Story Sense logo

Story Sense

Community
jwynia
story-sense

Diagnose what any story needs regardless of its current state. This skill should be used when a writer is stuck, evaluating story problems, when narrative feels broken, or when someone asks 'what's wrong with my story?'. Keywords: story, diagnosis, stuck, narrative, plot, character, worldbuilding, revision.

Overview

Publisherjwynia
Repositoryagent-skills
Skill namestory-sense
Stars
159
Forks
20
Bundled files
4
LicenseMIT
Links
  • 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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jwynia on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. 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.
2

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/jwynia/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/creative/fiction/core/story-sense .claude/skills/story-sense
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Story Sense 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 Story Sense 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 Story Sense 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.

Story Sense: Diagnostic Skill

Identify what state a story is in and what it needs to move forward. This is not a linear process but a diagnostic model: Assess → Diagnose → Intervene → Reassess.

When to Use This Skill

Use this skill when:

  • Writer is stuck and doesn't know why
  • Story feels broken but root cause unclear
  • Need to evaluate story problems systematically
  • Someone asks "what's wrong with my story?"

Do NOT use this skill when:

  • Writer wants you to write the story (use story-collaborator)
  • Writer wants coaching questions only (use story-coach)
  • Publishing/marketing questions (use book-marketing)

Core Principle

Story Sense is the ability to know what any story needs, regardless of its current state or intended medium.

There's no such thing as "stuck." There's only:

  • Not yet having diagnosed the problem
  • Not yet applying the right intervention

The Story States

State 0: No Story (Blank Page)

Symptoms: Nothing exists yet Interventions: story-idea-generator, elemental genres

State 1: Concept Without Foundation

Symptoms: Have idea but world/characters/plot feel thin Interventions: cliche-transcendence, systemic-worldbuilding, key-moments

State 2: World Without Life

Symptoms: Setting exists but feels like backdrop Interventions: worldbuilding skill suite (belief-systems, economic-systems, governance-systems)

State 3: Flat Non-Humans

Symptoms: Aliens/fantasy species feel like humans in costume Interventions: conlang, species development frameworks

State 4: Characters Without Dimension

Symptoms: Characters serve plot rather than driving it Interventions: character-arc, underdog-unit, positional-revelation

State 4.5: Plot Without Pacing

Symptoms: Scenes work individually but don't accumulate Interventions: scene-sequencing

State 5: Plot Without Purpose

Symptoms: Events happen but don't accumulate meaning Interventions: moral-parallax, key-moments

State 5.5: Dialogue Feels Flat

Symptoms: Characters sound alike, conversations lifeless Interventions: dialogue

State 5.75: Ending Doesn't Land

Symptoms: Story builds well but resolution disappoints Interventions: endings

State 5.85: Draft Not Progressing

Symptoms: Planning done but draft isn't happening Interventions: drafting

State 5.9: Prose Feels Flat

Symptoms: Story works but sentences are functional not memorable Interventions: prose-style

State 6: Draft Complete, Needs Revision

Symptoms: Draft exists but revision feels overwhelming Interventions: revision

State 7: Ready for Evaluation

Symptoms: Story exists but quality uncertain Interventions: sensitivity-check, story-analysis

Decision Tree

Is there anything on the page?
├── NO → story-idea-generator
└── YES → What's the problem?
    ├── Feels generic → cliche-transcendence
    ├── World feels thin → worldbuilding
    ├── Non-humans feel fake → conlang
    ├── Characters flat → character-arc
    ├── Pacing off → scene-sequencing
    ├── Dialogue wooden → dialogue
    ├── Ending weak → endings
    ├── Meaning unclear → moral-parallax
    ├── Draft not progressing → drafting
    ├── Prose flat → prose-style
    └── Draft needs revision → revision

Diagnostic Process

  1. Listen for symptoms - What are they describing as the problem?
  2. Ask clarifying questions - Get specific about where they're stuck
  3. Identify the state - Match symptoms to state list
  4. Name the diagnosis - Explain what you're seeing
  5. Recommend intervention - Point to specific skill
  6. Offer next steps - What should they try first?

Available Scripts

entropy.ts

Injects creative randomness from curated lists.

bash
deno run --allow-read scripts/entropy.ts lies
deno run --allow-read scripts/entropy.ts disasters --count 3
deno run --allow-read scripts/entropy.ts --combo

Lists: lies, ghosts, disasters, dilemmas, professions, locations, collisions, openings

functions.ts

Generates characters from abstract story functions.

bash
deno run --allow-read scripts/functions.ts
deno run --allow-read scripts/functions.ts --setting scifi
deno run --allow-read scripts/functions.ts healer --setting fantasy

Functions: healer, enforcer, keeper_of_secrets, maker, trader, guide, entertainer, death_worker, transgressor

Anti-Patterns

Prescribing Instead of Diagnosing

Fix: Always ask clarifying questions before diagnosing.

Framework Overload

Fix: Recommend one intervention. Expand after reassessment.

Ignoring Writer's Energy

Fix: Balance diagnostic accuracy with what energizes the writer.

Treating Structure as Story

Fix: Keep asking "Does this feel right?" alongside structural diagnosis.

Related Skills

Routes to all fiction skills based on diagnosed state.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Story Sense AI skill do?

Diagnose what any story needs regardless of its current state. This skill should be used when a writer is stuck, evaluating story problems, when narrative feels broken, or when someone asks 'what's wrong with my story?'. Keywords: story, diagnosis, stuck, narrative, plot, character, worldbuilding, revision.

Why use Story Sense on TypingMind?

Because you install it once and use it with any model. Story Sense 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 Story Sense in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jwynia/agent-skills/tree/main/skills/creative/fiction/core/story-sense. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Story Sense?

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 Story Sense?

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

Is the Story Sense AI skill free?

Yes. It is published on GitHub by jwynia under the MIT 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇