Game Narrative And Interactive Story Design logo

Game Narrative And Interactive Story Design

Community
peterbamuhigire
game-narrative-and-interactive-story-design

Use when designing, reviewing, or implementing interactive game stories, narrative systems, quests, characters, dialogue, environmental storytelling, branching choices, story beats, setups/payoffs, or narrative validation; use level-world-and-content-production for level assembly and content integration.

Overview

Publisherpeterbamuhigire
Repositorychwezi-dev-engine
Skill namegame-narrative-and-interactive-story-design
Stars
29
Forks
6
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Game Narrative And Interactive Story Design 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.
    https://github.com/peterbamuhigire/chwezi-dev-engine/tree/main/skills/game-development/game-narrative-and-interactive-story-design
  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/peterbamuhigire/chwezi-dev-engine.git /tmp/chwezi-dev-engine
mkdir -p .claude/skills
cp -r /tmp/chwezi-dev-engine/skills/game-development/game-narrative-and-interactive-story-design .claude/skills/game-narrative-and-interactive-story-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Narrative And Interactive Story Design 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 Game Narrative And Interactive Story Design 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 Game Narrative And Interactive Story Design 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.

Game Narrative and Interactive Story Design

Convert theme, audience, player fantasy, and gameplay constraints into a causal, testable narrative system whose delivery survives player agency, interruption, and production limits.

Prerequisites

Load world-class-engineering, game-design-and-experience, level-world-and-content-production, accessibility/localisation guidance, and the project's cultural research, rights, safeguarding, and content constraints.

Use When

  • Defining premise, theme, characters, wants/needs, conflict, beats, quests, dialogue, choices, consequences, environmental narrative, or story-state logic.
  • Diagnosing a story that is incoherent, over-exposed, disconnected from play, culturally unsafe, or impossible to validate.
  • Creating narrative requirements, state models, content schemas, review gates, localisation notes, or comprehension playtests.

Do Not Use When

  • The task is level layout, encounter pacing, or content integration without a narrative-system decision; use level-world-and-content-production.
  • The task is prose-only fiction with no interactive delivery or runtime state.
  • Cultural fact claims lack evidence; return to research and cultural review before canonising them.

Required Inputs

InputRequiredMissing-input response
Audience, player fantasy, genre/tone, platform and session shapeyesMark the premise provisional and stop detailed scripting.
Approved cultural/source ledger and rights/sensitivity constraintsconditionalBlock historical or community-specific canon.
Gameplay loop, player verbs, level/content topology and save modelyesProduce only a narrative hypothesis, not runtime logic.
Content budget, localisation/VO plan, rating and accessibility constraintsyesFlag cost and delivery as unvalidated.

Workflow

  1. State the player-facing narrative promise, theme, audience need and non-negotiable cultural boundaries in plain language.
  2. Build a causal spine: setup, destabilising event, dramatic question, escalating obstacles and choices, climax, resolution, and changed state. Every beat must follow from an action or consequence.
  3. Define characters by observable want, deeper need, stakes, tactics, contradiction, relationships, agency and change—not biography volume.
  4. Map the spine to player verbs, spaces, encounters and session boundaries. Choose authored, branching, environmental, systemic/emergent or hybrid delivery deliberately.
  5. Model story states, prerequisites, mutually exclusive branches, convergence, failure/recovery, save/load, replay and late-join behaviour. Give each state stable identifiers.
  6. Specify each delivery unit with trigger, payload, player control, interruption policy, fallback, localisation fields, accessibility channel and acceptance oracle.
  7. Track setups, reminders and payoffs; separate essential comprehension from optional depth. Never place a critical fact in one fragile channel.
  8. Prototype with the cheapest faithful form, then test comprehension, motivation, pacing, choice legibility and cultural interpretation with named builds and audiences.
  9. Stop on broken causality, unreachable state, missing cultural approval, inaccessible critical information, uncontrolled scope, or an untestable emotional claim.
  10. Load references/narrative-playtest-loop.md for the cross-discipline contract. Retain failed-path, branch, audio-off, localisation-expansion, and accessibility evidence; standardise only a change that improves the player hypothesis without breaking gameplay, performance, rights, or safety constraints.

Outputs

ArtefactAcceptance condition
Narrative promise, causal spine and character contractsWants, stakes, actions, consequences and changed states are explicit.
Beat/quest/state mapIDs, prerequisites, branches, convergence, failure and persistence are deterministic.
Narrative delivery specificationTrigger, channel, interruption, fallback, localisation and accessibility are defined.
Setup/payoff and evidence registerEvery essential setup has a reachable payoff and test evidence.

Evidence Produced

CategoryArtifactFormatExample
CorrectnessReachability/state-transition tests and setup-payoff coverage.Test report and coverage matrixdocs/narrative/reachability-tests.md
UX qualityComprehension, motivation, pacing and choice-legibility playtest results.Playtest report with observations and findingsdocs/narrative/player-experience.md
UX qualityCultural safety reviewReview record: named reviewer, source/provenance link, decision and unresolved caveatdocs/narrative/cultural-safety-review.md
Release evidenceBuild/content revision, localisation completeness and known narrative defects.Release record with revision identity, localisation status and defect listdocs/narrative/release-evidence.md

Capability and Degraded Mode

Editing canon, dialogue, localisation source or runtime content requires task authority; community representation and public claims require accountable review. Without a playable build, return a desk-reviewed state model and test plan with runtime comprehension, pacing and interruption marked not assessed.

Decision Rules

ConditionAction
Plot beat does not alter player knowledge, goal, relationship, capability or world stateCut, combine or make its purpose explicit.
Critical information has one missable delivery channelAdd an accessible, diegetically appropriate recovery path.
Choice has no legible difference or consequenceReframe as flavour or add a measurable consequence; do not market false agency.
Branch cost exceeds budgetShare states/content intentionally and preserve consequence through variables, reactions or later payoffs.
Historical authenticity and fun appear to conflictEscalate to research/cultural owners; label dramatization and never invent certainty.

Quality Standards

  • Prefer causal verbs and observable player evidence over adjectives such as “immersive” or “meaningful”.
  • Interactive flow outranks screenplay shape: the player must understand what to do, why, and what changed.
  • Preserve player control or specify the exact, tested reason for taking it away.
  • Treat the supplied story text as a design source, not a substitute for cultural evidence or project canon.
  • Complete the mechanics-to-meaning matrix for consequential mechanics; agency, feedback, state transitions, and player interpretation must be evidenced rather than assumed.
  • Publish the initial product audit at min(raw_score, 65) before any improvement claim; the chosen change targets 95/100 and has a reversible test, guardrails, and re-audit evidence.

Anti-Patterns

  • Lore dump before player need. Fix: reveal information through action, consequence and optional depth.
  • Branching diagram without state ownership. Fix: assign stable IDs, predicates, persistence and recovery.
  • Emotional acceptance criterion (“player feels heroic”). Fix: define observable comprehension/choice/behaviour evidence.
  • One “representative” reviewer. Fix: identify role, community relationship, scope and unresolved disagreement.
  • Cutscene logic detached from gameplay. Fix: map every major beat to player verbs and state change.

Read Next

  • level-world-and-content-production for spatial and encounter integration.
  • gameplay-systems-engineering for runtime state implementation.
  • game-testing-polish for playtest and regression evidence.

References

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 Game Narrative And Interactive Story Design AI skill do?

Use when designing, reviewing, or implementing interactive game stories, narrative systems, quests, characters, dialogue, environmental storytelling, branching choices, story beats, setups/payoffs, or narrative validation; use level-world-and-content-production for level assembly and content integration.

Why use Game Narrative And Interactive Story Design on TypingMind?

Because you install it once and use it with any model. Game Narrative And Interactive Story Design 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 Game Narrative And Interactive Story Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/peterbamuhigire/chwezi-dev-engine/tree/main/skills/game-development/game-narrative-and-interactive-story-design. 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 Game Narrative And Interactive Story Design?

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 Game Narrative And Interactive Story Design?

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

Is the Game Narrative And Interactive Story Design AI skill free?

Yes. It is published on GitHub by peterbamuhigire 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 👇