Distill a person's chat style from exported conversation records and generate replies that mimic their voice. Use when (1) analyzing chat history to extract...

This skill appears to do what it says, but take care before using it: - Privacy risk: The parser will output raw chat text and the SKILL.md encourages showing concrete examples. The code does not redact sensitive items. Before running, inspect exports and remove or redact passwords, addresses, financial data, or other sensitive content. - Model transmission risk: Analysis and mimicry typically involve sending extracted text to an LLM. If you use a cloud LLM, any raw chat content you send may be stored or used in model logs. Sanitize locally before sending, or run analysis fully offline. - Consent & legality: Mimicking someone's voice can be ethically or legally sensitive. Only analyze/mimic chats for which you have explicit permission, and be aware of local laws and platform policies. - Verify behavior: If you plan to automate this skill, test on harmless/synthetic data first to confirm it does not leak content or send data to external endpoints. The included script does file parsing only (no network), but the agent's analysis step may pass text to models—confirm where that happens. - If you need enforced redaction: either add a preprocessing step that detects and removes PII before analysis, or modify the script to filter sensitive tokens. Without that, follow SKILL.md's privacy guideline manually. Given these concerns (privacy mismatch between policy text and actual code), proceed only after you ensure data sanitization and consent. Additional info that would raise confidence to 'high': explicit redaction code, or documented enforcement that sensitive content is never forwarded to external services.

Type: OpenClaw Skill Name: chat-distill Version: 1.0.0 The skill bundle is designed to analyze chat export files (WeChat, WhatsApp, Telegram, etc.) to extract linguistic styles and generate mimicked replies. The Python script `scripts/extract_messages.py` uses standard libraries and regular expressions to parse local files without any network activity, obfuscation, or unauthorized file access. The instructions in `SKILL.md` and the reference documents are well-aligned with the stated purpose and explicitly include privacy safeguards, such as advising the agent to anonymize sensitive information like passwords or addresses found in chat logs.