gds-generate-project-context

Generates a project-context.md file documenting implementation rules for AI coding agents.

Updated Sep 3, 2026
One-click install
npx skills add https://github.com/watchthelight/shatterfish --skill gds-generate-project-context-watchthelight
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gds-generate-project-context
Source: https://github.com/watchthelight/shatterfish/tree/main/.claude/skills/gds-generate-project-context
Command: npx skills add https://github.com/watchthelight/shatterfish --skill gds-generate-project-context-watchthelight

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI coding agents working on a game project often miss unobvious conventions, engine-specific patterns, and critical rules, leading to inconsistent implementations. This Skill captures those rules in a single optimized project-context.md file that agents read before writing code. ## Core Features & Use Cases - Guided Discovery: Scans architecture documents, engine configs, and existing code to identify the technology stack, naming conventions, and coding patterns already in use. - Collaborative Rule Generation: Walks through engine-specific, performance, organization, testing, and platform rule categories with the user, supporting Unity, Unreal, and Godot projects. - LLM-Optimized Output: Produces a lean, scannable project-context.md with frontmatter tracking and usage guidelines for both agents and humans. - Use Case: A game studio onboarding multiple AI agents to a Unity project uses this Skill to document lifecycle rules, assembly definition constraints, and performance budgets so every agent implements code consistently. ## Quick Start Ask the AI to generate project context for this game project and follow the guided discovery and rule-generation steps.

Frequently Asked Questions about gds-generate-project-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a project context file for AI coding agents?

Run the generate project context workflow, which discovers your engine, dependencies, and code patterns, then collaboratively drafts rules per category. The result is saved as project-context.md in your configured output folder.

What should a project context file for game development include?

It should include exact technology versions, engine-specific lifecycle rules, performance budgets, code organization and naming conventions, testing requirements, platform constraints, and anti-patterns agents must avoid.

Does this workflow support Unity, Unreal, and Godot projects?

Yes. The discovery step checks for engine-specific files like ProjectSettings, .uproject files, and project.godot, and the generation step includes tailored rule categories for each engine's lifecycle, serialization, and scene patterns.

Can I update an existing project-context.md instead of creating a new one?

Yes. The discovery step first checks for an existing project-context.md in the output folder, reports how many sections it contains, and asks whether you want to update it or create a new one.

How do AI agents use the generated project context file?

Production workflows such as create-story, dev-story, and code-review read the file automatically when implementing. Conversational agents can opt in by adding the file path to their persistent_facts configuration.