agentleFS
taljeontaljeon/plzdo/skills/obsidian-memory-router/SKILL.md

obsidian-memory-router

Skill9 starsChanged 17 days agoMITView on GitHub

Route Obsidian, vault, external memory, ai_knowledge, Markdown note, Bases, JSON Canvas, vault search, and Obsidian CLI tasks safely. Use when the user asks Codex to record or retrieve Obsidian memory, work with Obsidian notes, evaluate kepano/obsidian-skills, create Obsidian-flavored Markdown/Bases/Canvas files, or decide whether live vault/CLI/plugin actions are allowed.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to keep Obsidian useful without making it the source of truth.

    line 8
  2. Very specific:

    Read facts/index first. Use --read-notes only when a match is relevant.

    line 18
  3. Distinctive:

    Do not store secrets, auth data, cookies, tokens, raw logs, live DB contents, full private documents, or full papers.

    line 33
  4. Very specific:

    Do not write .obsidian/ or live plugin/theme state unless explicitly requested and safe.

    line 34
  5. Distinctive:

    Do not use Obsidian CLI as a default memory backend.

    line 35
  6. Distinctive:

    When this skill routes a request, return:

    line 39

≈ “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

Obsidian Memory Router

Use this skill to keep Obsidian useful without making it the source of truth.

Route

  1. For prior context or reusable facts, search memory first:
$META_HARNESS_ROOT/bin/harness memory 검색 "<query>"
  1. Read facts/index first. Use --read-notes only when a match is relevant; it follows matched active note paths and returns compact, validated ai_knowledge, never raw note bodies. Do not full-scan the vault.
  2. For successful meaningful work, write sanitized memory:
$META_HARNESS_ROOT/bin/harness memory 기록 --label "work-complete: short-label" --domain "<domain>" --summary "<sanitized reusable result>"

Set META_HARNESS_ROOT to the Meta Harness repository root when using these commands outside that repository.

  1. For Obsidian syntax work, use Markdown, wikilinks, callouts, properties, .base, and .canvas patterns from references/adoption.md.
  2. For live Obsidian CLI, plugin/theme reload, DOM, screenshots, or vault mutation, stop for explicit approval and confirm exact vault/path.

Boundaries

  • Obsidian is external AI memory, not source of truth.
  • Do not store secrets, auth data, cookies, tokens, raw logs, live DB contents, full private documents, or full papers.
  • Do not write .obsidian/ or live plugin/theme state unless explicitly requested and safe.
  • Do not use Obsidian CLI as a default memory backend; the harness memory CLI remains the stable path.

Output

When this skill routes a request, return:

  • Memory: search, write, skip, or pending replay.
  • Vault Action: none, read-only note syntax, file write, or approval-required live CLI.
  • Evidence: memory result, output path, validation command, or blocked reason.

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.