@synsci/cli-darwin-x64 1.1.49

package/bin/skills/hugging-face-datasets/templates/chat.json

@@ -0,0 +1,55 @@
+{
+  "type": "chat",
+  "description": "Conversational AI training data with chat templating support",
+  "system_prompt": "You are an AI assistant expert at using tools and engaging in helpful conversations. Generate training examples that demonstrate natural dialogue patterns, tool usage, and problem-solving interactions.",
+  "validation_schema": {
+    "required_fields": ["messages"],
+    "recommended_fields": ["scenario", "complexity", "tools_used", "learning_objectives"],
+    "field_types": {
+      "messages": "array",
+      "scenario": "string",
+      "complexity": "enum:simple,intermediate,advanced",
+      "tools_used": "array",
+      "learning_objectives": "array"
+    }
+  },
+  "example_structure": {
+    "messages": [
+      {
+        "role": "user|assistant|tool|system",
+        "content": "Message content",
+        "tool_calls": [
+          {
+            "type": "function",
+            "function": {
+              "name": "tool_name",
+              "arguments": {"param": "value"}
+            }
+          }
+        ]
+      }
+    ],
+    "scenario": "Brief description of the use case",
+    "complexity": "simple|intermediate|advanced",
+    "tools_used": ["tool1", "tool2"],
+    "learning_objectives": ["objective1", "objective2"]
+  },
+  "examples": [
+    {
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello! Can you help me understand how to use APIs?"
+        },
+        {
+          "role": "assistant",
+          "content": "I'd be happy to help you understand APIs! An API (Application Programming Interface) is like a bridge that allows different software applications to communicate with each other.\n\nThink of it like ordering at a restaurant:\n- You (the client) look at the menu (API documentation)\n- You tell the waiter (the API) what you want\n- The waiter takes your order to the kitchen (the server)\n- The kitchen prepares your food (processes the request)\n- The waiter brings your food back (returns the response)\n\nWould you like me to show you a simple example of making an API call?"
+        }
+      ],
+      "scenario": "API education and explanation",
+      "complexity": "simple",
+      "tools_used": [],
+      "learning_objectives": ["API concepts", "educational conversation", "analogical explanation"]
+    }
+  ]
+}

package/bin/skills/hugging-face-datasets/templates/classification.json

@@ -0,0 +1,62 @@
+{
+  "type": "classification",
+  "description": "Text classification datasets for sentiment analysis, topic classification, intent detection, etc.",
+  "system_prompt": "Create high-quality text classification training data. Each example should have clear, unambiguous text and appropriate labels. Ensure balanced representation across all classes and include diverse language patterns.",
+  "validation_schema": {
+    "required_fields": ["text", "label"],
+    "recommended_fields": ["confidence", "metadata", "source"],
+    "field_types": {
+      "text": "string",
+      "label": "string|array",
+      "confidence": "number",
+      "metadata": "object",
+      "source": "string"
+    }
+  },
+  "example_structure": {
+    "text": "Input text to be classified",
+    "label": "classification_label",
+    "confidence": 0.95,
+    "metadata": {
+      "length": 42,
+      "language": "en",
+      "domain": "technology"
+    },
+    "source": "web_scraping"
+  },
+  "examples": [
+    {
+      "text": "I absolutely love this new smartphone! The camera quality is outstanding and the battery lasts all day.",
+      "label": "positive",
+      "confidence": 0.98,
+      "metadata": {
+        "length": 98,
+        "language": "en",
+        "domain": "product_reviews"
+      },
+      "source": "customer_feedback"
+    },
+    {
+      "text": "The software keeps crashing and customer support is unresponsive. Very disappointed with this purchase.",
+      "label": "negative",
+      "confidence": 0.92,
+      "metadata": {
+        "length": 96,
+        "language": "en",
+        "domain": "product_reviews"
+      },
+      "source": "customer_feedback"
+    },
+    {
+      "text": "Book a table for two at 7 PM tonight",
+      "label": "restaurant_reservation",
+      "confidence": 0.95,
+      "metadata": {
+        "length": 35,
+        "language": "en",
+        "domain": "intent_detection"
+      },
+      "source": "voice_assistant"
+    }
+  ]
+}

package/bin/skills/hugging-face-datasets/templates/completion.json

@@ -0,0 +1,51 @@
+{
+  "type": "completion",
+  "description": "Text completion and generation datasets for language modeling, code completion, creative writing",
+  "system_prompt": "Generate diverse text completion examples that demonstrate natural language patterns, creativity, and contextual understanding. Include various domains like code, creative writing, technical documentation, and conversational text.",
+  "validation_schema": {
+    "required_fields": ["prompt", "completion"],
+    "recommended_fields": ["domain", "style", "length", "difficulty"],
+    "field_types": {
+      "prompt": "string",
+      "completion": "string",
+      "domain": "enum:code,creative,technical,conversational,academic",
+      "style": "string",
+      "length": "enum:short,medium,long",
+      "difficulty": "enum:beginner,intermediate,advanced"
+    }
+  },
+  "example_structure": {
+    "prompt": "The beginning text or context",
+    "completion": "The expected continuation or completion",
+    "domain": "code|creative|technical|conversational|academic",
+    "style": "description of writing style",
+    "length": "short|medium|long",
+    "difficulty": "beginner|intermediate|advanced"
+  },
+  "examples": [
+    {
+      "prompt": "def fibonacci(n):\n    \"\"\"Calculate the nth Fibonacci number.\"\"\"\n    if n <= 1:\n        return n\n    else:",
+      "completion": "        return fibonacci(n-1) + fibonacci(n-2)",
+      "domain": "code",
+      "style": "python_function",
+      "length": "short",
+      "difficulty": "beginner"
+    },
+    {
+      "prompt": "The old lighthouse stood silently on the cliff, its beacon long extinguished. Sarah approached slowly, wondering",
+      "completion": "if the stories her grandmother had told her were true. As she pushed open the weathered door, a gust of salt air carried whispers of the past, and she could almost see the ghostly figure of the lighthouse keeper who had vanished mysteriously fifty years ago.",
+      "domain": "creative",
+      "style": "narrative_fiction",
+      "length": "medium",
+      "difficulty": "intermediate"
+    },
+    {
+      "prompt": "To configure SSL/TLS encryption for your web server, you'll need to:",
+      "completion": "1. Obtain an SSL certificate from a trusted Certificate Authority (CA)\n2. Install the certificate on your web server\n3. Configure your server to use HTTPS (port 443)\n4. Update your application to redirect HTTP traffic to HTTPS\n5. Test the implementation using SSL testing tools\n\nMake sure to backup your server configuration before making changes.",
+      "domain": "technical",
+      "style": "instructional",
+      "length": "medium",
+      "difficulty": "intermediate"
+    }
+  ]
+}

package/bin/skills/hugging-face-datasets/templates/custom.json

@@ -0,0 +1,75 @@
+{
+  "type": "custom",
+  "description": "Flexible template for custom dataset formats - define your own schema and validation rules",
+  "system_prompt": "Generate data according to the custom schema provided. Follow the field definitions, data types, and validation rules specified in the schema configuration.",
+  "validation_schema": {
+    "required_fields": ["data"],
+    "recommended_fields": ["schema", "metadata"],
+    "field_types": {
+      "data": "any",
+      "schema": "object",
+      "metadata": "object"
+    }
+  },
+  "example_structure": {
+    "data": "Your custom data structure goes here",
+    "schema": {
+      "fields": [
+        {
+          "name": "field_name",
+          "type": "string|number|boolean|array|object",
+          "required": true,
+          "description": "Field description"
+        }
+      ],
+      "validation_rules": {
+        "custom_rule_1": "validation logic",
+        "custom_rule_2": "additional validation"
+      }
+    },
+    "metadata": {
+      "created_by": "user",
+      "purpose": "dataset purpose",
+      "version": "1.0"
+    }
+  },
+  "examples": [
+    {
+      "data": {
+        "id": "unique_identifier",
+        "features": {
+          "text_feature": "sample text",
+          "numeric_features": [1.0, 2.5, -0.3],
+          "categorical_feature": "category_a"
+        },
+        "labels": {
+          "primary_label": "positive",
+          "confidence_score": 0.87,
+          "secondary_labels": ["helpful", "informative"]
+        },
+        "annotations": {
+          "annotator_id": "expert_1",
+          "annotation_time": "2024-01-15T10:30:00Z",
+          "quality_score": 9
+        }
+      },
+      "schema": {
+        "fields": [
+          {"name": "id", "type": "string", "required": true, "description": "Unique identifier"},
+          {"name": "features", "type": "object", "required": true, "description": "Input features"},
+          {"name": "labels", "type": "object", "required": true, "description": "Target labels"},
+          {"name": "annotations", "type": "object", "required": false, "description": "Annotation metadata"}
+        ],
+        "validation_rules": {
+          "id_format": "must be non-empty string",
+          "confidence_range": "must be between 0 and 1"
+        }
+      },
+      "metadata": {
+        "created_by": "data_scientist",
+        "purpose": "multi_modal_classification",
+        "version": "1.0"
+      }
+    }
+  ]
+}

package/bin/skills/hugging-face-datasets/templates/qa.json

@@ -0,0 +1,54 @@
+{
+  "type": "qa",
+  "description": "Question-answering datasets for reading comprehension, knowledge QA, and factual question answering",
+  "system_prompt": "Generate high-quality question-answer pairs with clear, informative answers. Include context when needed and ensure questions are well-formed and answerable. Cover diverse topics and question types.",
+  "validation_schema": {
+    "required_fields": ["question", "answer"],
+    "recommended_fields": ["context", "answer_type", "difficulty", "topic", "source"],
+    "field_types": {
+      "question": "string",
+      "answer": "string|array",
+      "context": "string",
+      "answer_type": "enum:factual,explanatory,opinion,yes_no,multiple_choice",
+      "difficulty": "enum:easy,medium,hard",
+      "topic": "string",
+      "source": "string"
+    }
+  },
+  "example_structure": {
+    "question": "What is the question being asked?",
+    "answer": "The complete answer to the question",
+    "context": "Additional context or passage (if needed)",
+    "answer_type": "factual|explanatory|opinion|yes_no|multiple_choice",
+    "difficulty": "easy|medium|hard",
+    "topic": "subject_area",
+    "source": "where_this_came_from"
+  },
+  "examples": [
+    {
+      "question": "What is the capital of France?",
+      "answer": "Paris",
+      "answer_type": "factual",
+      "difficulty": "easy",
+      "topic": "geography",
+      "source": "general_knowledge"
+    },
+    {
+      "question": "How does photosynthesis work?",
+      "answer": "Photosynthesis is the process by which plants use sunlight, carbon dioxide, and water to produce glucose and oxygen. Chlorophyll in plant cells captures light energy, which drives chemical reactions that convert CO2 and H2O into C6H12O6 (glucose) and O2. This process occurs primarily in the chloroplasts of leaf cells.",
+      "answer_type": "explanatory",
+      "difficulty": "medium",
+      "topic": "biology",
+      "source": "educational_content"
+    },
+    {
+      "question": "Based on the passage, what was the main cause of the economic downturn?",
+      "answer": "According to the passage, the main cause was the sudden drop in consumer confidence following the bank failures, which led to reduced spending and business investment.",
+      "context": "The economic downturn of 2008 began when several major banks failed due to subprime mortgage losses. This triggered a crisis of confidence among consumers and businesses, leading to decreased spending and investment. The ripple effects spread throughout the global economy.",
+      "answer_type": "explanatory",
+      "difficulty": "medium",
+      "topic": "economics",
+      "source": "reading_comprehension"
+    }
+  ]
+}

package/bin/skills/hugging-face-datasets/templates/tabular.json

@@ -0,0 +1,81 @@
+{
+  "type": "tabular",
+  "description": "Structured tabular data for regression, classification, or analysis tasks",
+  "system_prompt": "Generate structured tabular data with clear column definitions and appropriate data types. Ensure realistic value ranges and relationships between variables. Include proper metadata for each column.",
+  "validation_schema": {
+    "required_fields": ["data", "columns"],
+    "recommended_fields": ["target", "metadata", "description"],
+    "field_types": {
+      "data": "array",
+      "columns": "array",
+      "target": "string",
+      "metadata": "object",
+      "description": "string"
+    }
+  },
+  "example_structure": {
+    "columns": [
+      {
+        "name": "column_name",
+        "type": "numeric|categorical|text|datetime",
+        "description": "What this column represents",
+        "nullable": true
+      }
+    ],
+    "data": [
+      {"column1": "value1", "column2": "value2"},
+      {"column1": "value3", "column2": "value4"}
+    ],
+    "target": "target_column_name",
+    "metadata": {
+      "rows": 1000,
+      "features": 10,
+      "task": "classification|regression|clustering"
+    },
+    "description": "Description of the dataset purpose"
+  },
+  "examples": [
+    {
+      "columns": [
+        {
+          "name": "age",
+          "type": "numeric",
+          "description": "Customer age in years",
+          "nullable": false
+        },
+        {
+          "name": "income",
+          "type": "numeric",
+          "description": "Annual income in USD",
+          "nullable": false
+        },
+        {
+          "name": "education",
+          "type": "categorical",
+          "description": "Education level",
+          "nullable": false
+        },
+        {
+          "name": "purchased",
+          "type": "categorical",
+          "description": "Whether customer made a purchase",
+          "nullable": false
+        }
+      ],
+      "data": [
+        {"age": 25, "income": 45000, "education": "bachelor", "purchased": "yes"},
+        {"age": 34, "income": 67000, "education": "master", "purchased": "yes"},
+        {"age": 19, "income": 23000, "education": "high_school", "purchased": "no"},
+        {"age": 42, "income": 85000, "education": "bachelor", "purchased": "yes"},
+        {"age": 28, "income": 52000, "education": "bachelor", "purchased": "no"}
+      ],
+      "target": "purchased",
+      "metadata": {
+        "rows": 5,
+        "features": 3,
+        "task": "classification"
+      },
+      "description": "Customer purchase prediction based on demographics"
+    }
+  ]
+}