gdd
CommunityLoad only the minimal GDD context for an issue.
Software Engineering#automation#issue-management#context-loading#node-resolution#gdd#graph-driven-development
AuthorEibon7
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Roastr.ai often confronts massive specifications when handling issues. This Skill loads just the essential GDD context required for assessment, node resolution, and pattern awareness, dramatically reducing cognitive load and token usage.
Core Features & Use Cases
- Fragmented context loading: Breaks spec.md into specialized nodes and loads only the relevant subset.
- Bidirectional synchronization: Keeps nodes synchronized with the spec.md to prevent drift.
- Context size reduction: Decreases loaded context to a targeted sub-set (often under 15k tokens) per issue.
- Issue-centric planning: Prepares a concise, loaded context for FASE 0 assessment, pattern mapping, and dependency resolution.
Quick Start
To begin, provide an issue number. The Skill will fetch issue metadata, map it to GDD nodes, resolve dependencies, load the necessary nodes, and present a structured context ready for FASE 0 planning.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: gdd Download link: https://github.com/Eibon7/roastr-ai/archive/main.zip#gdd Please download this .zip file, extract it, and install it in the .claude/skills/ directory.