agentleFS
AndyMelnykovAndyMelnykov/obsidian-claude/skills/organize/SKILL.md

organize

Skill2 starsChanged 3 months agoMITView on GitHub

Sort inbox/ notes into notes/ or projects/ folders using the fuller vault context, normalizing any raw manually-dropped files into the note template's structure first, re-run the linking pass against notes that had nothing to link to at capture time, keep topic index pages current, and audit the vault for notes with no incoming or outgoing wikilinks. Use only when the user explicitly asks to organize/sort/tidy the vault or find orphan/unlinked notes — never run automatically after capture.

16 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use postmortem, dashboard and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Hongyu-yuSkill

    postmortem

    Use when analyzing failures, outages, incidents, or negative outcomes, conducting blameless postmortems, documenting root causes with 5 Whys or fishbone diagrams, identifying corrective actions with owners and timelines, learning from near-misses, establishing prevention strategies, or when user mentions postmortem, incident review, failure analysis, RCA, lessons learned, or after-action review.

    Also in 3 projects that use this

  • GoogleSkill

    dashboard

    Configures and launches the GKE Capacity & Triage Dashboard scoped to a GCP project ID, GKE cluster name, or target ML workload ID. Uses the configure-and-launch-dashboard action and launch-workload-dashboard workflow to verify local dashboard health, discover cluster capacity, trigger live scans, and generate deep-linked URLs. Use when the user types "/dashboard", says "launch dashboard", "open dashboard", "show capacity", or "view triage dashboard" with a project, cluster, or workload. Don't use for general workload log querying or automated failure attribution (use the troubleshoot skill).

    Also in 3 projects that use this

  • ElasticSkill

    create-skill

    Interactively create a new Claude Code skill and add it to the elastic-docs-skills catalog. Use when the user wants to generate a new skill, scaffold a slash command, or build automation for docs tasks.

    Also in 3 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the note format and vault layout reference first — organize reuses its folder-placement rule, index maintenance, and linking pass.

    line 8

“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “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

Organize the vault

Read the note format and vault layout reference first — organize reuses its folder-placement rule, index maintenance, and linking pass.

This skill never runs as a side effect of capture or anything else — only when the user explicitly asks (e.g. "organize the inbox", "sort my notes", "tidy the vault", "any orphan notes?", "what's not connected?").

Filing mode

Trigger: "organize the inbox", "sort my notes", "tidy the vault", or similar.

  1. Resolve the vault per Resolving the vault. List everything in inbox/. If it's empty, say so and stop.
  2. Normalize anything that isn't already in the template's shape. A file the user dropped into inbox/ themselves (not via capture) may have no frontmatter and no source/content/connections structure. Before deciding its destination, wrap it into templates/note-template.md's current shape: derive a title/slug if it doesn't already look like one, set the source role (the original filename, or "pasted" if there's no clue), and place its existing text verbatim under the content role. This is structural normalization, not a rewrite — the wording stays exactly as given; it's not turned into a summary in anyone's "own words" the way a fresh capture would.
  3. For each inbox note, decide its destination — projects/<slug>/ or notes/<topic>/ — using the same folder placement rule and fallback question as capture, but with the benefit of whatever's been captured since. Before moving, re-check the uniqueness rule against the destination: if the target folder already has a same-named file, ask the user whether to update it or rename the incoming note — never overwrite. Move the note (a plain move; delete-and-rewrite only if the host has no move primitive), creating the destination folder if a clear new grouping emerges. If it lands in notes/<topic>/, update the index for that topic. A note that's still not a confident fit for either stays in inbox/ — organize doesn't force placement just to empty the folder.
  4. Regenerate the master index, once, if anything moved in step 3. Regenerate indexes/README.md per Master index — a moved note always changed inbox/ and one of projects/<slug>/ or notes/<topic>/, so one regeneration after the whole pass covers every change from step 3.
  5. After moving a note, re-run the linking pass against the fuller vault — a note captured before a related one existed may not have had anything to link to yet.
  6. Report what moved where, what got newly linked, what got normalized from a raw drop, and what's still sitting in inbox/ unplaced.

Link audit mode

Trigger: "any orphan notes?", "what's not connected?", or a similar request to find unlinked/isolated notes.

  1. Scan every note's outgoing [[wikilinks]]. Build the reverse (incoming) map from that.
  2. Report every note with neither incoming nor outgoing links.
  3. This is a report only. Don't force-link an orphan — a genuinely standalone note is a valid outcome, not a defect. The user decides whether to connect it (via a follow-up capture or edit) or leave it as is.

Out of scope

Doesn't rewrite a note's wording or summarize on its own initiative — step 2's normalization only wraps already-existing text into the template's structure, it never rephrases it. Doesn't run automatically after every capture; only on an explicit request.

Error handling

  • Move collision (destination folder already has a same-named file): ask, don't overwrite — same rule as capture's collision handling.
  • Vault directory not writable: report the error and stop.

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.