Zettelclaw

Work inside a Zettelclaw vault using the current typed frontmatter schema, inbox + Base workflows, and human-write/agent-read guardrails. Use when creating,...

This skill is instruction-only and appears coherent with its purpose: helping an agent work inside a Zettelclaw vault. Before enabling it, confirm the following: (1) Only grant the agent filesystem access to the intended vault directory (don’t expose unrelated files). (2) If you don’t want the agent to act autonomously, disable autonomous invocation for this skill or require explicit user confirmation for edits. (3) Back up your vault/templates before allowing any automated edits. (4) Note that qmd/rg are optional helpers—the skill will read templates and files in the vault, so verify those files are ones you expect the agent to access. If you want extra assurance, review agent actions on a per-request basis (keep human-in-the-loop for any note creation, renaming, moving, or deletion).

Type: OpenClaw Skill Name: zettelclaw Version: 2026.3.11 The Zettelclaw skill bundle provides a structured framework for managing a Zettelkasten-style vault, focusing on note organization, metadata standards, and search workflows. It includes explicit guardrails in SKILL.md that prevent the agent from modifying, moving, or deleting files without user consent, and it utilizes standard search tools like ripgrep (rg). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.