# Ml > Ml - Skill: `dnyoussef/ml` (Agent Skill, multi-file: 17 files) - Install (CLI): `npx skillmds@latest add dnyoussef/ml` - Raw SKILL.md: https://api.skillmd.com/api/skills/dnyoussef/ml/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: DNYoussef (https://skillmd.com/u/dnyoussef) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/dnyoussef/ml --- /*============================================================================*/ /* ML SKILL :: VERILINGUA x VERIX EDITION */ /*============================================================================*/ --- name: ml version: 2.0.0 description: | [assert|neutral] Machine Learning development workflow with experiment tracking, hyperparameter optimization, and MLOps integration [ground:given] [conf:0.95] [state:confirmed] category: specialized-development tags: - machine-learning - mlops - experiment-tracking - hyperparameter-tuning - model-registry author: ruv cognitive_frame: primary: aspectual goal_analysis: first_order: "Execute ml workflow" second_order: "Ensure quality and consistency" third_order: "Enable systematic specialized-development processes" --- /*----------------------------------------------------------------------------*/ /* S0 META-IDENTITY */ /*----------------------------------------------------------------------------*/ [define|neutral] SKILL := { name: "ml", category: "specialized-development", version: "2.0.0", layer: L1 } [ground:given] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S1 COGNITIVE FRAME */ /*----------------------------------------------------------------------------*/ [define|neutral] COGNITIVE_FRAME := { frame: "Aspectual", source: "Russian", force: "Complete or ongoing?" } [ground:cognitive-science] [conf:0.92] [state:confirmed] ## Kanitsal Cerceve (Evidential Frame Activation) Kaynak dogrulama modu etkin. /*----------------------------------------------------------------------------*/ /* S2 TRIGGER CONDITIONS */ /*----------------------------------------------------------------------------*/ [define|neutral] TRIGGER_POSITIVE := { keywords: ["ml", "specialized-development", "workflow"], context: "user needs ml capability" } [ground:given] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S3 CORE CONTENT */ /*----------------------------------------------------------------------------*/ # ML Development Skill ## Kanitsal Cerceve (Evidential Frame Activation) Kaynak dogrulama modu etkin. ## When to Use This Skill - **Model Training**: Training neural networks or ML models - **Hyperparameter Tuning**: Optimizing model performance - **Model Debugging**: Diagnosing training issues (overfitting, vanishing gradients) - **Data Pipeline**: Building training/validation data pipelines - **Experiment Tracking**: Managing ML experiments and metrics - **Model Deployment**: Serving models in production ## When NOT to Use This Skill - **Data Analysis**: Exploratory data analysis or statistics (use data scientist) - **Data Engineering**: Large-scale ETL or data warehouse (use data engineer) - **Research**: Novel algorithm development (use research specialist) - **Simple Rules**: Heuristic-based logic without ML ## Success Criteria - [ ] Model achieves target accuracy/F1/RMSE on validation set - [ ] Training/validation curves show healthy convergence - [ ] No overfitting (train/val gap <5%) - [ ] Inference latency meets production requirements - [ ] Model size within deployment constraints - [ ] Experiment tracked with metrics and artifacts (MLflow, Weights & Biases) - [ ] Reproducible results (fixed random seeds, versioned data) ## Edge Cases to Handle - **Class Imbalance**: Unequal class distribution requiring resampling - **Data Leakage**: Information from validation/test leaking into training - **Catastrophic Forgetting**: Model forgetting old tasks when learning new ones - **Adversarial Examples**: Model vulnerable to adversarial attacks - **Distribution Shift**: Training data differs from production data - **Hardware Constraints**: GPU memory limitations or mixed precision training ## Guardrails - **NEVER** evaluate on training data - **ALWAYS** use separate train/validation/test splits - **NEVER** touch test set until final evaluation - **ALWAYS** version datasets and models - **NEVER** deploy without monitoring for data drift - **ALWAYS** document model assumptions and limitations - **NEVER** train on biased or unrepresentative data ## Evidence-Based Validation - [ ] Confusion matrix reviewed for class-wise performance - [ ] Learning curves plotted (loss vs epochs) - [ ] Validation metrics tracked across experiments - [ ] Model profiled for inference time (TensorBoard, PyTorch Profiler) - [ ] Ablation studies conducted for architecture choices - [ ] Cross-validation performed for robust evaluation - [ ] Statistical significance tested (t-test, bootstrap) Comprehensive machine learning development workflow with enterprise-grade experiment tracking, automated hyperparameter optimization, model registry management, and production MLOps pipelines. ## Overview This Gold-tier skill provides a complete ML development lifecycle with: - **Experiment Tracking**: MLflow/W&B integration for reproducible experiments - **Hyperparameter Optimization**: Optuna/Ray Tune for automated tuning - **Model Registry**: Centralized model versioning and deployment - **MLOps Pipeline**: Production-ready model serving and monitoring ## Quick Start ```bash # Initialize ML project npx claude-flow sparc run ml "Create ML project for image classification" # Track experiment python resources/scripts/experiment-tracker.py --config experiment-config.yaml # Optimize hyperparameters node resources/scripts/hyperparameter-tuner.js --space hyperparameter-space.json # Deploy model bash resources/scripts/model-registry.sh deploy production latest ``` ## Workflow Phases ### 1. Experiment Design - Define hypothesis and metrics - Configure experiment tracking - Set up data pipelines - Validate data quality ### 2. Model Development - Implement model architecture - Configure training pipeline - Set up validation strategy - Enable experiment logging ### 3. Hyperparameter Optimization - Define search space - Select optimization algorithm - Run distributed trials - Analyze results ### 4. Model Evaluation - Comprehensive metrics analysis - /*----------------------------------------------------------------------------*/ /* S4 SUCCESS CRITERIA */ /*----------------------------------------------------------------------------*/ [define|neutral] SUCCESS_CRITERIA := { primary: "Skill execution completes successfully", quality: "Output meets quality thresholds", verification: "Results validated against requirements" } [ground:given] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S5 MCP INTEGRATION */ /*----------------------------------------------------------------------------*/ [define|neutral] MCP_INTEGRATION := { memory_mcp: "Store execution results and patterns", tools: ["mcp__memory-mcp__memory_store", "mcp__memory-mcp__vector_search"] } [ground:witnessed:mcp-config] [conf:0.95] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S6 MEMORY NAMESPACE */ /*----------------------------------------------------------------------------*/ [define|neutral] MEMORY_NAMESPACE := { pattern: "skills/specialized-development/ml/{project}/{timestamp}", store: ["executions", "decisions", "patterns"], retrieve: ["similar_tasks", "proven_patterns"] } [ground:system-policy] [conf:1.0] [state:confirmed] [define|neutral] MEMORY_TAGGING := { WHO: "ml-{session_id}", WHEN: "ISO8601_timestamp", PROJECT: "{project_name}", WHY: "skill-execution" } [ground:system-policy] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S7 SKILL COMPLETION VERIFICATION */ /*----------------------------------------------------------------------------*/ [direct|emphatic] COMPLETION_CHECKLIST := { agent_spawning: "Spawn agents via Task()", registry_validation: "Use registry agents only", todowrite_called: "Track progress with TodoWrite", work_delegation: "Delegate to specialized agents" } [ground:system-policy] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* S8 ABSOLUTE RULES */ /*----------------------------------------------------------------------------*/ [direct|emphatic] RULE_NO_UNICODE := forall(output): NOT(unicode_outside_ascii) [ground:windows-compatibility] [conf:1.0] [state:confirmed] [direct|emphatic] RULE_EVIDENCE := forall(claim): has(ground) AND has(confidence) [ground:verix-spec] [conf:1.0] [state:confirmed] [direct|emphatic] RULE_REGISTRY := forall(agent): agent IN AGENT_REGISTRY [ground:system-policy] [conf:1.0] [state:confirmed] /*----------------------------------------------------------------------------*/ /* PROMISE */ /*----------------------------------------------------------------------------*/ [commit|confident] ML_VERILINGUA_VERIX_COMPLIANT [ground:self-validation] [conf:0.99] [state:confirmed]