[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE89N96WPAG700R5R4FFED":3,"skill-same:01M6AE89N96WPAG700R5R4FFED":97},{"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":28,"publishedAt":56,"linkOnly":57,"markdownContent":58,"markdownBody":59,"frontMatter":60,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6AE89N96WPAG700R5R4FFED","sql-server-table-reconciliation",null,"Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation report, production vs staging comparison. Uses mssql-python driver with Apache Arrow for fast columnar data transfer and comparison.","github\u002Fawesome-copilot","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3PBDYPK7NVFJNJ66Y8RS",41028,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsql-server-table-reconciliation\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55],"sql","sql server","reconciliation","server","table","sql server table reconciliation","when","python","for","tables","data migration","apache arrow","mssql","across","drift","instances","detection","Production","data","transfer","fast","arrow","etl","apache","verification","validation","report","2026-11-10 10:12:30",false,"---\nname: sql-server-table-reconciliation\ndescription: \"Use when: comparing SQL Server tables across instances, data migration validation, ETL verification, row mismatch detection, schema drift, reconciliation report, production vs staging comparison. Uses mssql-python driver with Apache Arrow for fast columnar data transfer and comparison.\"\n---\n\n# SQL Server Table Reconciliation\n\nCompare identical tables across two SQL Server instances using Python with `mssql-python` driver and Apache Arrow. Detect missing rows, column mismatches, schema drift, and produce a reconciliation report.\n\n## Workflow\n\n1. Collect connection details for source and target\n2. Identify primary key \u002F composite key\n3. Detect schema differences\n4. Extract data via Arrow for efficient columnar transfer\n5. Compare rows and columns\n6. Generate reconciliation report\n\n## Collect Inputs\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| Source server | Yes | Source SQL Server (e.g. `prod-server.database.windows.net`) |\n| Source database | Yes | Source database name |\n| Target server | Yes | Target SQL Server (e.g. `staging-server.database.windows.net`) |\n| Target database | Yes | Target database name |\n| Tables | Yes | Comma-separated `schema.table` names, or `schema.*` wildcard (e.g. `dbo.Orders,dbo.Items` or `dbo.*`) |\n| Auth mode | Yes | `sql` (user\u002Fpassword) or `entra` (Azure AD\u002Ftoken) |\n| Primary key | Auto-detect | Column(s) forming the row identity. Auto-detect from metadata if not provided. |\n| Columns to compare | All | Subset of columns, or all non-PK columns |\n| Chunk size | `100000` | Rows per batch for large tables |\n| Output format | `console` | `console`, `csv`, `parquet`, or `json` |\n\n## Bundled Script\n\nThe reconciliation logic is provided as a standalone script at `scripts\u002Freconcile.py`. Invoke it with the appropriate arguments based on user inputs:\n\n```bash\npython scripts\u002Freconcile.py \\\n    --source-server \u003Csource_server> \\\n    --source-database \u003Csource_database> \\\n    --target-server \u003Ctarget_server> \\\n    --target-database \u003Ctarget_database> \\\n    --tables \"\u003Ctable_spec>\" \\\n    --auth \u003Csql|entra> \\\n    --chunk-size \u003Cchunk_size> \\\n    --output \u003Cconsole|csv|json>\n```\n\n### Optional arguments\n\n| Argument | Description |\n|----------|-------------|\n| `--primary-key` | Comma-separated PK column(s). Omit to auto-detect. |\n| `--columns` | Comma-separated columns to compare. Omit to compare all non-PK columns. |\n\n### Example invocations\n\nSingle table with SQL auth:\n\n```bash\npython scripts\u002Freconcile.py \\\n    --source-server prod-server.database.windows.net \\\n    --source-database ProdDB \\\n    --target-server staging-server.database.windows.net \\\n    --target-database StagingDB \\\n    --tables \"dbo.Orders\" \\\n    --auth sql \\\n    --output console\n```\n\nWildcard with Entra auth and CSV output:\n\n```bash\npython scripts\u002Freconcile.py \\\n    --source-server prod-server.database.windows.net \\\n    --source-database ProdDB \\\n    --target-server staging-server.database.windows.net \\\n    --target-database StagingDB \\\n    --tables \"dbo.*\" \\\n    --auth entra \\\n    --output csv\n```\n\n### Prerequisites\n\nInstall required packages before running:\n\n```bash\npip install mssql-python pyarrow pandas\n```\n\n## Comparison Rules\n\n- **Normalize types before comparing**: cast decimals to same precision, trim strings, normalize datetime to UTC\n- **NULL handling**: `NULL == NULL` is considered a match (both sides missing = no diff)\n- **Ignore row order**: always compare by PK join, never positional\n- **Large tables**: chunk extraction with `OFFSET\u002FFETCH` or `ROW_NUMBER()` partitioning\n\n## Hash-Based Optimization (for large tables)\n\nWhen table has >1M rows, generate a hash pre-check:\n\n```sql\nSELECT {pk_cols},\n       HASHBYTES('SHA2_256', CONCAT_WS('|', col1, col2, ...)) AS row_hash\nFROM {table}\n```\n\nCompare hashes first; only fetch full rows for mismatched hashes. This reduces data transfer significantly.\n\n## Report Format\n\n```\nReconciling dbo.EMPLOYEES...\nReconciling dbo.DEPARTMENTS...\nReconciling dbo.JOBS...\n\n--- dbo.EMPLOYEES ---\n  Source: 107  Target: 107\n  Missing: 0  Extra: 0  Mismatches: 0\n  Result: ✓ IDENTICAL\n\n--- dbo.DEPARTMENTS ---\n  Source: 27  Target: 27\n  Missing: 0  Extra: 0  Mismatches: 3\n  Result: ✗ DIFFERENCES FOUND\n\n--- dbo.JOBS ---\n  Source: 19  Target: 19\n  Missing: 0  Extra: 0  Mismatches: 0\n  Result: ✓ IDENTICAL\n\n=== Summary: 2 passed, 1 failed, 0 skipped \u002F 3 tables ===\n```\n\nWhen a single table is provided, include full detail (schema drift, sample rows, mismatches). When multiple tables, use the compact per-table format above with full detail only for tables with `FAIL` status.\n\n## Performance Considerations\n\n| Scenario | Strategy |\n|----------|----------|\n| \u003C 100K rows | Single Arrow fetch, in-memory pandas compare |\n| 100K–1M rows | Chunked extraction (100K batches), streaming comparison |\n| > 1M rows | Hash pre-check → only fetch mismatched rows |\n| Wide tables (100+ cols) | Compare PK + hash first, drill into specific columns on mismatch |\n| Network-constrained | Use Arrow columnar format (10-50x smaller than row-by-row) |\n\n## Constraints\n\n- Always use `mssql-python` driver (not pyodbc, pymssql)\n- Always use Apache Arrow via cursor (`cursor.arrow()`) for data extraction\n- Connection MUST use connection string format, not keyword arguments (kwargs like `encrypt=True` throw errors)\n- Never compare without identifying PK first — ask user if auto-detect fails\n- Handle connection failures gracefully with retry logic\n- **Never hardcode credentials** in generated scripts — use `os.environ` \u002F `getpass` (env vars: `MSSQL_USER`, `MSSQL_PASSWORD`)\n- Do not print credentials in output or logs\n- Use parameterized queries (`?` placeholders) for metadata lookups — never f-string interpolate user input into SQL\n","# SQL Server Table Reconciliation\n\nCompare identical tables across two SQL Server instances using Python with `mssql-python` driver and Apache Arrow. Detect missing rows, column mismatches, schema drift, and produce a reconciliation report.\n\n## Workflow\n\n1. Collect connection details for source and target\n2. Identify primary key \u002F composite key\n3. Detect schema differences\n4. Extract data via Arrow for efficient columnar transfer\n5. Compare rows and columns\n6. Generate reconciliation report\n\n## Collect Inputs\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| Source server | Yes | Source SQL Server (e.g. `prod-server.database.windows.net`) |\n| Source database | Yes | Source database name |\n| Target server | Yes | Target SQL Server (e.g. `staging-server.database.windows.net`) |\n| Target database | Yes | Target database name |\n| Tables | Yes | Comma-separated `schema.table` names, or `schema.*` wildcard (e.g. `dbo.Orders,dbo.Items` or `dbo.*`) |\n| Auth mode | Yes | `sql` (user\u002Fpassword) or `entra` (Azure AD\u002Ftoken) |\n| Primary key | Auto-detect | Column(s) forming the row identity. Auto-detect from metadata if not provided. |\n| Columns to compare | All | Subset of columns, or all non-PK columns |\n| Chunk size | `100000` | Rows per batch for large tables |\n| Output format | `console` | `console`, `csv`, `parquet`, or `json` |\n\n## Bundled Script\n\nThe reconciliation logic is provided as a standalone script at `scripts\u002Freconcile.py`. Invoke it with the appropriate arguments based on user inputs:\n\n```bash\npython scripts\u002Freconcile.py \\\n    --source-server \u003Csource_server> \\\n    --source-database \u003Csource_database> \\\n    --target-server \u003Ctarget_server> \\\n    --target-database \u003Ctarget_database> \\\n    --tables \"\u003Ctable_spec>\" \\\n    --auth \u003Csql|entra> \\\n    --chunk-size \u003Cchunk_size> \\\n    --output \u003Cconsole|csv|json>\n```\n\n### Optional arguments\n\n| Argument | Description |\n|----------|-------------|\n| `--primary-key` | Comma-separated PK column(s). Omit to auto-detect. |\n| `--columns` | Comma-separated columns to compare. Omit to compare all non-PK columns. |\n\n### Example invocations\n\nSingle table with SQL auth:\n\n```bash\npython scripts\u002Freconcile.py \\\n    --source-server prod-server.database.windows.net \\\n    --source-database ProdDB \\\n    --target-server staging-server.database.windows.net \\\n    --target-database StagingDB \\\n    --tables \"dbo.Orders\" \\\n    --auth sql \\\n    --output console\n```\n\nWildcard with Entra auth and CSV output:\n\n```bash\npython scripts\u002Freconcile.py \\\n    --source-server prod-server.database.windows.net \\\n    --source-database ProdDB \\\n    --target-server staging-server.database.windows.net \\\n    --target-database StagingDB \\\n    --tables \"dbo.*\" \\\n    --auth entra \\\n    --output csv\n```\n\n### Prerequisites\n\nInstall required packages before running:\n\n```bash\npip install mssql-python pyarrow pandas\n```\n\n## Comparison Rules\n\n- **Normalize types before comparing**: cast decimals to same precision, trim strings, normalize datetime to UTC\n- **NULL handling**: `NULL == NULL` is considered a match (both sides missing = no diff)\n- **Ignore row order**: always compare by PK join, never positional\n- **Large tables**: chunk extraction with `OFFSET\u002FFETCH` or `ROW_NUMBER()` partitioning\n\n## Hash-Based Optimization (for large tables)\n\nWhen table has >1M rows, generate a hash pre-check:\n\n```sql\nSELECT {pk_cols},\n       HASHBYTES('SHA2_256', CONCAT_WS('|', col1, col2, ...)) AS row_hash\nFROM {table}\n```\n\nCompare hashes first; only fetch full rows for mismatched hashes. This reduces data transfer significantly.\n\n## Report Format\n\n```\nReconciling dbo.EMPLOYEES...\nReconciling dbo.DEPARTMENTS...\nReconciling dbo.JOBS...\n\n--- dbo.EMPLOYEES ---\n  Source: 107  Target: 107\n  Missing: 0  Extra: 0  Mismatches: 0\n  Result: ✓ IDENTICAL\n\n--- dbo.DEPARTMENTS ---\n  Source: 27  Target: 27\n  Missing: 0  Extra: 0  Mismatches: 3\n  Result: ✗ DIFFERENCES FOUND\n\n--- dbo.JOBS ---\n  Source: 19  Target: 19\n  Missing: 0  Extra: 0  Mismatches: 0\n  Result: ✓ IDENTICAL\n\n=== Summary: 2 passed, 1 failed, 0 skipped \u002F 3 tables ===\n```\n\nWhen a single table is provided, include full detail (schema drift, sample rows, mismatches). When multiple tables, use the compact per-table format above with full detail only for tables with `FAIL` status.\n\n## Performance Considerations\n\n| Scenario | Strategy |\n|----------|----------|\n| \u003C 100K rows | Single Arrow fetch, in-memory pandas compare |\n| 100K–1M rows | Chunked extraction (100K batches), streaming comparison |\n| > 1M rows | Hash pre-check → only fetch mismatched rows |\n| Wide tables (100+ cols) | Compare PK + hash first, drill into specific columns on mismatch |\n| Network-constrained | Use Arrow columnar format (10-50x smaller than row-by-row) |\n\n## Constraints\n\n- Always use `mssql-python` driver (not pyodbc, pymssql)\n- Always use Apache Arrow via cursor (`cursor.arrow()`) for data extraction\n- Connection MUST use connection string format, not keyword arguments (kwargs like `encrypt=True` throw errors)\n- Never compare without identifying PK first — ask user if auto-detect fails\n- Handle connection failures gracefully with retry logic\n- **Never hardcode credentials** in generated scripts — use `os.environ` \u002F `getpass` (env vars: `MSSQL_USER`, `MSSQL_PASSWORD`)\n- Do not print credentials in output or logs\n- Use parameterized queries (`?` placeholders) for metadata lookups — never f-string interpolate user input into SQL\n",{"name":5,"description":7},"main","5269f7ea2d6c3a9bfda5ed878b6726cf509121fd","skills\u002Fsql-server-table-reconciliation",5335,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot","https:\u002F\u002Fawesome-copilot.github.com\u002F","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-11 11:59:04",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add github\u002Fawesome-copilot --skill sql-server-table-reconciliation",{"tool":77,"command":78},"bunx","bunx skills add github\u002Fawesome-copilot --skill sql-server-table-reconciliation",{"tool":80,"command":81},"pnpm","pnpm dlx skills add github\u002Fawesome-copilot --skill sql-server-table-reconciliation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsql-server-table-reconciliation\u002FSKILL.md",true,[85,91],{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"agents\u002Fopenai.yaml","REFERENCE","参考文档",145,"https:\u002F\u002Fgithub.com\u002Fhareki\u002Fdotfiles\u002Fblob\u002Fmain\u002Fagents\u002F.agents\u002Fskills\u002Fgrill-with-docs\u002Fagents\u002Fopenai.yaml",{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Freconcile.py","SCRIPT","脚本",13208,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsql-server-table-reconciliation\u002Fscripts\u002Freconcile.py",[98,129,155,183,215,232],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":110,"publishedAt":56},"01M70KXZNX9ES38N2A8M58ZZMZ","supabase-rls-policies","Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fsupabase-rls-policies\u002FSKILL.md",[104,107],{"categoryNo":105,"categoryName":106,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[111,112,113,114,115,35,116,117,118,119,120,121,38,122,123,124,125,126,127,128],"supabase","rls","supabase rls","supabase rls policies","project","review","change","read","write","security","isolation","as","tests","prove","use","users","functions","with",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":136,"publishedAt":56},"01M70KWA5YWXDV6V8DZ19E3T2Y","skill-distribution-audit","Audit a skill collection before release or investigate installer omissions, archived\u002Ftemplate leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fskill-distribution-audit\u002FSKILL.md",[135],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},[137,138,139,140,141,142,37,143,144,145,146,147,148,43,149,150,151,152,153,154],"distribution","skill distribution audit","audit","SET","deterministic","installer","discovery","comparison","helper","manifest","version","collection","output","investigate","duplicate","template","release","reconcile",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":159,"sourceHtmlUrl":160,"categories":161,"keywords":165,"publishedAt":56},"01M70KCJPFVW7PPQ49CC5R8JGK","logicapps-custom-code-net10-migration","Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project\u002Fpackage configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Flogicapps-custom-code-net10-migration\u002FSKILL.md",[162],{"categoryNo":163,"categoryName":164,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师",[166,167,168,169,170,171,37,115,172,173,174,175,176,177,178,125,179,180,181,182],"custom","code","logicapps custom code net10 migration","migration","projects","standalone","deployment","applications","local","azure","worker","upgrades","package","apps","Legacy","debugging","workflows",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":187,"sourceHtmlUrl":188,"categories":189,"keywords":192,"publishedAt":56},"01M6AEBN37RQMXJ3298PEY7PG1","winmd-api-search","Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI\u002FML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fwinmd-api-search\u002FSKILL.md",[190,191],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":163,"categoryName":164,"taxonomyType":26,"taxonomyTypeDesc":27},[193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,35,208,209,210,211,212,37,213,214],"winmd api search","search","api","windows","desktop","file access","enumeration","ui","ml","file","networking","capabilities","notifications","explore","access","features","full","camera","events","platform","methods","controls",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":219,"licenseFileUrl":220,"sourceHtmlUrl":221,"categories":222,"keywords":228,"publishedAt":56},"01M6AE571R3SC1ZGE202B3NB5S","resemble-detect","Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fresemble-detect\u002FSKILL.md",[223,224,227],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":225,"categoryName":226,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},[229,140,202,230,231],"resemble detect","https","identity",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":219,"licenseFileUrl":236,"sourceHtmlUrl":237,"categories":238,"keywords":243,"publishedAt":56},"01M6AE30BSK2HCY4TQQ22Z8JRD","quality-playbook","Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fawesome-copilot\u002Fblob\u002Fmain\u002Fskills\u002Fquality-playbook\u002FSKILL.md",[239,242],{"categoryNo":240,"categoryName":241,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},[244,245,246,247,167,116,9,139,248,249,230,55,250,251,252,253,254,255,256,257,258,259,123,260,261,262,263],"playbook","quality playbook","quality","code review","tdd","run","spec","bug report","council","engineering","functional","spec audit","bug","verified","multi-model","three","coverage","model","regression","structural"]