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

vault-save

Skill0 starsChanged 7 months agoMITView on GitHub

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").

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. az9713/claude-code-obsidian★ 4same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After all agents complete: update today's daily note

    line 31
  2. Distinctive:

    Create from template if it doesn't exist

    line 32
  3. Distinctive:

    Update index.md: if any new notes were created

    line 37
  4. Very specific:

    Do not ask where to save -- infer from _CLAUDE.md folder map.

    line 49

≈ “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-save

Save conversation knowledge to your Obsidian vault.

Steps

  1. Read _CLAUDE.md at the vault root for operating rules and folder map.
  2. Read index.md to understand what already exists.
  3. Scan the conversation and identify all vault-worthy items:
    • Decisions made or confirmed
    • Project status changes or milestones
    • Research findings or analysis results
    • Engineering insights or patterns discovered
    • Tasks created, assigned, or completed
    • Ideas, learnings, or connections
  4. Group items by type and spawn parallel subagents:
    • One agent per target folder (as defined in _CLAUDE.md folder map)
    • Each agent: search target folder for existing notes, create or update
  5. After all agents complete: update today's daily note
    • Create from template if it doesn't exist
    • Link everything that was saved
  6. Append to log.md: ## [YYYY-MM-DD] save | Brief description
  7. Update index.md if any new notes were created
  8. Report back: clean list of what was saved and where

Rules

  • All output in the user's language (from _CLAUDE.md Language section). Note content, status reports, and log entries all in user's language. When updating an existing note, match that note's language.
  • Search before creating -- duplicate notes are vault rot
  • Propagate every write -- daily note + linked notes + index
  • Never create orphans -- every note linked from somewhere
  • Match existing style -- read 1-2 notes in target folder first
  • Frontmatter mandatory -- at minimum: date + tags
  • Do not ask where to save -- infer from _CLAUDE.md folder map. Only ask if genuinely ambiguous.

Proactive Reminders

Suggest saving when:

  • 10+ exchanges without a save
  • User signals wrap-up
  • A logical work block completes (feature shipped, decision made, problem solved)

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