Memory Bridge

If you're juggling multiple AI tools and storing their output in an Obsidian wiki, this surfaces which tool knew what. It reads your manifest file to show you all the pages Claude touched versus what Codex created versus what Hermes contributed. The diff mode is the real reason to use it: it shows you blind spots, like when Codex has twelve pages on build tooling that Claude has never seen. Helps you figure out which contexts are stuck in which tool silos. Works across projects, logs everything, and spawns impl-validator to check its own output if available.

skills.sh installs: 2.4K
GitHub stars: 3.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ar9av/obsidian-wiki --skill memory-bridge --agent claude-code

Installs into .claude/skills of the current project.

Files

Memory Bridge — Cross-Tool Knowledge Browser

You are helping the user browse and compare their Obsidian wiki knowledge filtered by which AI tool originally produced it. The wiki tracks source provenance in .manifest.json and page sources: frontmatter — this skill surfaces that metadata as a navigable view.

Before You Start

Resolve config — follow the Config Resolution Protocol in llm-wiki/SKILL.md (inline @name override → walk up CWD for .env → global config → prompt setup). This gives OBSIDIAN_VAULT_PATH.
Read $OBSIDIAN_VAULT_PATH/.manifest.json — this is the source-of-truth for what tool produced what.
Read $OBSIDIAN_VAULT_PATH/index.md for page titles and one-line descriptions.