[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C2VEPC28F39EN1N4GG46HH":3,"skill-same:01M7C2VEPC28F39EN1N4GG46HH":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7C2VEPC28F39EN1N4GG46HH","sqlite-map-parser",null,"Parse SQLite databases into structured JSON data. Use when exploring unknown database schemas, understanding table relationships, and extracting map data as JSON.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FWML\u002Ftasks\u002Fciv6-adjacency-optimizer\u002Frepaired_skill\u002Fsqlite-map-parser\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sqlite-map-parser\ndescription: Parse SQLite databases into structured JSON data. Use when exploring unknown database schemas, understanding table relationships, and extracting map data as JSON.\n---\n\n# SQLite to Structured JSON\n\nParse SQLite databases by exploring schemas first, then extracting data into structured JSON.\n\n## Step 1: Explore the Schema\n\nAlways start by understanding what tables exist and their structure.\n\n### List All Tables\n```sql\nSELECT name FROM sqlite_master WHERE type='table';\n```\n\n### Inspect Table Schema\n```sql\n-- Get column names and types\nPRAGMA table_info(TableName);\n\n-- See CREATE statement\nSELECT sql FROM sqlite_master WHERE name='TableName';\n```\n\n### Find Primary\u002FUnique Keys\n```sql\n-- Primary key info\nPRAGMA table_info(TableName);  -- 'pk' column shows primary key order\n\n-- All indexes (includes unique constraints)\nPRAGMA index_list(TableName);\n\n-- Columns in an index\nPRAGMA index_info(index_name);\n```\n\n## Step 2: Understand Relationships\n\n### Identify Foreign Keys\n```sql\nPRAGMA foreign_key_list(TableName);\n```\n\n### Common Patterns\n\n**ID-based joins:** Tables often share an ID column\n```sql\n-- Main table has ID as primary key\n-- Related tables reference it\nSELECT m.*, r.ExtraData\nFROM MainTable m\nLEFT JOIN RelatedTable r ON m.ID = r.ID;\n```\n\n**Coordinate-based keys:** Spatial data often uses computed coordinates\n```python\n# If ID represents a linear index into a grid:\nx = id % width\ny = id \u002F\u002F width\n```\n\n## Step 3: Extract and Transform\n\n### Basic Pattern\n```python\nimport sqlite3\nimport json\n\ndef parse_sqlite_to_json(db_path):\n    conn = sqlite3.connect(db_path)\n    conn.row_factory = sqlite3.Row  # Access columns by name\n    cursor = conn.cursor()\n\n    # 1. Explore schema\n    cursor.execute(\"SELECT name FROM sqlite_master WHERE type='table'\")\n    tables = [row[0] for row in cursor.fetchall()]\n\n    # 2. Get dimensions\u002Fmetadata from config table\n    cursor.execute(\"SELECT * FROM MetadataTable LIMIT 1\")\n    metadata = dict(cursor.fetchone())\n\n    # 3. Build indexed data structure\n    data = {}\n    cursor.execute(\"SELECT * FROM MainTable\")\n    for row in cursor.fetchall():\n        key = row[\"ID\"]  # or compute: (row[\"X\"], row[\"Y\"])\n        data[key] = dict(row)\n\n    # 4. Join related data\n    cursor.execute(\"SELECT * FROM RelatedTable\")\n    for row in cursor.fetchall():\n        key = row[\"ID\"]\n        if key in data:\n            data[key][\"extra_field\"] = row[\"Value\"]\n\n    conn.close()\n    return {\"metadata\": metadata, \"items\": list(data.values())}\n```\n\n### Handle Missing Tables Gracefully\n```python\ndef safe_query(cursor, query):\n    try:\n        cursor.execute(query)\n        return cursor.fetchall()\n    except sqlite3.OperationalError:\n        return []  # Table doesn't exist\n```\n\n## Step 4: Output as Structured JSON\n\n### Map\u002FDictionary Output\nUse when items have natural unique keys:\n```json\n{\n  \"metadata\": {\"width\": 44, \"height\": 26},\n  \"tiles\": {\n    \"0,0\": {\"terrain\": \"GRASS\", \"feature\": null},\n    \"1,0\": {\"terrain\": \"PLAINS\", \"feature\": \"FOREST\"},\n    \"2,0\": {\"terrain\": \"COAST\", \"resource\": \"FISH\"}\n  }\n}\n```\n\n### Array Output\nUse when order matters or keys are simple integers:\n```json\n{\n  \"metadata\": {\"width\": 44, \"height\": 26},\n  \"tiles\": [\n    {\"x\": 0, \"y\": 0, \"terrain\": \"GRASS\"},\n    {\"x\": 1, \"y\": 0, \"terrain\": \"PLAINS\", \"feature\": \"FOREST\"},\n    {\"x\": 2, \"y\": 0, \"terrain\": \"COAST\", \"resource\": \"FISH\"}\n  ]\n}\n```\n\n## Common Schema Patterns\n\n### Grid\u002FMap Data\n- Main table: positions with base properties\n- Feature tables: join on position ID for overlays\n- Compute (x, y) from linear ID: `x = id % width, y = id \u002F\u002F width`\n\n### Hierarchical Data\n- Parent table with primary key\n- Child tables with foreign key reference\n- Use LEFT JOIN to preserve all parents\n\n### Enum\u002FLookup Tables\n- Type tables map codes to descriptions\n- Join to get human-readable values\n\n## Debugging Tips\n\n```sql\n-- Sample data from any table\nSELECT * FROM TableName LIMIT 5;\n\n-- Count rows\nSELECT COUNT(*) FROM TableName;\n\n-- Find distinct values in a column\nSELECT DISTINCT ColumnName FROM TableName;\n\n-- Check for nulls\nSELECT COUNT(*) FROM TableName WHERE ColumnName IS NULL;\n```\n","# SQLite to Structured JSON\n\nParse SQLite databases by exploring schemas first, then extracting data into structured JSON.\n\n## Step 1: Explore the Schema\n\nAlways start by understanding what tables exist and their structure.\n\n### List All Tables\n```sql\nSELECT name FROM sqlite_master WHERE type='table';\n```\n\n### Inspect Table Schema\n```sql\n-- Get column names and types\nPRAGMA table_info(TableName);\n\n-- See CREATE statement\nSELECT sql FROM sqlite_master WHERE name='TableName';\n```\n\n### Find Primary\u002FUnique Keys\n```sql\n-- Primary key info\nPRAGMA table_info(TableName);  -- 'pk' column shows primary key order\n\n-- All indexes (includes unique constraints)\nPRAGMA index_list(TableName);\n\n-- Columns in an index\nPRAGMA index_info(index_name);\n```\n\n## Step 2: Understand Relationships\n\n### Identify Foreign Keys\n```sql\nPRAGMA foreign_key_list(TableName);\n```\n\n### Common Patterns\n\n**ID-based joins:** Tables often share an ID column\n```sql\n-- Main table has ID as primary key\n-- Related tables reference it\nSELECT m.*, r.ExtraData\nFROM MainTable m\nLEFT JOIN RelatedTable r ON m.ID = r.ID;\n```\n\n**Coordinate-based keys:** Spatial data often uses computed coordinates\n```python\n# If ID represents a linear index into a grid:\nx = id % width\ny = id \u002F\u002F width\n```\n\n## Step 3: Extract and Transform\n\n### Basic Pattern\n```python\nimport sqlite3\nimport json\n\ndef parse_sqlite_to_json(db_path):\n    conn = sqlite3.connect(db_path)\n    conn.row_factory = sqlite3.Row  # Access columns by name\n    cursor = conn.cursor()\n\n    # 1. Explore schema\n    cursor.execute(\"SELECT name FROM sqlite_master WHERE type='table'\")\n    tables = [row[0] for row in cursor.fetchall()]\n\n    # 2. Get dimensions\u002Fmetadata from config table\n    cursor.execute(\"SELECT * FROM MetadataTable LIMIT 1\")\n    metadata = dict(cursor.fetchone())\n\n    # 3. Build indexed data structure\n    data = {}\n    cursor.execute(\"SELECT * FROM MainTable\")\n    for row in cursor.fetchall():\n        key = row[\"ID\"]  # or compute: (row[\"X\"], row[\"Y\"])\n        data[key] = dict(row)\n\n    # 4. Join related data\n    cursor.execute(\"SELECT * FROM RelatedTable\")\n    for row in cursor.fetchall():\n        key = row[\"ID\"]\n        if key in data:\n            data[key][\"extra_field\"] = row[\"Value\"]\n\n    conn.close()\n    return {\"metadata\": metadata, \"items\": list(data.values())}\n```\n\n### Handle Missing Tables Gracefully\n```python\ndef safe_query(cursor, query):\n    try:\n        cursor.execute(query)\n        return cursor.fetchall()\n    except sqlite3.OperationalError:\n        return []  # Table doesn't exist\n```\n\n## Step 4: Output as Structured JSON\n\n### Map\u002FDictionary Output\nUse when items have natural unique keys:\n```json\n{\n  \"metadata\": {\"width\": 44, \"height\": 26},\n  \"tiles\": {\n    \"0,0\": {\"terrain\": \"GRASS\", \"feature\": null},\n    \"1,0\": {\"terrain\": \"PLAINS\", \"feature\": \"FOREST\"},\n    \"2,0\": {\"terrain\": \"COAST\", \"resource\": \"FISH\"}\n  }\n}\n```\n\n### Array Output\nUse when order matters or keys are simple integers:\n```json\n{\n  \"metadata\": {\"width\": 44, \"height\": 26},\n  \"tiles\": [\n    {\"x\": 0, \"y\": 0, \"terrain\": \"GRASS\"},\n    {\"x\": 1, \"y\": 0, \"terrain\": \"PLAINS\", \"feature\": \"FOREST\"},\n    {\"x\": 2, \"y\": 0, \"terrain\": \"COAST\", \"resource\": \"FISH\"}\n  ]\n}\n```\n\n## Common Schema Patterns\n\n### Grid\u002FMap Data\n- Main table: positions with base properties\n- Feature tables: join on position ID for overlays\n- Compute (x, y) from linear ID: `x = id % width, y = id \u002F\u002F width`\n\n### Hierarchical Data\n- Parent table with primary key\n- Child tables with foreign key reference\n- Use LEFT JOIN to preserve all parents\n\n### Enum\u002FLookup Tables\n- Type tables map codes to descriptions\n- Join to get human-readable values\n\n## Debugging Tips\n\n```sql\n-- Sample data from any table\nSELECT * FROM TableName LIMIT 5;\n\n-- Count rows\nSELECT COUNT(*) FROM TableName;\n\n-- Find distinct values in a column\nSELECT DISTINCT ColumnName FROM TableName;\n\n-- Check for nulls\nSELECT COUNT(*) FROM TableName WHERE ColumnName IS NULL;\n```\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FWML\u002Ftasks\u002Fciv6-adjacency-optimizer\u002Frepaired_skill\u002Fsqlite-map-parser",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill sqlite-map-parser",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill sqlite-map-parser",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill sqlite-map-parser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FWML\u002Ftasks\u002Fciv6-adjacency-optimizer\u002Frepaired_skill\u002Fsqlite-map-parser\u002FSKILL.md",true,[],[46,53,60,67,72,77],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":68,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":73,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":78,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]