Initial commit

skills/extract_from_pdfs/assets/schema_template.json

@@ -0,0 +1,105 @@
+{
+  "_comment": "This is a template extraction schema. Customize for your specific use case.",
+  "_instructions": "Fill in the sections below with your specific extraction requirements.",
+
+  "objective": "carefully analyze this paper and extract [DESCRIBE YOUR DATA TYPE, e.g., 'empirical observations of X', 'experimental measurements of Y', etc.]",
+
+  "system_context": "You are a scientific research assistant specializing in [YOUR DOMAIN, e.g., 'ecology', 'chemistry', 'medicine', etc.]. Your task is to analyze scientific papers and extract structured data for systematic review and meta-analysis.",
+
+  "instructions": [
+    "Determine if the paper contains [YOUR CRITERIA, e.g., 'primary empirical data']",
+    "If present, extract all [YOUR RECORD TYPE, e.g., 'observation records', 'measurements', 'outcomes']",
+    "For each record, extract the following information: [LIST KEY FIELDS]"
+  ],
+
+  "analysis_steps": [
+    "1. Identify and quote relevant sections containing [YOUR DATA TYPE]",
+    "2. List out each [RECORD UNIT, e.g., 'species', 'compound', 'patient cohort']",
+    "3. For each unit, extract required information and quote supporting text",
+    "4. [ADD DOMAIN-SPECIFIC VALIDATION STEPS]",
+    "5. Double-check for accuracy and completeness"
+  ],
+
+  "important_notes": [
+    "Only include PRIMARY data from this paper, not secondary sources",
+    "If a record involves multiple [UNITS], separate into individual records",
+    "Do not add fields not in the schema",
+    "Use 'none' or empty lists for unknown values",
+    "List names exactly as they appear in the source"
+  ],
+
+  "output_schema": {
+    "type": "object",
+    "properties": {
+      "has_relevant_data": {
+        "type": "boolean",
+        "description": "Whether the paper contains the target data type"
+      },
+      "data_description": {
+        "type": "string",
+        "description": "Brief explanation of what data is present"
+      },
+      "records": {
+        "type": "array",
+        "description": "List of extracted records",
+        "items": {
+          "type": "object",
+          "properties": {
+            "_comment": "CUSTOMIZE THESE FIELDS FOR YOUR USE CASE",
+            "location": {
+              "type": "string",
+              "description": "Geographic location (if applicable)"
+            },
+            "subject": {
+              "type": "string",
+              "description": "Main subject of the record (species, compound, etc.)"
+            },
+            "measurement_type": {
+              "type": "string",
+              "description": "Type of measurement or observation"
+            },
+            "value": {
+              "type": ["number", "string"],
+              "description": "Measured or observed value"
+            },
+            "units": {
+              "type": "string",
+              "description": "Units of measurement"
+            },
+            "method": {
+              "type": "string",
+              "description": "Brief description of methodology"
+            },
+            "sample_size": {
+              "type": "integer",
+              "description": "Sample size if applicable"
+            },
+            "notes": {
+              "type": "string",
+              "description": "Additional relevant notes"
+            }
+          },
+          "required": ["subject"]
+        }
+      }
+    },
+    "required": ["has_relevant_data", "records"]
+  },
+
+  "output_example": {
+    "has_relevant_data": true,
+    "data_description": "Paper reports 5 observation records across 3 locations",
+    "records": [
+      {
+        "location": "Example Location",
+        "subject": "Example Subject",
+        "measurement_type": "Example Type",
+        "value": 42.5,
+        "units": "mg/L",
+        "method": "Brief methodology description",
+        "sample_size": 20,
+        "notes": "Any relevant notes"
+      }
+    ]
+  }
+}