القائمة
Load vault context progressively -- identity, navigation, current state. Use at session start or when context about the vault is needed. Token-budgeted: start light, go deeper only as needed.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Vault argues back. Pulls your own history to challenge current thinking. Use when making decisions, proposing architecture, or before committing to a direction. The vault is not a yes-man -- it remembers what you've learned the hard way.
Bridge unrelated vault domains. Find structural analogues between different areas. The vault's link graph knows connections you haven't seen.
Surface unnamed patterns from recent vault activity. Reads N days of notes and finds recurring themes you haven't explicitly named. The vault notices what you don't.
Promote scattered vault mentions into dedicated notes. When an idea, pattern, or concept reaches critical mass (3+ mentions across contexts), it deserves its own page. Graduate it from scattered references to first-class citizen.
Ingest external content and REWRITE existing vault pages with new context. Not just "add a note" -- one source touches 5-15 existing pages. Resolves contradictions, updates claims, creates synthesis pages. The vault grows by integration, not accumulation.
Save everything worth keeping from the current conversation to the Obsidian vault. Use when conversation produces decisions, research, tasks, project updates, or insights. Also triggers on session wrap-up ("done", "that's it", "thanks").
| name | vault-world |
| description | Load vault context progressively -- identity, navigation, current state. Use at session start or when context about the vault is needed. Token-budgeted: start light, go deeper only as needed. |
Progressive context loader for your Obsidian vault.
Read _CLAUDE.md at vault root -- operating rules and folder map.
L0 -- Navigation (~1-2K tokens)
index.md -- catalog of all pages (cheaper than searching)log.md (last 10 entries only) -- what happened recentlyL1 -- Current State (~2-5K tokens)
_CLAUDE.md)L2 -- Deep Context (on demand, ~5-20K tokens)
Present brief status after L0-L1 (do NOT load L2 unless needed):
Keep output concise -- this is a boot-up sequence, not a report.
All output (status summary, priority list, labels) in the user's language from _CLAUDE.md Language section.