moai-workflow-gan-loop

Solid

Builder-Evaluator GAN loop workflow for iterative design quality improvement. Implements Sprint Contract negotiation, 4-dimension scoring (Design Quality, Originality, Completeness, Functionality), stagnation detection, and escalation protocol. Reads parameters from design.yaml.

AI & Automation 1,050 stars 192 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 99/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# moai-workflow-gan-loop Implements the Builder-Evaluator GAN loop for iterative design quality improvement. Absorbed from agency constitution Section 11 and Section 12. Integrates Sprint Contract Protocol, 4-dimension scoring, stagnation detection, and Evaluator Leniency Prevention. All loop parameters are read from `.moai/config/sections/design.yaml`. Do not hardcode thresholds. --- ## Quick Reference ### Loop Parameters (from design.yaml) ``` design.gan_loop: max_iterations: 5 # Maximum Builder-Evaluator cycles pass_threshold: 0.75 # Score >= this value to exit loop escalation_after: 3 # Escalate to user after N iterations without passing improvement_threshold: 0.05 # Minimum score delta per iteration strict_mode: false # If true, each dimension must pass individually sprint_contract: enabled: true required_harness_levels: [thorough] optional_harness_levels: [standard] artifact_dir: ".moai/sprints" max_negotiation_rounds: 2 ``` ### 4-Dimension Scoring Weights | Dimension | Weight | Description | | --- | --- | --- | | Design Quality | 30% | Visual consistency, brand token compliance, WCAG AA | | Originality | 25% | Not generic, not AI-slop, unique brand expression | | Completeness | 25% | All BRIEF sections present, copy matches contract | | Functionality | 20% | Responsive, accessible, all interactions work | Overall score = weighted average of all four dimensions. Pass condition: `overall_score >= pa...

Details

Author
modu-ai
Repository
modu-ai/moai-adk
Created
8 months ago
Last Updated
today
Language
Go
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

moai-workflow-ci-loop

Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see moai-workflow-loop).

1,050 Updated today
modu-ai
AI & Automation Listed

run-eval-loop

Scaffolds and maintains the workspace for a measurable strategy → execution → evaluation cycle — creates `.forsvn/loops/[slug]/` with program, context, a results ledger, and learnings. Use for an improvement loop, experiment ledger, or campaign/content iteration system tied to a metric. Routes surface scoring to the matching evaluate-* skill; not a universal evaluator. Not for one-shot planning (use discover or breakdown-tasks) or multi-perspective debate (use debate-agents).

10 Updated today
hungv47
AI & Automation Solid

moai-workflow-loop

Ralph Engine - Automated feedback loop with LSP diagnostics and AST-grep integration for continuous code quality improvement. Use when implementing error-driven development, automated fixing, or continuous quality validation workflows.

1,050 Updated today
modu-ai
AI & Automation Solid

moai-workflow-design

Unified design workflow skill — handles Path A (Claude Design handoff bundle import, via Figma extractor when needed) and design-brief context loading from .moai/design/ (research, system, spec). Validates DTCG tokens, enforces brand-context constitutional priority. Use for /moai design workflow — NOT for general design system documentation (see moai-design-system).

1,050 Updated today
modu-ai
AI & Automation Solid

moai-workflow-testing

Comprehensive testing and development workflow specialist combining DDD testing, characterization tests, performance profiling, and quality assurance. Use when writing tests or measuring coverage.

1,050 Updated today
modu-ai