agentleFS
Sign inStart free
2233admin2233admin/obsidian-vault-bridge/skills/vault-world/SKILL.md

vault-world

Skill0 starsChanged 7 months agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read index.md -- catalog of all pages (cheaper than searching)

    line 18
  2. Very specific:

    Read log.md (last 10 entries only) -- what happened recently

    line 19
  3. Very specific:

    Read dashboard/home page (if listed in _CLAUDE.md)

    line 22
  4. Distinctive:

    Read today's daily note if it exists

    line 23
  5. Distinctive:

    Read last 3 daily notes for recent momentum

    line 24
  6. Distinctive:

    Only load if needed for a specific question or task

    line 28
  7. Distinctive:

    Read active project notes

    line 29
  8. Distinctive:

    Read relevant research articles

    line 30
  9. Distinctive:

    Read technical/engineering notes

    line 31
  10. Very specific:

    Keep output concise -- this is a boot-up sequence, not a report.

    line 39
  11. Very specific:

    All output (status summary, priority list, labels) in the user's language from _CLAUDE.md Language section.

    line 40
  12. Distinctive:

    Before making vault writes (to avoid duplicates)

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/vault-world

Progressive context loader for your Obsidian vault.

Steps

  1. Read _CLAUDE.md at vault root -- operating rules and folder map.
  2. L0 -- Navigation (~1-2K tokens)
    • Read index.md -- catalog of all pages (cheaper than searching)
    • Read log.md (last 10 entries only) -- what happened recently
  3. L1 -- Current State (~2-5K tokens)
    • Read dashboard/home page (if listed in _CLAUDE.md)
    • Read today's daily note if it exists
    • Read last 3 daily notes for recent momentum
    • Scan task board for in-progress and overdue items
  4. L2 -- Deep Context (on demand, ~5-20K tokens)
    • Only load if needed for a specific question or task
    • Read active project notes
    • Read relevant research articles
    • Read technical/engineering notes
  5. Present brief status after L0-L1 (do NOT load L2 unless needed):
    • Current priorities: top 3-5 active threads
    • Open threads from last session: anything unfinished
    • Overdue / needs attention: stale tasks or projects
    • Today so far: what's already logged

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.

When to Use

  • Session start
  • User asks about vault state or what's been happening
  • Before making vault writes (to avoid duplicates)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free