/obsidian-synthesize
Automatic synthesis - scans the vault for unnamed patterns and writes synthesis pages without being asked
> /plugin marketplace add eugeniughelbur/obsidian-second-brain > /plugin install obsidian-second-brain@obsidian-second-brain
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/obsidian-synthesize
Context preview
What this command does when you run it.
Automatic synthesis - scans the vault for unnamed patterns and writes synthesis pages without being asked
Command definition
obsidian-synthesize.mddescription: Automatic synthesis - scans the vault for unnamed patterns and writes synthesis pages without being asked
category: thinking
triggers_en: ["synthesize", "auto-synthesis", "make synthesis notes", "find unnamed patterns"]
triggers_es: ["sintetiza", "síntesis automática", "crea notas de síntesis", "busca patrones nuevos", "saca conclusiones de mis notas"]
triggers_pt: ["sintetize", "auto-síntese", "crie notas de síntese", "encontre padrões sem nome"]
triggers_zh: ["自动综合我的知识库", "生成综合笔记", "把未命名的模式写成总结", "扫描知识库并形成综合结论"]
Use the obsidian-second-brain skill. Execute `/obsidian-synthesize`:
This command can run manually or as a scheduled agent. It thinks for you.
1. Read `_CLAUDE.md` first if it exists in the vault root 2. Read `index.md` to understand all existing pages 3. Read recent operation log: if `Logs/` exists, read the last 2-3 `Logs/YYYY-MM-DD.md` files; otherwise read `log.md` (last 20 entries)
4. Scan for synthesis opportunities - spawn parallel subagents:
- **Cross-source agent**: read all sources ingested in the last 7 days (`raw/`). Find concepts that appear in 2+ unrelated sources. If the same idea shows up in a podcast transcript AND an article AND a daily note - that's a synthesis candidate.
- **Entity convergence agent**: scan the entities folder (resolved per `references/folder-map.md`) for people who appear together in multiple contexts but have no explicit connection page. If Person A and Person B keep showing up in the same projects/decisions - write a connection note.
- **Concept evolution agent**: scan the concepts folder (resolved per `references/folder-map.md`) for ideas that have been updated 3+ times. Track how the concept evolved - write a "Concept Evolution" section showing the timeline of how the user's thinking changed.
- **Orphan rescue agent**: find notes in any note folder (enumerate the folders present, per `references/folder-map.md`) with no incoming links that contain claims or ideas that SHOULD be linked to existing pages. Create the missing links and explain why.
5. For each synthesis found:
- Create `Synthesis - Title.md` in the concepts folder (resolved per `references/folder-map.md`) with:
---
date: YYYY-MM-DD
tags:
- concept
- synthesis
auto_generated: true
---- Document: what pattern was found, which sources/notes it came from (with links), what it means, and a suggested action
- Link the synthesis page FROM all the source notes it references
6. Update `index.md` with new synthesis pages 7. Append to the operation log: if `Logs/` exists write `**HH:MM** - synthesize | X synthesis pages created, Y orphans rescued, Z connections found` to `Logs/YYYY-MM-DD.md`; otherwise append `## [YYYY-MM-DD] synthesize | X synthesis pages created, Y orphans rescued, Z connections found` to `log.md` 8. If a daily note exists for today, add a Synthesis section with a brief summary
The vault should generate its own insights. Not just when asked - on its own schedule.
---
**AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md` - `## For future Claude` preamble, rich frontmatter (`type`, `date`, `tags`, `ai-first: true`, plus type-specific fields), recency markers per external claim, mandatory `[[wikilinks]]` for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future-Claude retrieval - not human reading.
**Anti-fabrication:** Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as `TBD`). See the anti-fabrication and search-completeness hard rules in `references/ai-first-rules.md`.
Read more
description: Automatic synthesis - scans the vault for unnamed patterns and writes synthesis pages without being asked category: thinking triggers_en: ["synthesize", "auto-synthesis", "make synthesis notes", "find unnamed patterns"] triggers_es: ["sintetiza", "síntesis automática", "crea notas de síntesis", "busca patrones nuevos", "saca conclusiones de mis notas"] triggers_pt: ["sintetize", "auto-síntese", "crie notas de síntese", "encontre padrões sem nome"] triggers_zh: ["自动综合我的知识库", "生成综合笔记", "把未命名的模式写成总结", "扫描知识库并形成综合结论"]
Use the obsidian-second-brain skill. Execute `/obsidian-synthesize`:
This command can run manually or as a scheduled agent. It thinks for you.
1. Read `_CLAUDE.md` first if it exists in the vault root 2. Read `index.md` to understand all existing pages 3. Read recent operation log: if `Logs/` exists, read the last 2-3 `Logs/YYYY-MM-DD.md` files; otherwise read `log.md` (last 20 entries)
4. Scan for synthesis opportunities - spawn parallel subagents:
- **Cross-source agent**: read all sources ingested in the last 7 days (`raw/`). Find concepts that appear in 2+ unrelated sources. If the same idea shows up in a podcast transcript AND an article AND a daily note - that's a synthesis candidate.
- **Entity convergence agent**: scan the entities folder (resolved per `references/folder-map.md`) for people who appear together in multiple contexts but have no explicit connection page. If Person A and Person B keep showing up in the same projects/decisions - write a connection note.
- **Concept evolution agent**: scan the concepts folder (resolved per `references/folder-map.md`) for ideas that have been updated 3+ times. Track how the concept evolved - write a "Concept Evolution" section showing the timeline of how the user's thinking changed.
- **Orphan rescue agent**: find notes in any note folder (enumerate the folders present, per `references/folder-map.md`) with no incoming links that contain claims or ideas that SHOULD be linked to existing pages. Create the missing links and explain why.
5. For each synthesis found:
- Create `Synthesis - Title.md` in the concepts folder (resolved per `references/folder-map.md`) with:
---
date: YYYY-MM-DD
tags:
- concept
- synthesis
auto_generated: true
---- Document: what pattern was found, which sources/notes it came from (with links), what it means, and a suggested action
- Link the synthesis page FROM all the source notes it references
6. Update `index.md` with new synthesis pages 7. Append to the operation log: if `Logs/` exists write `**HH:MM** - synthesize | X synthesis pages created, Y orphans rescued, Z connections found` to `Logs/YYYY-MM-DD.md`; otherwise append `## [YYYY-MM-DD] synthesize | X synthesis pages created, Y orphans rescued, Z connections found` to `log.md` 8. If a daily note exists for today, add a Synthesis section with a brief summary
The vault should generate its own insights. Not just when asked - on its own schedule.
---
**AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md` - `## For future Claude` preamble, rich frontmatter (`type`, `date`, `tags`, `ai-first: true`, plus type-specific fields), recency markers per external claim, mandatory `[[wikilinks]]` for every person/project/concept referenced, sources preserved verbatim with URLs inline, and confidence levels where applicable. If that path does not resolve from your working directory, search upward for it; if you still cannot read it, say so before writing rather than producing a note that silently skips the rule. The vault is for future-Claude retrieval - not human reading.
**Anti-fabrication:** Search exhaustively before claiming any note, person, or file is absent - false absence is the most common failure mode - and never invent facts, entities, or dates (mark unknowns as `TBD`). See the anti-fabrication and search-completeness hard rules in `references/ai-first-rules.md`.
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and people every session. 45 commands: hybrid semantic search, self-rewriting notes, key-less web research, and scheduled agents that maintain the vault while you sleep.
Repo: eugeniughelbur/obsidian-second-brain
Other commands on obsidian-second-brain.
- /create-command
Create a new obsidian-second-brain command via interview - zero markdown editing required
Open command - /idea-discovery
Surface 3-5 next-direction candidates by reading ungraduated ideas, open project questions, and orphan research notes - what is worth working on next
Open command - /notebooklm
Vault-first source-grounded research via Gemini File Search. One command, no browser. The grounded parallel to /research-deep (which is open-web via Perplexity).
Open command - /obsidian-architect
Scan a codebase and write a maintained set of architecture notes into the vault - overview, per-module notes, key decisions. Re-run to refresh without clobbering your edits
Open command - /obsidian-board-hygiene
Bulk-triage a kanban board - surface stale items and archive, reschedule, or mark them done in one pass
Open command - /obsidian-board
Show or update a kanban board - flags overdue items, updates from conversation
Open command

