在 Manus 中运行任何 Skill
一键导入
一键导入
一键在 Manus 中运行任何 Skill
开始使用$pwd:
$ git log --oneline --stat
stars:331
forks:59
updated:2026年1月22日 15:00
文件资源管理器
SKILL.md
2 个文件
readonly
package.json
$ install --global
$ download --local
$ useful --forSOC
Process CSV data files by cleaning, transforming, and analyzing them. Use this when users need to work with CSV files, clean data, or perform basic data analysis tasks.
Deploy a Vibes app to exe.dev VM hosting. Uses nginx on persistent VMs with SSH automation. Supports client-side multi-tenancy via subdomain-based Fireproof database isolation.
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment plan.
Integrate Trackio for experiment tracking in Kaggle competitions. Use PROACTIVELY when user trains models, logs metrics, or manages experiments. Keywords: 実験, 訓練, train, training, tracking, metrics, 指標, ログ
Use Microsoft Fabric CLI (fab) to manage workspaces, semantic models, reports, notebooks, lakehouses, and other Fabric resources via file-system metaphor and commands. Use when deploying Fabric items, running jobs, querying data, managing OneLake files, or automating Fabric operations. Invoke this skill automatically whenever a user mentions the Fabric CLI, fab, or Fabric.
Provides automated fact-checking, quality assessment, and self-validation capabilities for AI outputs. Use this skill when you need to verify factual claims, assess implementation quality, or ensure outputs meet production standards before delivery.
| name | excel-field-analyzer |
| description | 分析Excel/CSV字段结构，AI自动生成中英文映射，验证翻译质量，输出统计报告。用于电子表格分析、数据字典创建、字段映射场景。 |
| allowed-tools | Read, Bash, Write, Glob, Grep |
智能分析 Excel 与 CSV 文件，自动生成中英文字段映射、统计报告与 HTML 可视化。
核心能力：
直接与 Claude 对话：
"帮我分析这个 Excel 文件的字段"
"分析 ./data/insurance_data.xlsx 的字段映射"
# 基础分析
python scripts/analyzer.py <file_path> [output_dir] [topn]
# 示例
python scripts/analyzer.py data.xlsx ./output 10
# 支持格式：.xlsx, .xls, .csv, .txt
商业险保费 → commercial_premium（finance/number）三级机构 → org_level_3（organization/string）确认时间 → time_confirm（time/datetime）custom.json 便于复用示例：
🔍 Found 70 unknown fields
💡 Using AI to generate mappings...
✅ Generated 70 mappings and saved to custom.json
- 刷新时间 → time_refresh [time/datetime]
- 交叉销售标识 → flag_cross_sales [flag/string]
- 签单保费 → premium_signing [finance/number]
custom.json{
"field_name": "commercial_premium",
"cn_name": "商业险保费",
"group": "finance",
"dtype": "number",
"role": "measure",
"aggregation": "sum",
"is_mapped": true
}
| 分组 | 描述 | 示例 |
|---|---|---|
| finance | 财务数据 | 保费、赔款、费用 |
| organization | 机构信息 | 三级机构、四级机构 |
| vehicle | 车辆相关 | 车牌、车型 |
| product | 产品信息 | 险类、险种 |
| time | 时间字段 | 确认时间、起保日期 |
| flag | 状态标识 | 续保标识、新能源标识 |
| partner | 合作方信息 | 4S 集团、经销商 |
| general | 通用字段 | 业务类型、客户类别 |
pip install pandas openpyxl numpy
MIT 许可证