shamt-validation-loop
CommunityOrchestrate end-to-end artifact validation.
Software Engineering#automation#testing#quality-assurance#artifact#haiku#validation-loop#adversarial-check
AuthorMizunoPK
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Runs the Shamt validation loop protocol on any artifact (spec, plan, guide, design doc, code). Tracks consecutive_clean, enforces the clean-round definition, runs adversarial self-check every round, and exits only after a primary clean round followed by 2 independent Haiku sub-agent confirmations.
Core Features & Use Cases
- Enforces consecutive_clean tracking and clean-round validation across artifacts.
- Performs adversarial self-check and requires two independent Haiku sub-agent confirmations.
- Applies to specs, implementation plans, guides, design docs, and code within Shamt projects.
- Integrates with governance guides like validation_loop_master_protocol.md and severity_classification_universal.md for consistent decisions.
Quick Start
Use the shamt-validation-loop skill to start validating a target artifact.
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: shamt-validation-loop Download link: https://github.com/MizunoPK/shamt-ai-dev/archive/main.zip#shamt-validation-loop 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.