only install the canonical skill from the official repo/homepage listed if you need the full toolset.
功能分析
Type: OpenClaw Skill
Name: model-correction-cn
Version: 0.1.3
This skill bundle acts as a Chinese-language alias and routing layer for the 'VeriClaw' tool. It contains no executable code and functions solely to map specific Chinese terms (e.g., AI纠错, 模型纠偏) to the main VeriClaw skill, providing links to project documentation on GitHub and ClawHub. No malicious indicators or risky behaviors were identified in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name and description say this is an alias/route into VeriClaw; the skill requires no binaries, env vars, or install steps—consistent with being a lightweight routing/intent-mapping skill.
Instruction Scope
SKILL.md only documents routing rules, canonical pages, and user guidance (e.g., tell users to install 'vericlaw' for the canonical surface). It does not instruct reading files, accessing credentials, or calling unrelated external endpoints.
Install Mechanism
No install spec or code files are present; instruction-only skills have minimal footprint and nothing is written to disk or fetched during install.
Credentials
No environment variables, credentials, or config paths are requested; proportional to the described intent-mapping role.
Persistence & Privilege
Flags are default (always: false, autonomous invocation allowed). The skill does not request persistent system privileges or modify other skills' configs.
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 model-correction-cn - 安装完成后，直接呼叫该 Skill 的名称或使用
/model-correction-cn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
Reframe this Chinese intent alias as a route back to Official VeriClaw so the canonical public install surface stays concentrated on the main vericlaw skill.
v0.1.2
Retarget the result surface toward exact AI纠错 intent.
v0.1.1
Strengthen title coverage for 模型纠偏, AI纠错, and AI校正.
v0.1.0
Launch 模型纠偏 discovery route for VeriClaw.
元数据
常见问题
AI纠错 是什么？
AI纠错 alias route into Official VeriClaw. 如果你的真实目标是官方公共安装入口，先安装 `vericlaw`；这个页面只负责把 AI纠错、模型纠偏、模型校正、AI纠偏 和 AI校正 这些中文纠偏意图映射回主 skill。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 145 次。
如何安装 AI纠错？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install model-correction-cn」即可一键安装，无需额外配置。
AI纠错 是免费的吗？
是的，AI纠错 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
AI纠错 支持哪些平台？
AI纠错 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纠错？
由 Sheygoodbai（@sheygoodbai）开发并维护，当前版本 v0.1.3。
推荐 Skills