Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill guides the maintenance of OpenClaw workspace files—the files that give an agent its identity, behavioral rules, environmental knowledge, and long-term memory. It helps agent operators, system admins, and memory engineers audit for bloat, set up new workspaces from scratch, distill daily logs into curated memory, and keep checklists and tool notes accurate. The goal is a workspace that fits the token budget and avoids stale or redundant content.
WHO IT'S FOR
AI Agent Platform Engineers
managing agent workspace lifecycle and token budgets
AI Agent Power Users
curating memory and soul files for agents
DevOps / Infrastructure Engineers
configuring multi-agent workspace paths and policies
Technical Leads / Architects
designing agent identity and behavioral rule systems
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Compatibility not documented
Use this skill
Follow the documented setup, then try a first task.
Claude Code user installation with Git
Installs: User-level installation of the openclaw-workspace skill · Claude Code
Before you start
Claude Code
Git
Run this command in a terminal to clone the skill into the recommended Claude Code user skills directory.
Replace `<path-to-workspace>` with the path to the OpenClaw workspace containing AGENTS.md.
Use the openclaw-workspace skill to review my AGENTS.md for token efficiency. The file is at `<path-to-workspace>/AGENTS.md`. Identify the most important sources of bloat or redundancy and suggest a small first set of improvements without editing the file.