agentleFS
slogsdonslogsdon/skills-vault-knowledge/skills/expand/skill.md

expand

Skill0 starsChanged 3 months agoMITView on GitHub

Use when asked to expand a stub or sparse note in the Obsidian vault through a targeted interview process. Reads the note, identifies gaps, asks batched questions, then rewrites the note in place with a structured expanded version. Invoke with /expand [note name or path].

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review.

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.
  • 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

11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 8

    Distinctive

    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. Very specific:

    Search the vault: obsidian search query='[note name]'

    line 15
  2. Very specific:

    Read the full contents: obsidian read file='[Note Name]'

    line 16
  3. Distinctive:

    If not found: stop and tell Shane to create a stub note first

    line 17
  4. Distinctive:

    Ask 4–6 questions max per round — don't firehose

    line 26
  5. Distinctive:

    Wait for responses before proceeding

    line 28
  6. Distinctive:

    After each response, assess remaining gaps

    line 31
  7. Very specific:

    Use obsidian create name='[Note Name]' content='...' silent to overwrite the note

    line 36
  8. Distinctive:

    Ask about the *why* before the *how* — motivation and audience unlock most structural decisions

    line 51
  9. Distinctive:

    When an example exists (like a PA flow or AGENTS.md), use it as an anchor: "Is X like [example], or different in this way?"

    line 52
  10. Distinctive:

    If an answer reveals a new gap, pursue it in the same round rather than waiting

    line 53
  11. Distinctive:

    If the note is already well-developed, say so and ask what specifically needs expanding

    line 60

“Common” is measured: kept by at least 6 in 10 of the 6 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

Skill: /expand [note name]

Expand a stub vault note into a structured document through a targeted interview — questions batched by theme, answers drive structure, unresolved items become open questions.

Don't: invoke if the note doesn't exist — create a stub first. Don't invent answers to unresolved questions — carry them forward as open questions in the note.

Steps

  1. Find and read the note
    • Search the vault: obsidian search query='[note name]'
    • Read the full contents: obsidian read file='[Note Name]'
    • If not found: stop and tell Shane to create a stub note first
  2. Analyze gaps
    • Identify what's present: explicit claims, named concepts, examples, open questions
    • Identify what's missing: definitions, examples, edge cases, stakeholders, success criteria, failure modes, intended audience, next actions
    • Note which gaps are blockers (can't structure the doc without them) vs. enriching (nice to have)
  3. Ask the first batch of targeted questions
    • Group questions by theme (e.g. "On the core concept:", "On the audience:", "On failure modes:")
    • Ask 4–6 questions max per round — don't firehose
    • Lead with blockers; save enriching questions for later rounds
    • Wait for responses before proceeding
  4. Ask follow-up rounds as needed
    • After each response, assess remaining gaps
    • Continue until enough is known to write a coherent structured document
    • Flag when you have enough: "I think I have enough to expand this — want me to proceed?"
  5. Rewrite the note in place
    • Use obsidian create name='[Note Name]' content='...' silent to overwrite the note
    • Note: obsidian CLI create overwrites if the note exists. If it doesn't support overwrite, fall back to the Write tool at the full vault path (this is an accepted exception — no obsidian CLI command can overwrite arbitrary content)
    • Structure the expanded note with:
      • A clear title (H1)
      • A brief framing statement (what this is, who it's for)
      • Sections derived from the interview — let content dictate structure, don't force a template
      • An Open Questions section at the bottom for anything unresolved
    • Preserve any original language worth keeping; don't sanitize Shane's voice out of it
  6. Confirm completion
    • Tell Shane the note has been updated
    • Highlight any open questions that are load-bearing (i.e. will block the next step if unresolved)

Interview Principles

  • Ask about the why before the how — motivation and audience unlock most structural decisions
  • When an example exists (like a PA flow or AGENTS.md), use it as an anchor: "Is X like [example], or different in this way?"
  • If an answer reveals a new gap, pursue it in the same round rather than waiting
  • Carry unresolved items forward as open questions in the note — don't invent answers

Notes

  • This skill is note-targeted. The note must exist before invoking — a stub is enough.
  • The expanded note replaces the stub in place; no new file is created unless Shane asks
  • If the note is already well-developed, say so and ask what specifically needs expanding

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.