obsidian-panel
The obsidian-panel command pressure-tests a decision by soliciting independent verdicts from multiple distinct perspectives, either from custom advisor personas stored in the vault or from four generic lenses (skeptic, user, operator, long-game thinker). Each panelist argues their position separately before a synthesis is written that preserves disagreement and recommends action with acknowledged risks. Use it when a decision needs scrutiny from genuinely different angles rather than a single adversarial challenge.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/eugeniughelbur/obsidian-second-brain/HEAD/commands/obsidian-panel.md -o ~/.claude/commands/obsidian-panel.mdobsidian-panel.md
Use the obsidian-second-brain skill. Execute `/obsidian-panel [decision or question]`: Pressure-tests a decision from several independent angles at once. Where `/obsidian-challenge` red-teams from one adversarial stance, this gathers a panel of distinct lenses and makes each argue on its own before you see a synthesis. 1. Resolve the decision/question from the argument. If none, ask what to put to the panel. 2. Choose the panel: - If the vault has an `Advisors/` folder, read those persona notes and use each as a panelist (each verdict reflects that advisor's stated lens and priorities). - Otherwise, use 4 generic lenses: the skeptic (what breaks this), the user/customer (who is served or hurt), the operator (can this actually be run/maintained), and the long-game (what does this look like in a year). 3. For EACH panelist, write an independent verdict: their position, the strongest reason behind it, and what would change their mind. Keep them genuinely distinct - do not let them converge prematurely. 4. Write a synthesis: where the panel agreed, where it split, and a recommended decision with its main risk. Do not hide the disagreement - the split is the most useful output. 5. Save to `wiki/concepts/YYYY-MM-DD - panel - <slug>.md` (`type: synthesis`, tagged `[thinking, panel]`), linking any `[[Advisors/...]]` notes and `[[entities/projects]]` the decision touches. Cross-link from today's daily note. --- **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. The vault is for future-Claude retrieval - not human reading. **Anti-fabrication:** If you use `Advisors/` notes, base each verdict on what that note actually says - do not invent an advisor's position or attribute views to a real person they have not expressed. Never fabricate a consensus; report the real split. 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