para-pkm

Manage PARA-based personal knowledge management (PKM) systems using Projects, Areas, Resources, and Archives organization method. Use when users need to (1) Create a new PARA knowledge base, (2) Organize or reorganize existing knowledge bases into PARA structure, (3) Decide where content belongs in PARA (Projects vs Areas vs Resources vs Archives), (4) Create AI-friendly navigation files for knowledge bases, (5) Archive completed projects, (6) Validate PARA structure, or (7) Learn PARA organizational patterns for specific use cases (developers, consultants, researchers, etc.)

This skill appears to do exactly what it says: create PARA folders, generate a short AI navigation file, validate structure, and archive projects. Things to consider before installing or running it: 1) The scripts make and modify files in the filesystem—init creates directories and README/AGENTS.md; generate_nav writes AGENTS.md; archive_project moves a project into archives and deletes the original—so back up your KB before using archive_project. 2) archive_project may error if you supply an absolute project path outside the kb root (it uses Path.relative_to), so test on a disposable directory first. 3) No network or credentials are required, and no external installs occur, but you need a Python runtime to run the scripts. If you want additional assurance, review the scripts locally and run them in a safe test folder before applying them to production data.

Type: OpenClaw Skill Name: para-pkm Version: 1.0.0 The skill bundle is designed for managing a PARA-based personal knowledge management system. All Python scripts perform file system operations (creating, reading, writing, moving, deleting files and directories) which are directly aligned with their stated purpose of initializing, archiving, generating navigation, and validating the knowledge base structure. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or obfuscation. The SKILL.md and other documentation files provide instructions for the AI agent on how to understand and interact with the PKM system and its tools, without any signs of prompt injection attempting to subvert the agent's purpose or perform unauthorized actions.