淘宝投放数据分析
v1.0.1基于淘宝直播、超级直播和财务数据，实现自动识别、编码处理、关键指标计算及跨报表多维投放数据分析与优化建议生成。
⭐ 0· 119·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (Taobao/直播/财务 投放数据分析) match the code and SKILL.md. The code only depends on standard Python data libraries (pandas, numpy, chardet, openpyxl) and reads local files; no unrelated credentials, binaries, or services are requested.
Instruction Scope
Runtime instructions and code are limited to identifying/reading files from a user-specified data directory, cleaning data, computing metrics, and writing reports. SKILL.md and the code use environment variables like TOUFANG_DATE_RANGE, TOUFANG_DATA_DIR and TOUFANG_OUTPUT_DIR. Note: some helper/test scripts (simple_run.py, test_simple.py) contain hard-coded paths (e.g. /Users/zhouhao/Documents/投放数据 and writing to ~/Desktop) — these are local defaults and not external exfiltration, but users should be aware they will read/write those locations if not overridden.
Install Mechanism
No install spec in registry (instruction-only from platform perspective), but the package includes a requirements.txt and the README instructs 'pip install -r requirements.txt'. Installing dependencies from PyPI is normal but introduces the usual supply-chain considerations for pip packages; no remote downloads/archives or unknown URLs are used by the skill itself.
Credentials
The skill requests no secrets or credentials. Environment variables used are for date range, data directory, metrics, output dir/format — all proportional to a data-processing tool. There are no requests for unrelated service tokens or system config paths.
Persistence & Privilege
Skill does not request permanent/always inclusion (always:false). It does not modify other skills or system-wide configuration. It reads/writes only user-specified local paths.
Assessment
This skill appears to do what it claims (local data ingestion, metric calculation, HTML/CSV report generation). Before installing or running: 1) inspect/confirm the data directory you pass in (default is /Users/zhouhao/Documents/投放数据) so you know which files will be read; 2) run in a Python virtualenv and review requirements.txt before pip installing; 3) be aware outputs are written to the output directory (default ~/Desktop/投放分析报告) — change TOUFANG_OUTPUT_DIR if needed; 4) if you have sensitive data, test on a small anonymized sample first. No credentials or network endpoints are used by the code, so risk is limited to local file access and installing Python dependencies.Like a lobster shell, security has layers — review code before you run it.
latestvk97cr8cene06c80jwe14cm8yeh832dfc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.