agentleFS
slogsdonslogsdon/skills-vault-knowledge/skills/backlinks/SKILL.md

backlinks

Skill0 starsChanged 3 months agoMITView on GitHub

Use when asked to audit backlinks or repair the knowledge graph structure, or when /backlinks is invoked. Do NOT use for finding conceptual bridges between ideas — use /connect for that.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't: use this to find conceptual bridges — that's /connect.

    line 10
  2. Distinctive:

    Follow Qwen Protocol with:

    line 15
  3. Distinctive:

    If Qwen is unavailable:

    line 22
  4. Very specific:

    If [argument] is provided, run obsidian search query='[argument]' limit=10 via bash.

    line 24
  5. Very specific:

    Read a set of notes by running obsidian read file='[note name]' via bash for each — look for [[wikilinks]] and [[note references]] embedded …

    line 25
  6. Very specific:

    If scoped to [argument], analyze the local backlink cluster.

    line 31

≈ “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

Skill: /backlinks [argument]

Audit the vault's backlink structure to surface orphaned notes, dead links, and one-way connections — the value is in finding what the knowledge graph has lost or never built.

Don't: use this to find conceptual bridges — that's /connect. Don't auto-fix findings — surface for Shane to act on.

Steps

  1. Parse the argument/topic from Shane's request.
  2. Follow Qwen Protocol with:
    • task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md), obsidian backlinks file='Note Name'. Audit the vault's backlink structure around '[argument]' (or broadly). Find orphaned notes, broken connections, and opportunities to strengthen the knowledge graph."
    • skill: "backlinks"
  3. Review Qwen's result, synthesize if needed, and present to Shane.

Fallback

If Qwen is unavailable:

  1. If [argument] is provided, run obsidian search query='[argument]' limit=10 via bash; otherwise run broad searches (e.g. obsidian search query='MOC OR index OR hub' limit=20) via bash to sample the vault
  2. Read a set of notes by running obsidian read file='[note name]' via bash for each — look for [[wikilinks]] and [[note references]] embedded in them
  3. Identify backlink health:
    • Orphaned notes: notes that exist but appear nowhere as a [[link]] in other notes
    • Dead links: [[links]] that reference notes that don't exist yet
    • One-way links: A links to B, but B never links back to A despite being clearly related
    • Hub notes: notes that are referenced frequently — check they're actually well-developed
  4. If scoped to [argument], analyze the local backlink cluster; if broad, sample across the vault
  5. Present findings as:
    • Orphaned notes (list with brief description of what's isolated)
    • Dead links / missing notes worth creating
    • Recommended reciprocal links to add
    • Hub notes that need more development
  6. Prioritize the top 3–5 highest-value repairs

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.