Idea discovery

--- description: Identify 3:5 potential next steps by reviewing unorganized ideas, open project questions, and orphaned research notes:what’s worth working on next category: thinking triggers_en: ["what should I work on next", "idea discovery", "identify next steps", "what’s worth pursuing"] --- Use the obsidian-second-brain skill. Run /idea-discovery: Answers the question “what is worth doing next” based on material already in the vault. Distinct from /obsidian-emerge (which identifies unstated patterns) and /obsidian-graduate (which promotes a single chosen idea into a project):this ranks several candidate directions so you can pick one. 1. Gather candidate signals:list and search exhaustively (see the anti-fabrication rule): - Ungraded ideas in Ideas/ (status captured or exploring, not yet graduated). - Open questions in active project notes (Open Questions sections, unresolved decisions). - Orphan research notes in Research/ that no project links to. 2. Rank the candidates using a simple, stated heuristic: recency (recently accessed), pull (how many notes reference or depend on it), and momentum (is there already work building toward it). State the heuristic in the output so the ranking is auditable. 3. For each of the top 3:5, write: the candidate, why now, the [[source notes]], and the smallest next step that would move it forward. 4. Optionally, suggest running /research [topic] on a candidate to gather external feedback before committing, or /obsidian-graduate to promote it to a full project. 5. Save the shortlist to Ideas/YYYY-MM-DD - discovery.md (type: synthesis, tagged [thinking, idea-discovery]) with source links in the frontmatter. Do NOT auto-graduate anything:this command only surfaces and ranks. --- 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-Clauderetrieval:not for human reading. Anti-fabrication: Rank only real candidates found in the vault:never invent an idea, an open question, or a research note to pad the shortlist. Exhaustively listIdeas/s, project Open Questions, and orphan research rather than sampling them. See the anti-fabrication and search-completeness hard rules at references/ai-first-rules.md.