agentleFS
Sign inStart free
slogsdonslogsdon/skills-vault-knowledge/skills/ghost/SKILL.md

ghost

Skill0 starsChanged 3 months agoMITView on GitHub

Use when you want to answer a question in Shane's voice, when asked to ghost-write as Shane, or when the /ghost command is invoked. Do NOT use for writing in Shane's voice when he is the author — this produces content as Shane, for external use.

10 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

8 rules. 0 are common, 4 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write content in Shane's authentic voice by grounding in his vault's vocabulary and reasoning style — a mirror, not a generic imitation.

    line 8
  2. Distinctive:

    Follow Qwen Protocol with:

    line 17
  3. Distinctive:

    If Qwen is unavailable:

    line 24
  4. Very specific:

    Run obsidian search query='[argument]' limit=10 via bash to find notes related to the topic

    line 26
  5. Very specific:

    Run obsidian search query='voice OR style OR writing' limit=10 via bash to find notes that reveal Shane's voice patterns

    line 27
  6. Very specific:

    Run obsidian search query='Ghost Writer' limit=5 via bash to find the Ghost Writer Context file if it exists

    line 28
  7. Very specific:

    Read 5–8 relevant notes by running obsidian read file='[note name]' via bash for each, to absorb his vocabulary and reasoning style

    line 29
  8. Distinctive:

    Use his reasoning style (builds from first principles, acknowledges tradeoffs)

    line 32

“Common” is measured: kept by at least 6 in 10 of the 10 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: /ghost [argument]

Write content in Shane's authentic voice by grounding in his vault's vocabulary and reasoning style — a mirror, not a generic imitation.

Profiles/voice.md is authoritative for voice; read it first. Knowledge/Context/Ghost Writer Context.md is subordinate to it for register, format, and audience. Where the two disagree, voice.md wins.

Don't: invent voice patterns not present in the vault. Don't use generic writing conventions — mirror what the vault actually reveals about Shane's style. Don't invent grounding: war stories, numbers, and receipts must come from the vault or from Shane. If they don't exist, stay abstract or leave [TK: your question] — never fabricate one to sound credible.

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). Answer the question or topic '[argument]' in Shane's authentic voice. Use Profiles/voice.md (authoritative) and vault notes to mirror his vocabulary, reasoning style, and tone; Ghost Writer Context is subordinate to voice.md. Produce content as Shane would write it."
    • skill: "ghost"
  3. Review Qwen's result, synthesize if needed, and present to Shane.

Fallback

If Qwen is unavailable:

  1. Run obsidian search query='[argument]' limit=10 via bash to find notes related to the topic
  2. Run obsidian search query='voice OR style OR writing' limit=10 via bash to find notes that reveal Shane's voice patterns
  3. Run obsidian search query='Ghost Writer' limit=5 via bash to find the Ghost Writer Context file if it exists
  4. Read 5–8 relevant notes by running obsidian read file='[note name]' via bash for each, to absorb his vocabulary and reasoning style
  5. Produce the content in Shane's voice:
    • Mirror his vocabulary (direct and specific; he hedges sparingly and accurately, and when he is sure he does not soften)
    • Use his reasoning style (builds from first principles, acknowledges tradeoffs)
    • Match his tone (intellectually engaged, occasionally dry, no fluff)
    • Cite specific vault material where relevant, as he would
  6. Present the ghost-written content to Shane

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.

Check your setup, free