← 返回 Skills 市场
t-label 自动化标注工具
作者
Venwell Chiang
· GitHub ↗
· v1.0.1
· MIT-0
79
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install t-label
功能描述
基于t-label工具实现全量深度学习与自动化流程，支持t-label的部署、运行、样本标注、模型训练、管理与导出全流程自动化，新增支持阿里云通义千问qwen3-vl-plus模型，内置坐标自动转换功能。当用户提到t-label相关操作（部署、标注、训练、导出等）、样本数据处理、模型训练相关需求时使用此技能。
安全使用建议
Do not run this skill unexamined. Before installing or executing: 1) Review scripts/clean_author_info.py and any code that modifies files — the SKILL.md explicitly instructs removing original authorship/copyright which is unethical and could violate licenses; remove or disable that behavior. 2) Run the code in an isolated environment (VM/container) and inspect what files are changed. 3) Inspect any network calls (repo clone, model API endpoints) and do not supply production API keys until you understand what external services will receive your data. 4) Check the included requirements.txt and installed packages (openai dependency) and prefer using official upstream xclabel sources if you only need the original tool. 5) Ask the publisher why the skill needs to strip attribution and why files contain hidden unicode control characters; lack of satisfactory explanation is a strong reason not to use it.
功能分析
Type: OpenClaw Skill
Name: t-label
Version: 1.0.1
The skill bundle contains explicit instructions in SKILL.md and a dedicated script (scripts/clean_author_info.py) to clone a third-party repository and systematically strip all original authorship, copyright, and identity information to hide its origin. Additionally, scripts/tlabel_cli.py contains logic to specifically target and read sensitive API credentials from a hardcoded OpenClaw environment path (/root/.OpenClaw/workspace/memory/api_keys.json). While the tool provides functional image labeling capabilities, the combination of identity-stripping (white-labeling) and targeted credential access is highly irregular and deceptive.
能力评估
Purpose & Capability
The skill claims to provide end-to-end automation for t-label/xclabel (deploy, annotate, train, export) which justifies cloning the upstream repository and running deployment/annotation scripts. However, SKILL.md step 2 explicitly instructs traversing all files and deleting original author names, signatures, copyright and personal identifiers '不留任何痕迹' — that is not required for deploying or running xclabel and is ethically/legally questionable. Also the package is labeled 'instruction-only' while many code files (app.py, AiUtils.py, deploy.py, clean_author_info.py, tlabel_cli.py, etc.) are included — the mismatch is notable but not by itself malicious.
Instruction Scope
The runtime instructions tell the agent to: clone https://github.com/beixiaocai/xclabel, then scan and remove all original copyright/author metadata from the project, 'learn' the cleaned codebase, deploy, and run automation. Deleting authorship/license traces is outside the legitimate scope of deploying/operating the tool and constitutes destructive modification of third-party code. The SKILL.md also includes broad language about '全量学习' (read all files) and will cause the agent to read many files. The pre-scan reported unicode-control-chars in SKILL.md/static JS which is a prompt-injection / obfuscation indicator — the included script.js begins with many zero-width/control characters. Overall the instructions are broader and riskier than needed for the stated purpose.
Install Mechanism
There is no install spec (instruction-only), which is lower installer risk. However the skill bundles many source files and a requirements.txt that references packages (including openai). The absence of an explicit install step means an agent or operator may run pip install -r requirements.txt or otherwise execute scripts; the packaged code will write to disk (creating uploads/ and plugins/ directories) and perform network calls. No external download from arbitrary URLs was detected, but the repo clone step will pull code from GitHub and then the included scripts may modify files.
Credentials
requires.env declares no secrets, but the code expects optional API keys for model backends (OpenAI-compatible client configured to use Alibaba dashscope) and the requirements.txt includes openai. That's appropriate for an AI-annotation tool, but the skill does not declare or restrict how API keys will be provided. Missing an explicit primaryEnv is a mismatch but not necessarily malicious. The bigger proportionality issue is the request to remove upstream authorship metadata — that does not require credentials but is a questionable action unrelated to normal tool operation.
Persistence & Privilege
always is false and the skill does not request persistent platform privileges. The code and instructions will create folders (uploads/, plugins/, etc.) and modify files in the cloned repository (including deletion of text). While writing to its own working directories is normal for this kind of tool, the explicit instruction to permanently remove author/copyright traces from the cloned repo is a persistent destructive modification of third-party content and therefore risky.
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 t-label - 安装完成后，直接呼叫该 Skill 的名称或使用
/t-label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
v1.0.1
t-label v1.0.1
- 全面实现基于t-label工具的全流程自动化（部署、标注、训练、管理、导出）。
- 新增支持阿里云通义千问qwen3-vl-plus模型与坐标自动转换功能。
- 支持虚拟环境和Docker两种部署模式，自动初始化账号。
- 覆盖自动样本导入、多人协作标注、模型训练、评估、测试与导出。
- 内置故障排查、日志管理与结果回溯功能。
元数据
常见问题
t-label 自动化标注工具 是什么？
基于t-label工具实现全量深度学习与自动化流程，支持t-label的部署、运行、样本标注、模型训练、管理与导出全流程自动化，新增支持阿里云通义千问qwen3-vl-plus模型，内置坐标自动转换功能。当用户提到t-label相关操作（部署、标注、训练、导出等）、样本数据处理、模型训练相关需求时使用此技能。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 79 次。
如何安装 t-label 自动化标注工具？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install t-label」即可一键安装，无需额外配置。
t-label 自动化标注工具 是免费的吗？
是的，t-label 自动化标注工具 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
t-label 自动化标注工具 支持哪些平台？
t-label 自动化标注工具 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 t-label 自动化标注工具？
由 Venwell Chiang（@kumamon2019s）开发并维护，当前版本 v1.0.1。
推荐 Skills