obsidian-review
The obsidian-review command generates a structured weekly or monthly retrospective note by synthesizing vault history, including accomplishments, decisions, collaborators, and learnings extracted from daily notes, project statuses, and completed tasks. Use this to create accountability records and surface implicit patterns or next actions by generating targeted follow-up questions grounded in specific vault notes, ensuring future Claude interactions remain contextual and vault-aware.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/eugeniughelbur/obsidian-second-brain/HEAD/commands/obsidian-review.md -o ~/.claude/commands/obsidian-review.mdobsidian-review.md
Use the obsidian-second-brain skill. Execute `/obsidian-review $ARGUMENTS`: The optional argument specifies `weekly` or `monthly`. Ask if not clear from context. 1. Read `_CLAUDE.md` first if it exists in the vault root 2. Determine the period: weekly or monthly 3. Read daily notes and dev logs for the period 4. Read active projects and check for status changes 5. Read completed tasks from kanban boards 6. Draft a review note using `Templates/Review.md` (or lowercase `templates/Review.md`) if one exists, otherwise use: - What I accomplished - Key decisions made - People I worked with - What I learned - What to carry forward - **Suggested questions for future agent** - 4 to 5 questions this period's vault content can answer that the user has not asked yet. Each question must cite at least one specific note (with `[[wikilink]]`). Prefer questions that surface contradictions across notes, connect entities that co-appeared without being explicitly linked, or name an unstated next action. Skip generic prompts the review section already covers. 7. Save to the reviews folder resolved per `references/folder-map.md` (read the vault's `_CLAUDE.md` Folder Map first; wiki-style `wiki/reviews/`, Obsidian-style `Reviews/`), named `YYYY-MM-DD - Weekly Review.md` (or Monthly) 8. Link from the last daily note of the period --- **AI-first rule:** Every note created or updated by this command MUST follow `references/ai-first-rules.md` - `## For future agent` 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 agent 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`.
>
Create a new obsidian-second-brain command via interview - zero markdown editing required
Surface 3-5 next-direction candidates by reading ungraduated ideas, open project questions, and orphan research notes - what is worth working on next
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).
Generate a decision record when the vault structure changes - the vault knows why it knows what it does
Read Google Calendar and write an AI-first snapshot to the vault - today, week, next week, or a custom range
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
Show or update a kanban board - flags overdue items, updates from conversation