Build or refresh the Sprang knowledge graph for this workspace. Use when the user says "/sprang", "build the knowledge graph", "scan the codebase", "index this project", or "run sprang".
Installation
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Build or refresh the Sprang knowledge graph for this workspace. Use when the user says "/sprang", "build the knowledge graph", "scan the codebase", "index this project", or "run sprang".
Check if .sprang/knowledge-graph.json exists — note its generated_at, phase, and kind (codebase or knowledge).
Detect what to analyze:
If the target directory has source code (.ts, .py, .go, .rs, etc.) → run /sprang-analyze for full LLM-driven codebase analysis.
If it contains primarily markdown notes (.md, Obsidian vault, Logseq, Zettelkasten) → run /sprang-knowledge for note graph analysis.
If both → ask the user which they want.
For codebase: run npx @faviovazquez/sprang scan $ARGUMENTS (use cwd if no args) to produce the skeleton graph (<60s), then follow /sprang-analyze for full enrichment.
For knowledge base: follow /sprang-knowledge directly — no CLI prerequisite needed.
Read .sprang/SPRANG_REPORT.md and display key findings.
Report: nodes created, edges, top insights, smells detected (codebase) or top connected notes (knowledge).
Suggest next steps: /sprang-onboard (codebase tour), /sprang-chat (ask questions), /sprang-diff (blast radius before commits), or open dashboard with pnpm --filter @sprang/dashboard dev.
