agentleFS
benororbenoror/obsidianos_work/.agents/skills/people-stubs/SKILL.md

people-stubs

Skill166 starsChanged 5 months agoMITView on GitHub

Batch-create Teams/People/@Name.md stubs from unresolved [[@*]] wikilinks across the vault. Each stub is minimal frontmatter; the user fills team/role/details later.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    When meeting notes are wrapped via /fill-participants, names get linked as [[@Jane Doe]], [[@John Smith]], etc.

    line 16
  2. Very specific:

    Run obsidian unresolved format=json and filter to entries where the link target starts with @.

    line 24
  3. Distinctive:

    Ask the user: "all", "1,2", "none", or per-line skips.

    line 38
  4. Very specific:

    Use obsidian create path="Teams/People/@<Name>.md" content="<frontmatter>" so Obsidian indexes it immediately (the next /vault-health run …

    line 53
  5. Very specific:

    Leave FullName, Team, Location empty — the stub is a placeholder.

    line 55
  6. Very specific:

    Filename collision: if Teams/People/@<Name>.md exists already (even empty), don't overwrite.

    line 79

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

People Stubs

Usage

  • /people-stubs — Scan unresolved [[@*]] links, present a creation list, prompt to confirm each.
  • /people-stubs --auto — Create stubs for every unresolved [[@*]] link without per-name confirmation. Useful after a big batch of new interviews.

Why this skill exists

When meeting notes are wrapped via /fill-participants, names get linked as [[@Jane Doe]], [[@John Smith]], etc. If the corresponding Teams/People/@Name.md file doesn't exist yet, Obsidian shows a dead-link indicator and the name doesn't appear in People.base. This skill creates the missing stubs in one pass.

Stubs are intentionally minimal — they're placeholders. The user (or a future /onboard-person skill) fills in the real metadata (Team, Location, FullName, Start Date, etc.).

Workflow

Step 1: Discover unresolved [[@*]] links

Run obsidian unresolved format=json and filter to entries where the link target starts with @. Aggregate by target — one stub per unique target, with a list of files where it's referenced.

Step 2: Present the creation list

Display a numbered table sorted by reference count descending:

| # | Stub to create | Referenced in (count) | Sample file |
|---|----------------|----------------------|-------------|
| 1 | Teams/People/@Jane Doe.md | 6 | Meetings/Interviews/Interview Alex Kim... |
| 2 | Teams/People/@John Smith.md | 3 | Meetings/Engineering/Weekly Team Leads... |
| 3 | Teams/People/@Alex Kim.md | 2 | Meetings/Engineering/Weekly Team Leads... |

Ask the user: "all", "1,2", "none", or per-line skips.

Step 3: Create stubs

For each confirmed stub, write Teams/People/@<Name>.md with this minimal frontmatter:

---
FullName:
Team:
Location:
created: <ISO 8601 with offset>
---

Use obsidian create path="Teams/People/@<Name>.md" content="<frontmatter>" so Obsidian indexes it immediately (the next /vault-health run won't show the link as unresolved any more).

Leave FullName, Team, Location empty — the stub is a placeholder. The agent can fill in FullName if it can infer from the wikilink display text (e.g. [[@Jane Doe]] → FullName: Jane Doe).

Step 4: Report

Print a summary:

Created 3 stubs:
  Teams/People/@Jane Doe.md
  Teams/People/@John Smith.md
  Teams/People/@Alex Kim.md

Next steps:
- Open each stub and fill in Team / Location / Start Date.
- Or run /onboard-person <name> to pull metadata from external sources.

Step 5: Commit

See /commit. Commit message: chore(people): add N stubs (Jane Doe, John Smith, ...).

Important Notes

  • Don't create stubs for the user's own aliases — they're handled by USER.md aliases.
  • Don't create stubs for candidate names (someone interviewed once but never hired). The /vault-health report should let the user skip those manually. If a name has only 1-2 references and they're all from an interviews folder, surface a hint that this might be a candidate.
  • Filename collision: if Teams/People/@<Name>.md exists already (even empty), don't overwrite. Skip and note in the report.
  • Stubs make subsequent /vault-health runs cleaner — the unresolved-links count drops as stubs are created.

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.