Smart Daily Assistant

When user asks to set reminders, save quick notes, get morning briefing, draft messages, use quick reply templates, translate text, plan day, schedule tasks,...

What to check before installing: - Confirm you are comfortable granting the agent read/write permission and verify (with the platform) that these permissions are limited to ~/.openclaw/smart-daily-assistant and not broader filesystem access. - Ask the author or maintainer (source is unknown) how time-based reminders are actually delivered: does the platform run the agent in the background, do you need a cron job, or do reminders only appear when you next message the agent? Don’t assume the skill will pop up notifications unless that mechanism is documented. - Because data is stored locally, review the created files after first run and avoid storing highly sensitive secrets in notes/contacts unless you add encryption. - If you do not want autonomous scheduling, disable autonomous invocation for the skill (or disable reminder-related behaviors) until you confirm how scheduling works. - The lack of a homepage or published source reduces provenance; if this matters, request source code or provenance before widespread use.

Type: OpenClaw Skill Name: smart-daily-assistant Version: 1.0.0 The skill bundle is designed to be a local-only personal assistant. It explicitly and repeatedly states that it makes no external API calls, no network requests, and sends no data to any server. All data operations are confined to the `~/.openclaw/smart-daily-assistant/` directory. The `read` and `write` permissions requested in `_meta.json` are justified and explicitly scoped within the `SKILL.md` documentation. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or instructions for prompt injection against the agent that would lead to harmful actions; instead, the instructions actively constrain the agent to benign, local operations.