Menü
Guide AI model selection based on task complexity, cost constraints, and latency requirements
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | model-selection |
| version | 1.0.0 |
| category | ai |
| description | Guide AI model selection based on task complexity, cost constraints, and latency requirements |
| type | reference |
| capabilities | [] |
| requires | [] |
| see_also | [] |
| tags | [] |
| scripts_exempt | true |
Version: 1.0.0 Category: Optimization Triggers: Starting tasks, choosing Codex model, usage optimization
NEW TASK
│
├── WORK REPO + COMPLEX → OPUS
├── WORK REPO + STANDARD → SONNET
├── PERSONAL + SIMPLE → HAIKU
└── DEFAULT → SONNET
| Model | Target % | Use For |
|---|---|---|
| OPUS | 30% | Architecture, multi-file refactoring (>5 files), security review |
| SONNET | 40% | Standard implementations, code review, documentation |
| HAIKU | 30% | Quick queries, status checks, simple operations |
# Get model recommendation before each task
./scripts/monitoring/suggest_model.sh <repository> "<task description>"
# Examples:
./scripts/monitoring/suggest_model.sh digitalmodel "Design authentication architecture"
# → Recommends: OPUS (complexity score: 4)
./scripts/monitoring/suggest_model.sh digitalmodel "Implement user login"
# → Recommends: SONNET (complexity score: 1)
./scripts/monitoring/suggest_model.sh hobbies "Quick file check"
# → Recommends: HAIKU (complexity score: -3)
Algorithm evaluates:
Score Mapping:
Tier 1 (Production): 60% Opus, 30% Sonnet, 10% Haiku
Tier 2 (Active): 30% Opus, 50% Sonnet, 20% Haiku
Tier 3 (Maintenance): 10% Opus, 30% Sonnet, 60% Haiku
Active: 20% Opus, 40% Sonnet, 40% Haiku Experimental: 5% Opus, 25% Sonnet, 70% Haiku Archive: 0% Opus, 20% Sonnet, 80% Haiku
Check before starting work: https://Codex.ai/settings/usage
Alert Thresholds:
✅ Multi-file refactoring (>5 files) ✅ Architecture decisions ✅ Complex algorithm design ✅ Security-critical code review ✅ Cross-repository coordination ✅ Performance optimization strategies
✅ Standard feature implementation ✅ Code review (single PR) ✅ Documentation writing ✅ Test generation ✅ Bug fixing (standard complexity) ✅ Configuration updates
✅ File existence checks ✅ Simple grep/search operations ✅ Quick status updates ✅ Log analysis (pattern matching) ✅ Template generation ✅ Format validation
⛔ STOP using Sonnet immediately
✅ Switch to Opus for critical work
✅ Switch to Haiku for everything else
📅 Defer non-urgent work to Tuesday
⏸️ Pause AI tasks
⏰ Wait for session reset (~3-4 hours)
📦 Batch work for next session
See: @docs/AI_MODEL_SELECTION_AUTOMATION.md See: @docs/CLAUDE_MODEL_SELECTION_QUICK_REFERENCE.md
Use this when starting tasks, selecting models, or optimizing AI usage.
Class-level Gmail and email operations: multi-account setup, OAuth, triage, extraction, archiving, attachments, unsubscribe, and touchbase workflows.
Conventions for creating consistent Mermaid diagrams including decision node layout, edge ordering, and flowchart direction rules.
Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
Class-level Hermes local configuration and setup workflows, including config audit gotchas and Windows installation.
Sub-skill of modular-architecture-documentation: 1. Module Definition Framework (+9).
Sub-skill of modular-architecture-documentation: Overview (+6).