georgeantonopoulos

Build and maintain project-specific Obsidian knowledge bases via the obmem CLI. This skill should be used when an agent needs to (1) persist a vault mapping for a workspace, (2) capture prompt/run context as structured Markdown notes, (3) weave notes into a densely interconnected brain via bidirectional wikilinks (not just hub-and-spoke), (4) retrieve context via search/read commands, or (5) audit graph hygiene with unresolved/orphan/dead-end link checks.

Build and maintain project-specific Obsidian knowledge bases via the obmem CLI. Use when an agent needs to (1) persist a vault mapping for a workspace, (2) capture prompt/run context as structured Markdown notes, (3) auto-link notes with wikilinks for backlink coverage, (4) retrieve context via search/read commands, or (5) audit graph hygiene with unresolved/orphan/dead-end link checks.

Use when an agent needs to build, label, retrieve from, surface thoughts from, or safely write temporary memory into a Mneme graph-backed Markdown vault.

Canonical skill for Mneme — single memory system for retrieval, writing, graph connections, thought surfacing, private runtime work, and public repo development. Use for any memory, graph, vault, retrieval, synapse, or Mneme CLI task.

This skill should be used when the user asks to "create a hyperframes video", "build a hyperframes composition", "make a video with hyperframes", "render HTML to MP4", "author a kinetic title sequence", "use heygen-com/hyperframes", or scaffolds/edits any project containing hyperframes.json, index.html with data-composition-id, or a compositions/ folder. Encodes the framework's non-obvious rules (class="clip" requirement, paused GSAP timelines on window.__timelines, deterministic-only logic, the example-vs-block registry split, draft-then-final render workflow) and ships a proven teaser template plus a render-and-verify script.

Launch Ο ΝΟΣΤΟΣ in headless Chromium and drive it via the __nostos debug handle

Manage an Obsidian-backed personal memory system for an agent: resolve vault, read/search recent context, append daily events, organize notes into a stable taxonomy, distill daily notes into long-term memory, and run graph health audits.