/obsidian-recap
Summarize a time period from the vault - today, week, or month
> /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-recap
Context preview
What this command does when you run it.
Summarize a time period from the vault - today, week, or month
Command definition
obsidian-recap.mddescription: Summarize a time period from the vault - today, week, or month
category: vault
triggers_en: ["recap today", "recap the week", "summarize the week", "month recap"]
triggers_es: ["resumen de hoy", "resumen de la semana", "resume la semana", "resumen del mes"]
triggers_pt: ["recapitule hoje", "recapitule a semana", "resuma a semana", "recap do mês"]
triggers_zh: ["总结今天发生的事", "汇总本周记录", "总结这一周发生了什么", "生成本月摘要"]
Use the obsidian-second-brain skill. Execute `/obsidian-recap $ARGUMENTS`:
The argument is the period: `today`, `week`, or `month`. Default to `week` if not specified.
1. Read `_CLAUDE.md` first if it exists in the vault root 2. Determine the date range from the argument 3. List all daily notes in the range from the daily folder, resolved per `references/folder-map.md` (wiki-style `wiki/daily/`, Obsidian-style `Daily/`) 4. Spawn parallel subagents - one per daily note - to read and extract key points from each simultaneously 5. Also spawn parallel agents to read dev logs and completed kanban tasks from the same period 6. Synthesize all agent results: what was worked on, decisions made, people interacted with, tasks completed, ideas captured 7. Present as a clean narrative summary - not a raw dump of note content 8. End the recap with a **Suggested questions for future-Claude** section: 4 to 5 questions this period's vault content is uniquely positioned to answer that the user has not asked yet. Each question must cite at least one specific note (with `[[wikilink]]`) so future-Claude can resolve it without re-scanning. Prefer questions that:
- Surface tensions across notes (e.g., "Why does the X decision in [[note A]] contradict the rationale in [[note B]]?")
- Connect entities that co-appeared but were never explicitly linked
- Identify unstated next actions implied by the period's work
Avoid generic prompts ("What did I work on?") - the recap already answers those.
---
**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: Summarize a time period from the vault - today, week, or month category: vault triggers_en: ["recap today", "recap the week", "summarize the week", "month recap"] triggers_es: ["resumen de hoy", "resumen de la semana", "resume la semana", "resumen del mes"] triggers_pt: ["recapitule hoje", "recapitule a semana", "resuma a semana", "recap do mês"] triggers_zh: ["总结今天发生的事", "汇总本周记录", "总结这一周发生了什么", "生成本月摘要"]
Use the obsidian-second-brain skill. Execute `/obsidian-recap $ARGUMENTS`:
The argument is the period: `today`, `week`, or `month`. Default to `week` if not specified.
1. Read `_CLAUDE.md` first if it exists in the vault root 2. Determine the date range from the argument 3. List all daily notes in the range from the daily folder, resolved per `references/folder-map.md` (wiki-style `wiki/daily/`, Obsidian-style `Daily/`) 4. Spawn parallel subagents - one per daily note - to read and extract key points from each simultaneously 5. Also spawn parallel agents to read dev logs and completed kanban tasks from the same period 6. Synthesize all agent results: what was worked on, decisions made, people interacted with, tasks completed, ideas captured 7. Present as a clean narrative summary - not a raw dump of note content 8. End the recap with a **Suggested questions for future-Claude** section: 4 to 5 questions this period's vault content is uniquely positioned to answer that the user has not asked yet. Each question must cite at least one specific note (with `[[wikilink]]`) so future-Claude can resolve it without re-scanning. Prefer questions that:
- Surface tensions across notes (e.g., "Why does the X decision in [[note A]] contradict the rationale in [[note B]]?")
- Connect entities that co-appeared but were never explicitly linked
- Identify unstated next actions implied by the period's work
Avoid generic prompts ("What did I work on?") - the recap already answers those.
---
**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

