Game Design Ideal Outcome Backcasting

Start from the ideal player-facing result and work backward to the design steps, systems, and decisions required to reach it. Use when a team knows the kind...

Security Scan

This is an instruction-only game-design facilitation skill that requests no binaries, credentials, or installs and its instructions are consistent with its stated purpose.

Purpose & Capability

Name and description (backcasting an ideal player outcome) align with the actual requirements: no external services, no credentials, and only a short reference file. Nothing requested is disproportionate to a design-facilitation skill.

Instruction Scope

SKILL.md limits the agent to producing a structured design output and optionally reading the provided references/family-conventions.md. It does not instruct the agent to read unrelated files, environment variables, or to send data to external endpoints.

Install Mechanism

No install spec and no code files. As an instruction-only skill, it writes nothing to disk and does not pull external artifacts.

Credentials

No required environment variables, credentials, or config paths are declared or referenced. The skill does not request sensitive tokens or unrelated system access.

Persistence & Privilege

always is false and the skill is user-invocable. It does not request persistent presence or modify other skills or system-wide settings.

Assessment

This skill is instruction-only and appears safe: it only uses the included reference file and produces a design-backcasting output. Before installing, consider (1) the privacy of any project details you paste into prompts (the skill will use whatever you provide), (2) whether you want the agent to invoke skills autonomously (the default allows invocation but this skill requires user invocation to be useful), and (3) reviewing the reference file if you want to confirm conventions. No credentials, downloads, or extra permissions are required.

Start from the ideal future and work backward.

Use this skill when the end-state is easier to imagine than the path to reach it. Treat the ideal outcome as a design tool, not a fantasy wish list. The aim is to define the best believable player-facing result, then retrace the steps needed to make it real.

Read references/family-conventions.md when you need the shared conventions for this GROW-derived skill family.

What to produce

Generate:

1. Ideal outcome - the best believable player-facing result
2. Required conditions - what must be true for that result to exist
3. Backward path - the enabling steps, systems, and decisions
4. Near-term priorities - what must happen first

Process

1. Describe the ideal future

Clarify:

• what the player experience looks and feels like
• what success looks like in the feature or system
• what makes this version meaningfully better than the current one

2. Identify enabling conditions

Ask:

• what must exist for this outcome to work
• what systems, UX, content, or support layers are required
• what assumptions must hold true

3. Work backward

Retrace the path from the ideal state to the current state. List:

• key milestones
• prerequisite systems
• sequencing dependencies
• learnings or tests needed before commitment

4. Distill immediate priorities

Separate:

• what must happen now
• what can wait
• what should be prototyped or validated first

Response structure

Ideal Outcome

• ...

Required Conditions

• ...

Backward Path

1. ...
2. ...
3. ...

Immediate Priorities

• ...

Fast mode

• What does the best believable version look like?
• What would need to be true for that version to work?
• What are the first steps backward from that destination?

Working principle

A clearer destination makes the path easier to design.