agentleFS
FiredMosquito831FiredMosquito831/my-writing-companion/skills/creative-writing-muse/SKILL.md

creative-writing-muse

Skill2 starsChanged 25 days agoApache-2.0View on GitHub

Load when no subagents are available and one agent must plan, draft, critique, research, and capture memory by switching stances.

2 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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when there are no subagents.

    line 10
  2. Distinctive:

    Start by understanding author intent: desired reader simulation, emotional target, constraints, taste signals, open uncertainty, and what …

    line 15
  3. Distinctive:

    Before doing the next pass, name the prompt you are giving yourself:

    line 41
  4. Distinctive:

    Ask the author only when the answer would change the work.

    line 50
  5. Distinctive:

    Before switching stance, synthesize what changed and whether the next move still serves the author's intent.

    line 59

≈ “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

Creative Writing Muse

Use this when there are no subagents. Act as the muse in one conversation by loading the relevant writing skills and switching stances deliberately. Keep the author-facing thread coherent while you move between direction, drafting, critique, revision, and memory.

Start by understanding author intent: desired reader simulation, emotional target, constraints, taste signals, open uncertainty, and what should remain unsaid. Keep that intent visible as you change stance. The author has the final say.

Choose the Stance

Load the skills needed for the next stance:

  • Direction: /story-planning
  • Drafting: /creative-writing-modes, /creative-writing-craft, /llm-writing
  • Critique: /story-review, /reader-sim, /writing-principles
  • Research: /creative-research
  • Voice and terms: /creative-writing-craft, /character-sim, /shared-dao
  • Memory: /story-memory; also /kb-management and /project-setup if available
  • Ledgers: /story-ledgers — planning chapters, capturing what a chapter changed, answering what's still open / who knows what
  • Series: /series — linking a book to a library, bootstrap and retcon lifecycle, the retcon detection catalog, handoff generation, series state card (optional library layer; advisory-only, no fourth gate)
  • Gates: /gates — before accepting a pivotal chapter, before export, any scoring task
  • Demolition: /demolition — offered before marking a chapter final (author may decline)
  • Voice: /voice — voice capture, drift checks, retune when the prose stops sounding like the author

Note: in single-agent mode (this skill), the stance switch replaces subagent isolation — demolition and drafting must never share a stance-turn.

Self-Prompt Before Each Stance

Before doing the next pass, name the prompt you are giving yourself:

  • What is the author's intent for this pass?
  • What reader effect should the output create or protect?
  • Which constraints, style references, canon, and vocabulary matter now?
  • What should remain ambiguous, unresolved, rough, or strange?
  • What output should this pass produce?
  • What would be the wrong kind of success?

Ask the author only when the answer would change the work. Otherwise state your read and continue.

Keep Stances Separate

Explore without committing too early. Draft before judging. Critique from the reader's experience. Revise the highest-impact issue. Update memory only for settled facts and decisions.

Before switching stance, synthesize what changed and whether the next move still serves the author's intent. For pivotal passages, create two meaningfully different takes and explain what each take proves.

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.