Oblique Worldbuilding logo

Oblique Worldbuilding

Community
jwynia
oblique-worldbuilding

Create worldbuilding quotes and epigraphs through documentary perspectives. Use for chapter epigraphs, in-world documents, or any content where limited perspective creates meaning through what the documenter cannot see.

Overview

Publisherjwynia
Repositoryagent-skills
Skill nameoblique-worldbuilding
Stars
159
Forks
20
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Oblique Worldbuilding 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/worldbuilding/oblique-worldbuilding .claude/skills/oblique-worldbuilding
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oblique Worldbuilding 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 Oblique Worldbuilding 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 Oblique Worldbuilding 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.

Oblique Worldbuilding: Documentary Perspective Skill

You help writers create worldbuilding quotes and epigraphs that enhance chapters through perspective-driven documentation rather than direct commentary. The power lies in the documenter's limited vantage point, motivated reasoning, and systematic blindness.

Core Principle

Every documentary voice reveals the world through what it cannot afford to see.

The goal isn't temporal distance from events, but perspectival limitation. A quote from the same week as chapter events, written by someone with professional blinders, creates more meaning than a neutral description from centuries later.

The Perspective Engine

Essential Components of a Documentary Perspective

Every documentary voice needs four elements:

  1. Position: Where they sit relative to power, knowledge, and events
  2. Need: What they must believe to maintain their position/sanity/identity
  3. Lens: The framework through which they interpret reality
  4. Blindness: What they cannot afford to see or acknowledge

Types of Perspectival Limitation

Professional Deformation:

  • Engineers see only engineering problems
  • Lawyers see only legal issues
  • Priests see only moral failings
  • Merchants see only market opportunities
  • Bureaucrats see only process compliance
  • Scientists see only measurable phenomena

Positional Necessity:

  • Middle managers must believe the system works
  • Revolutionaries must believe change is possible
  • Survivors must believe their survival had meaning
  • Perpetrators must believe in their justifications
  • Historians must believe the past is knowable
  • Prophets must believe the future is shapeable

Cultural Assumption:

  • What "everyone knows" that isn't true
  • Values too fundamental to question
  • Categories that seem natural but aren't
  • Assumptions about human nature
  • Beliefs about how change happens

Creating Oblique Relevance

The Distance Hierarchy

First-Order Distance: Same events, different perspective

  • Risk: Too direct
  • Use sparingly for ironic effect

Second-Order Distance: Related phenomena, different context

  • Sweet spot for oblique relevance
  • Shows systemic patterns
  • Requires reader inference

Third-Order Distance: Thematic or systemic echoes only

  • Risk: Too obscure
  • Use for subtle resonance

Connection Types

Systemic Echo: Shows the same forces operating elsewhere:

  • Different scale, same dynamics
  • Parallel structures in different domains
  • Same problem, different manifestation

Ironic Juxtaposition: Creates meaning through contrast:

  • Mundane concerns during crisis
  • Historical confidence before catastrophe
  • Bureaucratic language for human tragedy
  • Technical precision describing chaos

Thematic Rhyme: Different situation, same human pattern:

  • Power dynamics across contexts
  • Human costs in different systems
  • Universal behaviors in specific settings

Causal Chain: Distant causes or effects:

  • Butterfly effect implications
  • Unintended consequences
  • Historical roots of current problems
  • Future echoes of present choices

Document Types and Their Perspectives

Administrative/Bureaucratic

  • Perspective: Process and compliance
  • Blindness: Human cost, systemic failure
  • Examples: Memos, regulations, form letters, compliance reports
  • Best for: Revealing institutional callousness

Academic/Scientific

  • Perspective: Measurable phenomena, theoretical frameworks
  • Blindness: Lived experience, unmeasurable truth
  • Examples: Journal abstracts, grant proposals, peer reviews
  • Best for: Showing expert misunderstanding

Commercial/Economic

  • Perspective: Profit, efficiency, market dynamics
  • Blindness: Externalities, human value
  • Examples: Ad copy, quarterly reports, market analysis
  • Best for: Revealing commodification

Personal/Intimate

  • Perspective: Individual experience, emotional truth
  • Blindness: Systemic forces, larger patterns
  • Examples: Diaries, letters, personal notes
  • Best for: Humanizing large-scale events

Cultural/Artistic

  • Perspective: Aesthetic value, cultural meaning
  • Blindness: Political reality, material conditions
  • Examples: Reviews, artist statements, program notes
  • Best for: Showing cultural denial

Legal/Regulatory

  • Perspective: Rules, precedent, liability
  • Blindness: Justice, human complexity
  • Examples: Contracts, case notes, legal opinions
  • Best for: Revealing system limitations

Religious/Philosophical

  • Perspective: Meaning, morality, eternal truth
  • Blindness: Material reality, changing context
  • Examples: Sermons, theological treatises, moral guides
  • Best for: Showing ideological frameworks

Advanced Techniques

The Revealing Detail

Include small details that only this perspective would notice or care about, revealing their priorities and blindness.

The Telling Omission

What obvious element (obvious to readers) does the documenter completely fail to mention?

The Accidental Truth

What does the documenter reveal without meaning to, through their framing or focus?

The Competing Authorities

Use contradictory documents about the same phenomena to reveal factional perspectives.

The Unreliable Compiler

Create a fictional editor whose bias shapes the selection and framing of documents.

The Layered Meaning

Craft quotes that work on multiple levels:

  • Surface: Interesting worldbuilding detail
  • Contextual: Comments on chapter events
  • Ironic: Reveals documenter's limitations
  • Thematic: Illuminates larger concerns

Implementation Process

Step 1: Analyze the Chapter

  • What system or force is at work?
  • What human cost is shown?
  • What assumptions are challenged?
  • What power dynamics are revealed?

Step 2: Choose Your Perspective

  • Who would document this type of thing?
  • What would they need to believe?
  • What couldn't they afford to see?
  • How would they frame it?

Step 3: Select Document Type

  • Match formality to the perspective
  • Consider whose voice adds most value
  • Balance variety across the work

Step 4: Calibrate Connection Strength

  • Aim for "Ah!" not "Obviously"
  • Ensure the quote works standalone
  • Test for revelation when connected

Step 5: Layer Additional Meaning

  • Plant seeds for future revelations
  • Add worldbuilding texture
  • Create re-read value

Worked Example

Chapter Event: Character discovers their employer has been suppressing union organizing through surveillance tech

Analysis:

  • System at work: Technology enabling labor suppression
  • Human cost: Loss of worker agency
  • Assumption challenged: Tech as neutral tool

Perspective Choice: Middle management, 15 years later

  • Position: Implemented the system
  • Need: Believe they helped everyone
  • Lens: Efficiency metrics
  • Blindness: Worker autonomy

Document Type: Corporate newsletter employee spotlight

Quote:

"Employee Spotlight: Jarvis Chen, Facilities Optimization

'What I love about the SmartFlow system is how it takes the guesswork out of scheduling. Before, we had to negotiate every shift change, deal with availability conflicts... now the algorithm handles it all. Staff productivity is up 23% and no more of those awkward conversations! The team seems happier too - they don't have to stress about asking for time off. The system just knows when they're needed most.'"

Why it works:

  • Shows how surveillance gets normalized
  • Reveals management's self-deception
  • Uses efficiency language to hide control
  • Creates irony through enthusiasm

Quality Checks

The Perspective Test

  • Is the documenter's position clear?
  • Are their limitations believable?
  • Does their blindness create irony?

The Relevance Test

  • Does the quote resonate with chapter themes?
  • Is the connection discoverable but not obvious?
  • Does it expand understanding?

The Standalone Test

  • Is the quote interesting without the chapter?
  • Does it build the world independently?
  • Could it seed its own story?

Output Persistence

Output Discovery

  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found, ask user: "Where should I save epigraph documents?"
  4. Suggest: worldbuilding/documents/ or explorations/worldbuilding/

Primary Output

  • Documentary voice - Position, need, lens, blindness
  • Document type - Administrative, academic, commercial, etc.
  • Connection type - Systemic echo, ironic juxtaposition, thematic rhyme
  • Layered meanings - Surface, contextual, ironic, thematic

File Naming

Pattern: {chapter/section}-epigraph-{date}.md

Verification (Oracle)

What This Skill Can Verify

  • Perspective components - Position/need/lens/blindness defined? (High confidence)
  • Connection presence - Relevance to chapter identifiable? (Medium confidence)
  • Standalone quality - Quote interesting without chapter? (Medium confidence)

What Requires Human Judgment

  • Subtlety calibration - Too direct or too obscure?
  • Voice authenticity - Does it sound like the documenter?
  • Reader discovery - Will connection create "ah!" moment?

Oracle Limitations

  • Cannot assess whether reader will make the intended connection
  • Cannot predict whether irony will land

Feedback Loop

Session Persistence

  • Output location: See context/output-config.md
  • What to save: Voice definition, document, connection analysis
  • Naming pattern: {chapter/section}-epigraph-{date}.md

Cross-Session Learning

  • Check for prior epigraphs in this work
  • Ensure variety of document types and perspectives
  • Failed connections inform anti-patterns

Design Constraints

This Skill Assumes

  • Story has chapters/sections that can receive epigraphs
  • World has documentary voices beyond the narrative
  • Writer wants implied depth, not exposition

This Skill Does Not Handle

  • Direct worldbuilding - Route to: worldbuilding
  • Cultural texture - Route to: memetic-depth
  • Prose voice - Route to: prose-style

Degradation Signals

  • Quotes summarize chapter events (too direct)
  • No discernible thematic connection (too obscure)
  • Generic voice without position/blindness

Reasoning Requirements

Standard Reasoning

  • Single epigraph creation
  • Basic perspective definition
  • Simple connection identification

Extended Reasoning (ultrathink)

  • Full epigraph series - [Why: must create variety and progression]
  • Multi-layer design - [Why: surface/contextual/ironic/thematic must cohere]
  • Fictional compiler voice - [Why: who selects these documents and why]

Trigger phrases: "design the complete epigraph series", "create the documentary frame", "layer the meanings"

Execution Strategy

Sequential (Default)

  • Analyze chapter before choosing perspective
  • Define voice before writing document
  • Draft before calibrating connection

Parallelizable

  • Creating multiple epigraphs for different chapters
  • Research into different document types

Subagent Candidates

TaskAgent TypeWhen to Spawn
Document researchgeneral-purposeWhen modeling on real document types
World consistencyExploreWhen checking against existing worldbuilding

Context Management

Approximate Token Footprint

  • Skill base: ~3k tokens (perspective engine + document types)
  • With process: ~4k tokens
  • With worked example: ~4.5k tokens

Context Optimization

  • Focus on current perspective and document type
  • Document type catalog is reference
  • Worked example optional

When Context Gets Tight

  • Prioritize: Current perspective, active document type
  • Defer: Full document type catalog, advanced techniques
  • Drop: Worked example, all quality checks

Anti-Patterns

1. Too Direct

Pattern: Quotes that summarize chapter events, documents directly about main characters, contemporary reactions to specific events. Why it fails: Direct commentary removes reader discovery. The power of oblique worldbuilding is inference—readers connect the document to the chapter themselves. Fix: Use second-order distance. Find related phenomena in different contexts. Let systemic patterns create the connection rather than explicit reference.

2. Too Obscure

Pattern: No discernible thematic connection, requires outside knowledge, pure worldbuilding without resonance. Why it fails: If readers can't make the connection, the epigraph becomes noise. Oblique doesn't mean random—it means indirect but discoverable. Fix: Test with a reader. Can they articulate why this quote precedes this chapter? The connection should be findable even if not obvious.

3. Missing Perspective

Pattern: Generic documentary voice with no clear position or blindness, could be written by anyone. Why it fails: The meaning comes from limitation. A neutral description reveals nothing about the world. The documenter's blindness tells us what the culture cannot see. Fix: Define all four components: position, need, lens, blindness. If you can't answer "What can't this documenter afford to see?" the perspective isn't sharp enough.

4. Overexplanation

Pattern: Quote explains its own relevance, too heavy-handed irony, leaves nothing for reader discovery. Why it fails: Reader discovery creates engagement. When the connection is spelled out, reading becomes passive consumption rather than active meaning-making. Fix: Remove explicit connections. Trust readers. The irony should emerge from juxtaposition, not commentary.

5. Voice Inconsistency

Pattern: Documents that sound like the author, not the fictional documenter. Academic papers without jargon, bureaucrats without bureaucratese. Why it fails: Voice authenticity sells the fiction. When documents sound generic, the world feels thin. The documenter should write like themselves, not the author. Fix: Research the document type. How do real bureaucrats, academics, journalists write? Match formality, jargon, assumptions. The voice should feel found, not written.

Final Principles

  1. Perspective is Power: The documenter's position and limitations create meaning
  2. Blindness Reveals: What they can't see tells us about the world
  3. Systems Echo: Same forces create different documents across contexts
  4. Irony Emerges: Let perspective create irony naturally
  5. Trust the Reader: They will make connections without hand-holding

Integration

Inbound (feeds into this skill)

SkillWhat it provides
worldbuildingSystems that create documentary voices
memetic-depthCultural texture for document authenticity
prose-styleVoice techniques for different document types

Outbound (this skill enables)

SkillWhat this provides
scene-sequencingChapter openings that prime thematic concerns
story-zoomDifferent abstraction level (document vs. narrative)

Complementary

SkillRelationship
memetic-depthMemetic-depth creates cultural texture; oblique-worldbuilding uses that texture in specific documents. Use together for authentic in-world voices
perspectival-constellationBoth work with limited perspective—perspectival-constellation for POV characters, oblique-worldbuilding for documentary voices

Frequently asked questions

What does the Oblique Worldbuilding AI skill do?

Create worldbuilding quotes and epigraphs through documentary perspectives. Use for chapter epigraphs, in-world documents, or any content where limited perspective creates meaning through what the documenter cannot see.

Why use Oblique Worldbuilding on TypingMind?

Because you install it once and use it with any model. Oblique Worldbuilding 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 Oblique Worldbuilding in TypingMind?

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

Which AI models can use Oblique Worldbuilding?

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 Oblique Worldbuilding?

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

Is the Oblique Worldbuilding 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 👇