Novel Standard

Community

alfredxw

novel-standard

Standard writing workflow in which the main Agent drafts and revises while the built-in general-purpose SubAgent reviews, balancing quality and speed.

Overview

Publisher	alfredxw
Repository	`denova`
Skill name	`novel-standard`
Stars	906
Forks	143
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by alfredxw on GitHub. Read the source before you install it.

Installation

Install the Novel Standard AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/alfredxw/denova/tree/master/skills/novel-standard
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/alfredxw/denova.git /tmp/denova
mkdir -p .claude/skills
cp -r /tmp/denova/skills/novel-standard .claude/skills/novel-standard

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Novel Standard in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Novel Standard on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Novel Standard is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

novel-standard

Use this standard Writing Agent workflow to balance quality and speed.

Determine the writing scope

Infer the scope from the user's actual request, such as continuing a passage, writing a scene, one chapter, three chapters, a short story arc, or a custom target.
Do not assume the task is the next chapter unless the user explicitly asks for it.
There is no writing_scope field. The user message is the sole source for scope, goal, constraints, and output form.
When the user requests N chapters or another multi-part deliverable, first make a concise overall and per-chapter plan to guide the draft.

Workflow

main Agent drafts -> general-purpose SubAgent reviews -> main Agent revises and updates state -> final output

Use only the main Agent and the built-in general-purpose SubAgent. Do not assume other named SubAgents exist or start additional writing subprocesses. If the task tool is unavailable or general-purpose cannot be used, the main Agent performs the same review itself and must not fabricate delegation or review results.

Tool requirements

Before writing, use read for the necessary context: CREATOR.md, setting/outline.md, setting/progress.md, setting/character-states.md, the relevant chapter-group plan, and recent chapters. For lore, use query_lore_items with exact ids/names or search filters and detail=full to load complete bodies. Follow next_offset for additional pages; the default index only returns briefs.
After drafting, use write to create the correctly named chapter file under chapters/. For a localized revision to an existing chapter, use edit; old_string must match the current file exactly and uniquely and must not contain line-number prefixes returned by read.
When available, delegate review to general-purpose through task. Its description must state the user's goal, chapter path, necessary context sources, review focus, output format, and that the SubAgent reviews only and must not modify files.
After review, use write for a complete chapter replacement or edit for a few localized changes. Apply the same localized-edit versus complete-rewrite rule to setting/progress.md and setting/character-states.md.
Inspect every write or edit result. If it contains [tool error], invalid JSON arguments, string not found, a non-unique match, a path error, or a truncation notice, do not claim completion. Reread the target, correct the arguments, and retry, or clearly report that the write did not succeed.
Before the final response, use read to verify key excerpts from every new or revised chapter and from any updated state files.

Draft at the scope and under the constraints requested by the user, then write the draft to the correctly named chapter file under chapters/. Do not update progress or character state yet.
When available, use task to start a general-purpose SubAgent review and provide the new chapter path, user requirements, necessary context, and rules that require particular attention. Otherwise, perform the review in the main Agent.
The review returns structured issues only and does not edit prose. It must rigorously check continuity, lore grounding, pacing, prose style, character motivation, plot logic, and compliance with every creative rule. Do not include praise.
Revise the chapter directly from the review, fixing only genuine issues while preserving the original story, strong passages, effective plot beats, character voices, and continuity.
After the final revision, update setting/progress.md and setting/character-states.md in the same turn without waiting for separate chapter confirmation. Chapter status is only a UI editing marker. Suggest or perform lore updates only when an explicitly established, long-lived fact changes and the user request authorizes it.

Review requirements

The general-purpose review or main-Agent self-review may read the necessary preceding prose, CREATOR.md, outline, progress, character state, and lore for comparison. Check the new chapter against the task, user prompt, CREATOR.md, long-term outline, character canon and current state, world rules, and established continuity. Evaluate plot progression, character motivation, setting consistency, pacing, language quality, and readability. Return issues by severity with evidence locations, impact, and actionable fixes. If the execution mode does not allow writes, return only the review and revision plan.

Final output

Return the final prose or other writing artifact requested by the user.
Do not expose the review report or internal revision notes unless requested.
If a critical constraint cannot be satisfied, briefly report the blocker or ask for confirmation.

Frequently asked questions

What does the Novel Standard AI skill do?

Standard writing workflow in which the main Agent drafts and revises while the built-in general-purpose SubAgent reviews, balancing quality and speed.

Why use Novel Standard on TypingMind?

Because you install it once and use it with any model. Novel Standard is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Novel Standard in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alfredxw/denova/tree/master/skills/novel-standard. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Novel Standard?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Novel Standard?

As many as you like. As long as a model supports skills, you can use Novel Standard with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Novel Standard AI skill free?

Yes. It is published on GitHub by alfredxw under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Karpathy Guidelines

multica-ai

OrganizationPopular

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

Create Agent

Create a custom agent (.agent.md) for a specific job.

Create Hook

Create a hook (.json) to enforce policy or automate agent lifecycle events.

Generate Run Commands

microsoft

OrganizationPopular

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

novel-standard

Determine the writing scope

Workflow

Tool requirements

Review requirements

Final output

Frequently asked questions

Related AI Skills

Set up your own AI workspace now