ai-usage-collector
PassAudited by ClawScan on May 13, 2026.
Overview
This instruction-only skill is coherent and low-risk, but it processes coworker chat content and produces spreadsheet-ready CSV, so users should review sensitive and formula-like content before sharing.
This skill appears safe to install as an instruction-only extractor. Before using it, make sure you have permission to process the chat screenshots or text, redact unrelated private messages, verify extracted names and facts, and check the CSV for formula-like cells before pasting into Excel or Teams.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Coworker names and internal chat details may be turned into a reusable table that could be shared more broadly than intended.
The skill processes group chat screenshots/text and extracts coworker identities and AI-tool usage into structured records. This is purpose-aligned, but it can summarize potentially private workplace context.
用户发送微信群截图和/或文字消息。... 姓名 | 同事姓名 ... 每周批量处理微信群消息（文字+截图）
Only provide relevant messages, redact unrelated personal or sensitive content, and verify the output before sharing it in workplace systems.
Unreviewed rows could create incorrect team records, and formula-like spreadsheet cells may be interpreted by spreadsheet software.
The skill outputs message-derived content as CSV for direct spreadsheet use. If source text contains formula-like values or extraction errors, they could be propagated into Excel/Teams unless reviewed.
以 CSV 格式（逗号分隔）输出... 用户可直接复制粘贴到 Excel / Teams 表格
Review the CSV before pasting; sanitize cells that start with characters such as =, +, -, or @ by prefixing them with an apostrophe if needed.