Task Weight Manager

Use when a user wants OpenClaw to manage several interleaved conversation threads inside one chat, keep a primary mission in focus, classify side topics, ass...

This skill appears coherent and low-risk: it classifies threads, keeps a mainline, and optionally writes small template files in your current workspace. Before installing, note that: (1) the included Python script will create task-weight-manager/threads.md and related templates in whatever directory the agent runs in — if you don't want files created, run in an empty or controlled folder or inspect the script first; (2) the references discuss optional cron/heartbeat and external automation that could later require you to supply LLM or service credentials — the skill itself does not request those, but any automation you add will; (3) verify python3 is on PATH if you want to use the bootstrap. If you plan to enable periodic automation or external helpers, review those components and any credentials they need before enabling them.

Type: OpenClaw Skill Name: openclaw-task-weight-manager Version: 1.0.1 The skill bundle is a productivity tool designed to help an AI agent manage multiple conversation threads through a weighting and prioritization system. The Python script `scripts/bootstrap_workspace.py` is a simple utility that initializes the workspace by creating a directory and copying template files using standard libraries (pathlib, shutil), with no network activity or suspicious execution logic. The instructions in `SKILL.md` and the documentation in the `references/` directory focus entirely on organizational logic and state persistence within the local workspace, containing no evidence of prompt injection attacks, data exfiltration, or malicious intent.