agentleFS
benororbenoror/obsidianos_work/.agents/skills/onboard-person/SKILL.md

onboard-person

Skill166 starsChanged 5 months agoMITView on GitHub

Create or enrich a Teams/People/@Name.md file with metadata pulled from external sources (an ATS for hiring data, a profile source for bio). Replaces manual data entry for newly-hired teammates.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 2 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When a new teammate joins, manually creating their @Name.md file means hopping between your ATS, a profile source, and the vault to copy …

    line 17
  2. Very specific:

    If neither MCP is set up yet, gracefully fall back to manual input — prompt the user for each property one at a time, defaults filled in …

    line 38
  3. Very specific:

    Use known mappings (e.g. eng membership → [[+Engineering]], design → [[+Design]], etc.).

    line 42
  4. Distinctive:

    If team is ambiguous, ask the user.

    line 44
  5. Very specific:

    Use obsidian create path="Teams/People/@<Name>.md" content="<frontmatter + body>".

    line 48
  6. Very specific:

    Run obsidian property:read name=FullName path="Teams/People/@<Name>.md" to confirm the write.

    line 66
  7. Distinctive:

    Conflicting data: if the ATS says Team A but the user manually says Team B, prefer manual input.

    line 75
  8. Very specific:

    Name collision: if Teams/People/@<Name>.md exists with non-empty content, switch to enrich mode (additive only, no overwrites).

    line 76
  9. Very specific:

    Candidate handling: if --candidate, write to Teams/People/Candidates/@<Name>.md instead.

    line 77

≈ “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

Onboard Person

Usage

  • /onboard-person <Name> — Create or enrich Teams/People/@<Name>.md. Pulls from available MCPs (an applicant-tracking system for hiring data, a professional-network profile source for bio).
  • /onboard-person @<Name> — Same; bracket-less form also accepted.
  • /onboard-person <Name> --candidate — Treat as a candidate stub (lower-confidence frontmatter, parked in Teams/People/Candidates/).

Why this skill exists

When a new teammate joins, manually creating their @Name.md file means hopping between your ATS, a profile source, and the vault to copy FullName, Team, Location, Start Date, and so on. This skill consolidates the data pull and stub creation into one prompt.

It's complementary to /people-stubs: that one creates empty stubs from unresolved wikilinks; this one fills out a single stub with real metadata.

Workflow

Step 1: Check what exists

  • Teams/People/@<Name>.md exists? → enrich mode (add missing properties, never overwrite existing ones)
  • Doesn't exist? → create mode

Step 2: Gather metadata

Try the following sources in order, accumulating what each returns. Which MCPs are available depends on your setup — examples below:

SourceMCP / toolPulls
ATS (if MCP available, e.g. Greenhouse)the ATS's MCP tools (when set up)FullName, Role, Start Date, Hiring manager, Team (mapped from job → team)
Profile source (if MCP available, e.g. LinkedIn)the profile MCP (when set up)FullName, Location, Job title, Profile URL
Manual fallbackPrompt the userWhatever's missing

If neither MCP is set up yet, gracefully fall back to manual input — prompt the user for each property one at a time, defaults filled in from the wikilink display name (e.g. [[@Jane Doe]] → FullName: Jane Doe).

Step 3: Resolve Team

Use known mappings (e.g. eng membership → [[+Engineering]], design → [[+Design]], etc.). Cross-reference with Teams/+TeamName.md files via obsidian list folders path=Teams to confirm the team file exists.

If team is ambiguous, ask the user.

Step 4: Write the file

Use obsidian create path="Teams/People/@<Name>.md" content="<frontmatter + body>". Frontmatter shape:

---
FullName: <Full Name>
Team: "[[+<TeamFile>]]"
Location: <Country flag emoji>
Office: <City, if applicable>
Start Date: <YYYY-MM-DD>
created: <ISO 8601 with offset>
---
#team-<short> #<role-tag>

Body: usually empty for new stubs. If pulled from a profile source, add a single-line bio.

Step 5: Verify

Run obsidian property:read name=FullName path="Teams/People/@<Name>.md" to confirm the write. If --candidate, ALSO verify the file is in Teams/People/Candidates/.

Step 6: Commit

See /commit. Commit message: chore(people): onboard @<Name> (<Team>).

Edge Cases

  • MCPs not yet set up: skill falls back to interactive prompting. Note in output: "ATS MCP not configured — used manual entry. Set up via /mcp."
  • Conflicting data: if the ATS says Team A but the user manually says Team B, prefer manual input. Log the conflict.
  • Name collision: if Teams/People/@<Name>.md exists with non-empty content, switch to enrich mode (additive only, no overwrites).
  • Candidate handling: if --candidate, write to Teams/People/Candidates/@<Name>.md instead. This keeps the main Teams/People/ clean for actual teammates and prevents candidates from polluting People.base Active view (which filters by file.folder == "Teams/People" and would not match a sub-folder).

Important Notes

  • Never overwrite an existing non-empty property. Use enrich (fill blanks) only.
  • The skill creates a file; subsequent skills (like /fill-participants) consume it. Order matters when bulk-onboarding from a fresh batch of interview notes.
  • Candidates folder filtering: ensure People.base Active view filter (file.folder == "Teams/People") excludes sub-folders. If not, candidates will show up.

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.