adr-consultation
CommunityDecide architecture with evidence-backed consensus.
Software Engineering#adr#multi-agent review#gating#architecture decision#verdict synthesis#concern severity#parallel consultation
Authornotque
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill prevents architecture decisions from moving forward without challenging assumptions, assessing user impact, and checking system-level risks before implementation.
Core Features & Use Cases
- Multi-agent ADR consultation: Dispatches three specialized reviewers (contrarian, user-advocate, and meta-process) to evaluate an ADR and produce lens-specific verdicts.
- File-based, reproducible synthesis: Writes each reviewer’s output to disk and then synthesizes a unified PROCEED or BLOCKED verdict from the persisted artifacts.
- Hard gate on blocking concerns: Enforces that any
severity: blockingissue results in a BLOCKED verdict, preventing rationalization-driven “skip” behavior. - Use Case: Before implementing a Medium+ architecture change (e.g., new subsystem or major decision), consult on the ADR to reduce costly post-implementation rework.
Quick Start
Run the adr-consultation Skill with your intent like “consult on ADR <name or path> before implementing this architecture change.”
Dependency Matrix
Required Modules
None requiredComponents
references
💻 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: adr-consultation Download link: https://github.com/notque/vexjoy-agent/archive/main.zip#adr-consultation 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.