creative-writing-skills

 

Write novels, short stories, and serial fiction with AI that maintains your voice, tracks your continuity, and gets better the more you use it. From first brainstorm to polished draft: specialized agents handle each mode of work (writing, critiquing, revising, exploring) while shared skills carry the craft methodology.

What you get:

• •Brainstorm without committing: explore plot options, character arcs, and world mechanics with multiple AI perspectives before deciding anything
• •Write in your voice: create style files from your existing prose, then draft new scenes that match
• •Catch your own mistakes: structured critique, continuity checks, and simulated reader reactions
• •Keep everything in sync: knowledge base updates as your story evolves

Quick Start

meridian mars add haowjy/creative-writing-skills
meridian mars sync
meridian bootstrap

Installation

Mars (Meridian)

meridian mars add haowjy/creative-writing-skills
meridian mars sync

Then run meridian to start a session with muse. First-time setup runs the bootstrap automatically.

Claude Code / Cowork

Claude Code and Cowork use the same plugin format.

Claude Code: add the marketplace and install:

/plugin marketplace add haowjy/creative-writing-skills
/plugin install creative-writing-skills@cw

Cowork: in the sidebar, Customize → Personal plugins → + → Create plugins → Add marketplace → Add from repository, enter haowjy/creative-writing-skills, then install the creative-writing-skills plugin. (Same flow as Claude.ai below — Cowork just also runs the agents.)

Once installed, start a session with muse as your agent:

claude --agent creative-writing-skills:muse

Run the one-time project setup to create your CLAUDE.md and kb/ structure:

/creative-writing-skills:project-setup

Claude.ai

cw-muse turns an ordinary Claude chat into a creative-writing partner. Turn it on, tell it what you're working on, and it carries you from first idea to finished draft in one conversation — talking through ideas, drafting scenes in your voice, flagging what isn't working, and revising. The other skills (prose, scene craft, critique, structure) are the craft knowledge it draws on; you don't have to invoke them yourself.

First, add the skills to claude.ai — pick one:

• •Add the marketplace (easiest): in the sidebar, Customize → Personal plugins → + → Create plugins → Add marketplace → Add from repository, enter haowjy/creative-writing-skills, and click Sync.

!Adding the marketplace in claude.ai: the plugins icon and + in the sidebar, with the repository entered in the Add marketplace dialog

• •Upload the files: download the .skill files from the latest release, then Customize → Skills → "+" → Upload skill for each one.

Then start a chat, turn on `cw-muse`, and describe what you want to write — it leads from there. Adding skills one at a time instead? Start with cw-muse, writing-principles, prose-writing, scene-construction, and prose-critique.

Want to build the files yourself? Clone the repo and run python scripts/create_skill_zips.py to regenerate them in zips/.

How It Works

flowchart TB
    You([You]) --> M[muse]

    M --> Explore
    M --> Draft
    M --> Maintain

    subgraph Explore ["Explore & Plan"]
        direction LR
        B[brainstormer] ~~~ CS[character-sim]
        CS ~~~ O[outliner]
    end

    subgraph Draft ["Draft & Revise"]
        direction TB
        W[writer] --> CR[critic]
        CR -->|synthesis| RW[revision-writer]
        RW -.->|iterate| CR
        M -.->|pivotal scenes| RS[reader-sim]
        M -.->|voice check| CC[continuity-checker]
    end

    subgraph Maintain ["Knowledge"]
        direction LR
        CH[chronicler]
        SC[style-creator]
    end

    Explore -->|direction confirmed| Draft
    Draft -->|decisions & facts| Maintain
    Maintain -.->|context for next session| Explore

Explore: Fan out brainstormers for creative variety. Spawn character-sims to discover voices. Use outliners to shape structure once a direction is chosen.

Draft & Revise: Muse runs the write/critique/revise loop: writer produces prose, critics evaluate across the four reward channels (transportation, aesthetic, social simulation, flow), revision-writer fixes specific issues. Reader-sim gives experiential signal on pivotal scenes.

Knowledge: Chronicler extracts facts from completed chapters into the kb. Style-creator captures voice patterns from prose samples. The kb grows as the project evolves, giving every future agent accurate context.

Agents

Skills

Project Layout

my-story/
├── CLAUDE.md              # Project conventions (created by project-setup)
├── story/                 # Chapters and manuscript
├── work/                  # Current drafting effort
│   ├── outline/
│   ├── drafts/
│   ├── critique-reports/
│   └── brainstorm/
└── kb/                    # Durable knowledge base
    ├── styles/            # Voice reference files
    ├── characters/        # Character state and profiles
    ├── world/             # Locations, lore, systems
    ├── timeline/          # Chronology
    ├── canon/             # Established facts
    └── issues/            # Tracked writing problems

Compatibility

Claude Code and Cowork use the same plugin format with all agents as flat subagents under muse. The Meridian version adds intermediate orchestrators (bard for drafting, lore-keeper for knowledge maintenance) for deeper context isolation. You can add the marketplace to the Claude desktop app from GitHub; Cowork runs the agents, but plain claude.ai chat runs skills only (agents grayed out) — there the cw-muse skill provides the session-lead orchestration in a single conversation, backed by the craft skills.

Current Experiments

Rhetorical questions in skill prompts. The economy section in writing-principles uses rhetorical questions ("what can you leave out and still have the scene work?") rather than declarative statements. LLMs can distinguish rhetorical from information-seeking questions internally (arxiv 2604.14128), and Self-Ask prompting shows questions improve reasoning, but no research directly tests whether rhetorical questions in system prompts improve task performance vs. equivalent declaratives. Keeping the rhetorical form to see if it activates a self-check loop that declaratives don't.

Development

Validate package

meridian mars check

Release

mars version patch              # bump, commit, tag
mars version patch --push       # bump, commit, tag, push

License

Apache License 2.0. See LICENSE.