narrative-game-prototype-planner
Skill1 starsChanged 53 days agoMITView on GitHub
Use when turning story-heavy game notes into playable prototypes before engine or Figma implementation, including letter or chat mechanics, keyword marking, response-card systems, scene function checklists, content tables, local HTML/SVG prototypes, or emotional design critique.
In this repository20 other files it gives its agents.
- llms.txtllms.txt
- agent-skill-migrationSkill
- agents-md-verification-mapSkill
- cocos-creator-mobile-gameSkill
- game-entity-movement-presentationSkill
- game-event-directorSkill
- game-ui-panelsSkill
- godot-narrative-workflowSkill
- obsidian-article-writebackSkill
- offline-ux-kitSkill
- product-image-prompt-iterationSkill
- product-teardownSkill
- reporting-disciplineSkill
- scene-anchor-systemSkill
- screen2layersSkill
- sol-luna-local-parallelSkill
- sprite-atlas-slicerSkill
- unfinished-work-auditSkill
- windows-ai-cli-recoverySkill
- xiaohongshu-copywriterSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read references/narrative-prototype-workflow.md when the task involves multi-night/episode content, keyword marking, response cards, …
- Distinctive: line 29
Keep implementation boundaries clear.
- Distinctive: line 30
Do not invent Cocos node bindings, Figma team permissions, or production art requirements.
- Distinctive: line 32
When sensitive themes appear, include safety/help affordances and avoid manipulative or clinical claims.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Narrative Game Prototype Planner
Overview
Use this skill for story-heavy games where the hard part is turning intent, tone, text, and interaction rules into something playable and implementable. Keep the scope at design and prototype packaging; hand off to Cocos, Figma, imagegen, or document skills only when the user asks for engine code, design-file writes, final art, or polished documents.
Read references/narrative-prototype-workflow.md when the task involves multi-night/episode content, keyword marking, response cards, letter/chat drafts, scene checklists, local HTML/SVG prototypes, or comparing a design doc against the intended player experience.
Workflow
- Establish the playable unit.
- Identify the episode/night/chapter, the player goal, the input text, available choices, resources, and ending condition.
- Separate theme and atmosphere from actual mechanics the player can use.
- Critique before expanding.
- Flag unclear player decisions, weak feedback loops, missing failure states, content safety gaps, and places where the theme is stated but not played.
- Preserve the user's premise unless they ask for a larger redesign.
- Convert design into testable artifacts.
- For text mechanics, create keyword tables, scoring rules, response-card pools, generated draft examples, and outcome states.
- For scenes, create function checklists with required elements, states, interactions, and feedback.
- For local prototypes, prefer simple SVG/HTML/PNG packages that can be inspected or manually imported elsewhere.
- Keep implementation boundaries clear.
- Do not invent Cocos node bindings, Figma team permissions, or production art requirements.
- Mark what is prototype-only versus what is ready for engine implementation.
- When sensitive themes appear, include safety/help affordances and avoid manipulative or clinical claims.
- End with verification.
- Provide a short playtest path: what the user should click/read/choose, what should change, and what would prove the prototype is coherent.
- List the exact files or tables created or updated.
Output Expectations
For a design critique, lead with the highest-impact risks and concrete fixes.
For playable text content, include:
- scene or episode goal
- source text the player reads
- markable keywords or signals
- response options or cards
- generated draft/output examples
- scoring or state changes
- success, partial success, and miss outcomes
For scene planning, include:
- function positioning
- required UI/visual elements
- states
- interactions
- feedback and accessibility/safety notes
For local prototype packages, include:
- file list
- which file is for preview
- which file is for import or handoff
- known limits of the prototype
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

