The Agent Skills Directory

[SAFE]: The skill instructions define a purely functional workflow for organizing Markdown files in a personal knowledge management system. It establishes rules for file naming, metadata tagging, and content structure that align with standard productivity workflows.
[COMMAND_EXECUTION]: The skill uses platform-provided tools (Read, Edit, Write, Grep, Glob) to perform file operations within the Obsidian vault. These actions are scoped to the intended purpose of managing vault notes and do not involve arbitrary command execution or shell access.
[DATA_EXFILTRATION]: There are no network operations or external communication patterns. The skill operates entirely on local vault data without attempting to transmit information to remote servers.
[PROMPT_INJECTION]: The instructions do not contain attempts to override agent behavior, bypass safety filters, or extract system prompts. The language is instructional and focused on the task of MOC curation.
[INDIRECT_PROMPT_INJECTION]: While the skill reads and processes user-controlled notes from an Obsidian vault (ingestion points), the capabilities are limited to file manipulation within the vault scope. The instructions include safety guidelines to preserve user-defined structures and intent, which mitigates risk.

vault-mocs