Smart Tasks

Intelligent task management using workspace markdown files. Natural language CRUD via chat, context-aware reminders, priority briefings, and weekly reviews....

This skill appears coherent and its init script is harmless (it only creates tasks/ and small files). Before enabling: 1) Review and explicitly approve any changes to AGENTS.md, SOUL.md, or HEARTBEAT.md — especially the line about auto-reading INDEX.md at session startup; 2) If you enable cron jobs, confirm which channel credentials (telegram/discord/slack) the agent will use and whether automated alerts are acceptable; 3) Check that the agent's use of workspace memory and any automatic scans for "related files" won't read sensitive files you don't want indexed; 4) Run the included init script in a safe test workspace first to verify behavior. If you want stricter privacy, decline the proposed AGENTS.md integration or require explicit consent before session-start reads of INDEX.md.

Type: OpenClaw Skill Name: smart-tasks Version: 1.0.0 The 'smart-tasks' skill bundle is a legitimate task management system for the OpenClaw platform. It uses a shell script (scripts/init-tasks.sh) to safely initialize a local directory structure and provides clear instructions for the agent to manage tasks via markdown files. The bundle includes well-documented strategies for context management and automated reminders via internal cron jobs, and it explicitly requires user approval for any modifications to core workspace configuration files (references/workspace-integration.md).