Skip to main content Accueil Créateurs rdmptv adbautoplayer moai-foundation-core
moai-foundation-core MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
Aller à l'installation Skills Marketplace Découvrez et explorez les compétences IA créées par la communauté.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Afficher les détails du prompt Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
npx skills add https://github.com/rdmptv/AdbAutoPlayer --skill moai-foundation-coreLa commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.
Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.
Télécharger Zip Téléchargement... Métiers associés SOC
Basé sur la classification professionnelle SOC
Explorateur de fichiers
24 fichiers DEPLOYMENT-SUMMARY.md 8.7 KB MIGRATION_GUIDE.md 12.0 KB PHASE-2-1-COMPLETION-REPORT.md 8.3 KB PHASE-2-2-COMPLETION-REPORT.md 11.4 KB PHASE-4-DELIVERABLES.md 11.7 KB PHASE-4-DEPLOYMENT-REPORT.md 12.5 KB name moai-foundation-core description MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows version 2.2.0 modularized true allowed-tools Read, Grep, Glob last_updated "2025-11-30T00:00:00.000Z" compliance_score 75 auto_trigger_keywords ["authentication","core","foundation"] color red
MoAI Foundation Core
Foundational principles and architectural patterns that power MoAI-ADK's AI-driven development workflow.
Core Philosophy : Quality-first, test-driven, modular, and efficient AI development through proven patterns and automated workflows.
Quick Reference (30 seconds)
What is MoAI Foundation Core?
Six essential principles that ensure quality, efficiency, and scalability in AI-powered development:
TRUST 5 Framework - Quality gate system (Test-first, Readable, Unified, Secured, Trackable)SPEC-First TDD - Specification-driven test-driven development workflowDelegation Patterns - Task orchestration via specialized agents (never direct execution)Token Optimization - 200K budget management and context efficiencyProgressive Disclosure - Three-tier knowledge delivery (Quick → Implementation → Advanced)Modular System - File splitting and reference architecture for scalability
Quick Access :
Use Cases :
✅ New agent creation with quality standards
✅ New skill development with structural guidelines
✅ Complex workflow orchestration
✅ Token budget planning and optimization
✅ Documentation architecture design
✅ Quality gate configuration
Implementation Guide (5 minutes)
1. TRUST 5 Framework - Quality Assurance System
Purpose : Automated quality gates ensuring code quality, security, and maintainability.
Pillar Requirement Validation Failure Action Test-first ≥85% coverage pytest --cov Block merge, generate tests Readable Clear naming ruff linter Warning, suggest refactor Unified Consistent patterns black, isort Auto-format or warn Secured OWASP compliance security-expert Block merge, review Trackable Clear commits Git regex Suggest format
Pre-commit hooks → Automated validation
CI/CD pipelines → Quality gate enforcement
Agent workflows → core-quality validation
Documentation → Quality metrics
2. SPEC-First TDD - Development Workflow Purpose : Specification-driven development ensuring clear requirements before implementation.
Phase 1: SPEC (/moai:1-plan)
├─ workflow-spec → EARS format
├─ Output: .moai/specs/SPEC-XXX/spec.md
└─ Execute /clear (saves 45-50K tokens)
Phase 2: TDD (/moai:2-run)
├─ RED: Failing tests
├─ GREEN: Passing code
├─ REFACTOR: Optimize
└─ Validate: ≥85% coverage
Phase 3: Docs (/moai:3-sync)
├─ API documentation
├─ Architecture diagrams
└─ Project reports
Ubiquitous : System-wide (always active)Event-driven : Trigger-based (when X, do Y)State-driven : Conditional (while X, do Y)Unwanted : Prohibited (shall not do X)Optional : Nice-to-have (where possible, do X) Token Budget : SPEC 30K | TDD 180K | Docs 40K | Total 250K
Key Practice : Execute /clear after Phase 1 to initialize context.
3. Delegation Patterns - Agent Orchestration Purpose : Task delegation to specialized agents, avoiding direct execution.
Core Principle : Alfred NEVER executes directly. All work via Task().
result = await Task(
subagent_type="specialized_agent" ,
prompt="Clear, specific task" ,
context={"relevant" : "data" }
)
Sequential (dependencies):
design = Task(subagent_type="api-designer" , prompt="Design API" )
code = Task(subagent_type="backend-expert" , prompt="Implement" , context={"design" : design})
results = await Promise.all ([
Task(subagent_type="backend-expert" , prompt="Backend" ),
Task(subagent_type="frontend-expert" , prompt="Frontend" )
])
Conditional (analysis-based):
analysis = Task(subagent_type="debug-helper" , prompt="Analyze" )
if analysis.type == "security" :
Task(subagent_type="security-expert" , prompt="Fix" )
Simple (1 file): 1-2 agents sequential
Medium (3-5 files): 2-3 agents sequential
Complex (10+ files): 5+ agents mixed
4. Token Optimization - Budget Management Purpose : Efficient 200K token budget through strategic context management.
Phase Budget Strategy SPEC 30K Load requirements only, /clear after TDD 180K Selective file loading Docs 40K Result caching, templates Total 250K Phase separation
Phase Separation : /clear between phases
After /moai:1-plan (saves 45-50K)
When context > 150K
After 50+ messages
Selective Loading : Load only necessary files
Context Optimization : 20-30K tokens target
Model Selection : Sonnet (quality) | Haiku (speed/cost)
Monitoring : /context command, track budget, suggest /clear
Cost Savings : Haiku 70% cheaper → 60-70% total savings
5. Progressive Disclosure - Content Architecture Purpose : Three-tier knowledge delivery balancing value with depth.
Level Time Content Tokens Quick Reference 30s Core principles 1,000 Implementation 5min Workflows, examples 3,000 Advanced 10+min Deep dives, edge cases 5,000
SKILL.md Structure (≤500 lines):
## Quick Reference (30s)
## Implementation Guide (5min)
## Advanced Patterns (10+min)
## Works Well With
SKILL.md : Entry point, cross-referencesmodules/ : Deep dives, unlimitedexamples.md : Working samplesreference.md : External links File Splitting (when >500 lines):
SKILL.md (500 lines)
├─ Quick (80-120)
├─ Implementation (180-250)
├─ Advanced (80-140)
└─ References (10-20)
Overflow → modules/[topic].md
6. Modular System - File Organization Purpose : Scalable file structure enabling unlimited content.
.claude/skills/skill-name/
├── SKILL.md # Core (≤500 lines)
├── modules/ # Extended (unlimited)
│ └── patterns.md
├── examples.md # Working samples
├── reference.md # External links
├── scripts/ # Utilities (optional)
└── templates/ # Templates (optional)
SKILL.md : ≤500 lines, progressive disclosure, cross-referencesmodules/ : Topic-focused, no limits, self-containedexamples.md : Copy-paste ready, commentedreference.md : API docs, resources Details: [Module ](modules/patterns.md )
Examples: [Examples ](examples.md#auth )
External: [Reference ](reference.md#api )
Discovery Flow : SKILL.md → Topic → modules/[topic].md → Deep dive
Advanced Implementation (10+ minutes)
Cross-Module Integration TRUST 5 + SPEC-First TDD :
spec = Task(subagent_type="workflow-spec" , prompt="SPEC with TRUST 5" )
impl = Task(subagent_type="workflow-tdd" , prompt="≥85% coverage" ,
context={"spec" : spec, "quality_gates" : ["TRUST5" ]})
validation = Task(subagent_type="core-quality" , prompt="Validate TRUST 5" ,
context={"implementation" : impl})
Token-Optimized Delegation :
spec = Task(subagent_type="workflow-spec" , prompt="Generate SPEC" )
execute_clear()
results = await Promise.all ([
Task(subagent_type="backend-expert" , prompt="Backend" , context={"spec_id" : spec.id }),
Task(subagent_type="frontend-expert" , prompt="Frontend" , context={"spec_id" : spec.id })
])
Task(subagent_type="workflow-docs" , prompt="Docs" , context={"results" : results})
Progressive Agent Workflows :
quick = Task(subagent_type="debug-helper" , prompt="Quick diagnosis" )
if quick.complexity == "high" :
detailed = Task(subagent_type="debug-helper" , prompt="Detailed analysis" )
if detailed.requires_expert:
expert = Task(subagent_type="security-expert" , prompt="Deep dive" )
Quality Validation def validate_execution_requirements (task, context ):
return all ([
validate_security_clearance(task),
validate_resource_availability(context),
validate_quality_standards(task),
validate_permission_compliance(task)
])
def validate_execution_results (result, task ):
validations = [
validate_output_quality(result),
validate_security_compliance(result),
validate_test_coverage(result),
validate_documentation_completeness(result)
]
if not all (validations):
raise QualityGateError("Quality gate failures" )
return True
Error Handling try :
result = Task(subagent_type="backend-expert" , prompt="Complex task" )
except AgentExecutionError as e:
analysis = Task(subagent_type="debug-helper" , prompt=f"Analyze: {e} " )
if analysis.issue == "complexity" :
results = await Promise.all ([
Task(subagent_type="backend-expert" , prompt="Subtask 1" ),
Task(subagent_type="backend-expert" , prompt="Subtask 2" )
])
if token_usage > 150_000 :
execute_clear()
context = {"spec_id" : current_spec.id , "phase_results" : summarize(previous_results)}
Task(subagent_type="next-agent" , prompt="Continue" , context=context)
Works Well With
agent-factory - Create agents with foundation principlesskill-factory - Generate skills with modular architecturecore-quality - Automated TRUST 5 validationworkflow-spec - EARS format specificationworkflow-tdd - RED-GREEN-REFACTOR executionworkflow-docs - Documentation with progressive disclosure
moai-cc-claude-md - CLAUDE.md with foundation patternsmoai-cc-configuration - Config with TRUST 5moai-cc-memory - Token optimizationmoai-core-ask-user-questions - User clarificationmoai-context7-integration - MCP integration
/moai:1-plan - SPEC-First Phase 1
/moai:2-run - TDD Phase 2
/moai:3-sync - Documentation Phase 3
/moai:9-feedback - Continuous improvement
/clear - Token management
Foundation Modules (Extended Documentation):
Quick Decision Matrix Scenario Primary Principle Supporting New agent TRUST 5 + Delegation Token, modular New skill Progressive + Modular TRUST 5, token Workflow Delegation SPEC-First, token Quality TRUST 5 SPEC-First Budget Token Optimization Progressive, modular Docs Progressive + Modular Token
Version : 1.0.0
Last Updated : 2025-11-25
Status : ✅ Active (496 lines, within 500-line limit)
