rat-dse-policy
CommunityIterative DSE policy for RTL design
Software Engineering#architecture#policy#microarchitecture#rtl#self-critique#dse#design-space-exploration
Authorbabyworm
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Provides a formalized policy and procedural checklist to make Design Space Exploration (DSE) for RTL projects repeatable, auditable, and decision-driven, preventing ad-hoc design choices and lost rationale during Phase 1→3 exploration.
Core Features & Use Cases
- Gate definitions & quality criteria: Explicit Artifact + Quality Gate rules for Phase 1→2, Phase 2→3, and Phase 3 completion with PASS/FAIL semantics and retry limits.
- Algorithm & architecture comparison: Structured algorithm comparison matrices, multi-candidate architecture formats, and ADR recording for user decisions.
- Functional→Architectural C model transformation: Guidance to restructure C models into block-aligned, DPI-C compatible refc code with bitexact verification.
- Self-critique & trial comparison: Automated self-critique protocol and worktree-based trial comparison workflow to iterate and select the best trial.
- Use Case: When evaluating multiple encoder/decoder algorithms and architectures, use this policy to produce quantitative trade-offs, verified ref C transformations, and a defensible pre-implementation package for Phase 4 review.
Quick Start
Produce a DSE pre-implementation package from my project requirements and functional C model using the rat-dse-policy rules.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: rat-dse-policy Download link: https://github.com/babyworm/rtl-agent-team/archive/main.zip#rat-dse-policy Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.