← ClaudeAtlas

distilllisted

Aggregate already-vaulted notes from multiple sessions or sources on a specific topic into a single structured digest note. Use when the user wants to synthesize a completed research thread — 'distill everything I know about X', 'crystallize my notes on Y'. Do NOT use for: promoting session insights to memory (use recap), writing today's session summary (use wrapup), or clearing raw inbox items (use consolidate — distill works on notes already in the vault).
onebrain-ai/onebrain · ★ 10 · AI & Automation · score 77
Install: claude install-skill onebrain-ai/onebrain
# Distill Take a completed research thread, brainstorming topic, or recurring theme and compress it into a single, structured knowledge note. Unlike /wrapup (session-focused), /distill is topic-focused and spans multiple sessions. Usage: `/distill [topic]` --- ## Step 1: Identify the Topic If a topic was provided after the command, use it directly. If not, ask: > What topic do you want to distill? (e.g. "OneBrain memory architecture", "Mac Mini purchase decision", "MCP server setup") --- ## Step 2: Gather Source Material Search across the vault for notes related to the topic. Use 2–3 specific keywords or phrases from the topic (prefer proper nouns and multi-word phrases over generic single words): Use qmd if available for content searches; Grep/Glob as fallback. 1. **Session logs**: Search `[logs_folder]/session/**/*-session-*.md` for topic keywords — extract matching `## Key Decisions`, `## Action Items`, `## Open Questions` sections. (Post-v2.4.0: session logs live under `session/` only; the `-session-` infix is now defense-in-depth.) 2. **Inbox**: Search `[inbox_folder]/*.md` for related content 3. **memory/ files**: Search `[agent_folder]/memory/` for related entries — match topic keywords against filename and frontmatter `topics:` field 4. **Project/knowledge notes**: Search `[projects_folder]/**/*.md`, `[knowledge_folder]/**/*.md`, and `[resources_folder]/**/*.md` — filter by note title or first 100 words Report to user (N = total matches across all sources;