← 返回 Skills 市场
51
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install cut-tool
功能描述
Extract specific fields or columns from text files using delimiter-based parsing. Use when you need to select columns from CSV, TSV, or delimited data.
使用说明 (SKILL.md)
Cut Tool - Field Extraction
Extract columns and fields from delimited text files by specifying delimiter and field position. Ideal for processing log files, CSV data, and structured text.
Quick Start
cut-tool -d ',' -f 1,3 data.csv
Features
- Extract fields by position (-f 1,3,5)
- Custom delimiter (-d for comma, tab, space)
- Complement selection (everything except specified fields)
- Output range of characters (-c 1-10)
Examples
# Extract first and third columns from CSV
cut-tool -d ',' -f 1,3 data.csv
# Extract characters 1-10 from each line
cut-tool -c 1-10 file.txt
# Use tab as delimiter
cut-tool -f 2-4 file.tsv
安全使用建议
This package is inconsistent: the documentation promises a cut-like CLI with flags, but the included script only prints the first five characters of each stdin line and does not implement any flags or an install. Do not rely on this skill for field/column extraction. If you need a cut utility, use the system 'cut' (coreutils) or ask the author to: (1) add argument parsing and implement the documented features, (2) provide an install wrapper so 'cut-tool' is available on PATH, and (3) document exactly what input/output behavior to expect. From a security perspective there are no obvious secrets or network operations, but the mismatch suggests sloppy or incomplete packaging — treat it as untrusted until fixed.
功能分析
Type: OpenClaw Skill
Name: cut-tool
Version: 1.0.0
The tool exhibits a significant discrepancy between its documentation and implementation. While SKILL.md describes a versatile field extraction tool supporting delimiters and character ranges, the actual implementation in scripts/cut.py is a hardcoded script that merely prints the first five characters of every line, ignoring all command-line arguments. While no explicitly malicious logic like data exfiltration or remote code execution was found, the misrepresentation of functionality is a red flag.
能力评估
Purpose & Capability
The skill claims delimiter-based field extraction, -f/-d/-c flags, complement selection, and a 'cut-tool' CLI, but the sole script ignores arguments and simply prints the first five characters of each input line. There is no wrapper or installation that would provide the CLI named in documentation.
Instruction Scope
SKILL.md instructs running 'cut-tool' with various flags and operating on files, but the runtime artifact reads only stdin and implements only line[:5]. The instructions therefore overreach the actual behavior and could mislead users about what data will be processed or how.
Install Mechanism
There is no install spec (instruction-only plus a script file). This reduces attack surface, but also means the documented 'cut-tool' command is not provided; the script sits in scripts/cut.py and would need to be installed or invoked directly to run.
Credentials
The skill requests no environment variables, no credentials, and references no config paths — its resource requests are minimal and proportionate to a simple text-processing tool.
Persistence & Privilege
The skill does not request persistent or elevated privileges (always:false) and does not modify other skills or system-wide configuration.
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 cut-tool - 安装完成后，直接呼叫该 Skill 的名称或使用
/cut-tool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
v1.0.0
Initial release
元数据
常见问题
Cut Tool 是什么？
Extract specific fields or columns from text files using delimiter-based parsing. Use when you need to select columns from CSV, TSV, or delimited data. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 51 次。
如何安装 Cut Tool？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cut-tool」即可一键安装，无需额外配置。
Cut Tool 是免费的吗？
是的，Cut Tool 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Cut Tool 支持哪些平台？
Cut Tool 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 Cut Tool？
由 BIN（@dinghaibin）开发并维护，当前版本 v1.0.0。
推荐 Skills