Principles

Ray Dalio-inspired personal knowledge system. Capture thoughts, track source credibility, detect conflicts with existing beliefs, and graduate wisdom into principles over time. Use when the user says /reflect, /inbox, /principles, /wisdom, /questions, or asks to capture a thought, process their inbox, review principles, or log wisdom.

This skill is coherent with its stated purpose: it will create and manage a personal/ directory in your workspace and will read and write the listed markdown files. Before installing, consider: (1) Where your workspace is stored and whether those files will be synced to cloud providers or backups — personal thoughts can be sensitive; (2) Whether you want the agent to be able to invoke this skill autonomously (default) and thus modify files without an explicit command every time; (3) File permissions and backups — you may prefer to put personal/ in an encrypted folder or a repo with controlled access; (4) The skill copies its instructions into personal/_system.md on init — if you don't want that metadata in your workspace, decline initialization. No network credentials or installs are requested, so there are no hidden external dependencies.

Type: OpenClaw Skill Name: principles Version: 1.0.0 The OpenClaw AgentSkills skill bundle is benign. The `SKILL.md` file outlines a personal knowledge management system, instructing the AI agent to create, read, and write files exclusively within a user-specific `personal/` directory. All file system operations are directly aligned with the stated purpose of managing notes, wisdom, and principles. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's core function or perform unauthorized actions. The instructions are clear, transparent, and limited to local file management within the designated workspace.