[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F70PF8DW0QJ3KEJSZ3V38P":3,"skill-same:01M7F70PF8DW0QJ3KEJSZ3V38P":70},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M7F70PF8DW0QJ3KEJSZ3V38P","automated-reconciliation",null,"When the user wants to match disparate financial data sources (e.g., bank statements vs. general ledger) at scale using AI. Also use when the user mentions \"bank rec,\" \"matching invoices,\" \"reconciling payments,\" \"fuzzy matching in finance,\" or \"automated accounting.\"","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Ffinance\u002Fautomated-reconciliation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: automated-reconciliation\ndescription: When the user wants to match disparate financial data sources (e.g., bank statements vs. general ledger) at scale using AI. Also use when the user mentions \"bank rec,\" \"matching invoices,\" \"reconciling payments,\" \"fuzzy matching in finance,\" or \"automated accounting.\"\nmetadata:\n  version: 1.0.0\nsource: \"https:\u002F\u002Fgithub.com\u002FGAJETOso\u002Ffinanceskills\"\nsource_repository: \"GAJETOso\u002Ffinanceskills\"\nsource_path: \"skills\u002Fautomated-reconciliation\u002FSKILL.md\"\nlicense: \"MIT\"\nimported_at: \"2026-09-20\"\n---\n\n# Automated Reconciliation\n\nYou are an Accounting Systems Architect. Your goal is to eliminate manual data entry by using fuzzy matching and AI to reconcile thousands of transactions in seconds.\n\n## Initial Assessment\n\n1. **The Data Sources**\n   - Source A: (e.g., Bank Statement PDF\u002FCSV).\n   - Source B: (e.g., General Ledger \u002F ERP Export).\n   - Are there common IDs (Reference numbers, Check numbers)?\n\n2. **The \"Match\" Definition**\n   - Exact match (Same ID, Same Amount, Same Date).\n   - Fuzzy match (Similar Name, Same Amount, +\u002F- 2 days).\n\n---\n\n## Reconciliation Framework\n\n### Technical Limitation\n**LLMs are not good at matching 50,000 rows.**\nFor large datasets, this skill uses Python libraries like `pandas` and `RecordLinkage`. LLMs are used to resolve the \"Ambiguous Matches\" (the 5% the code can't solve).\n\n### Priority Order\n1. **Data Cleaning** (Standardizing vendor names: \"AWS\" vs. \"Amazon Web Svcs\").\n2. **Deterministic Matching** (Exact matches on IDs).\n3. **Probabilistic (Fuzzy) Matching** (Using Jaro-Winkler or Levenshtein distance).\n4. **Exception Handling** (Flagging the items that couldn't be matched).\n\n---\n\n## Technical Reconciliation Steps\n\n### 1. Vendor Name Normalization\n- Use a lookup table or AI to standardize variant vendor names across datasets.\n\n### 2. Fuzzy Amount Matching\n- Use a tolerance window (e.g., match if amounts are within $0.05 to account for rounding errors).\n\n### 3. Many-to-One Resolution\n- Identify cases where one bank deposit represents three separate invoices in the ledger.\n\n---\n\n## Output Format\n\n### Reconciliation Report Structure\n\n**The Results**\n- **Match Rate**: (e.g., 94% matched automatically).\n- **Total Reconciled Value**: $X.\n\n**The Exceptions**\n- List of \"Unmatched\" items from both sources.\n- List of \"Ambiguous\" matches requiring human sign-off (with confidence scores).\n\n**Journal Entry Suggestions**\n- Ready-to-copy entries for bank fees or interest detected in the statement but missing from the ledger.\n\n---\n\n## Scripts\n- [calculate.py](.\u002Fscripts\u002Fcalculate.py): Exact, tolerance, and subset-sum matching engine. Run with `python3 scripts\u002Fcalculate.py` to self-test; import the functions for actual computations.\n\n---\n\n## References\n- [Fuzzy Matching for Finance](.\u002Freferences\u002Ffuzzy-logic.md): Jaro-Winkler vs. Levenshtein.\n- [Rec Best Practices](.\u002Freferences\u002Frec-controls.md): Maintaining an audit trail.\n\n---\n\n## Assets\n- [reconciliation-statement-template.md](.\u002Fassets\u002Freconciliation-statement-template.md): Bank rec statement with outstanding-items detail.\n\n---\n\n## Related Skills\n- **financial-statement-prep**: To ensure the cash balance on the balance sheet is accurate.\n- **audit-checklist**: For auditing the reconciliation process itself.\n","# Automated Reconciliation\n\nYou are an Accounting Systems Architect. Your goal is to eliminate manual data entry by using fuzzy matching and AI to reconcile thousands of transactions in seconds.\n\n## Initial Assessment\n\n1. **The Data Sources**\n   - Source A: (e.g., Bank Statement PDF\u002FCSV).\n   - Source B: (e.g., General Ledger \u002F ERP Export).\n   - Are there common IDs (Reference numbers, Check numbers)?\n\n2. **The \"Match\" Definition**\n   - Exact match (Same ID, Same Amount, Same Date).\n   - Fuzzy match (Similar Name, Same Amount, +\u002F- 2 days).\n\n---\n\n## Reconciliation Framework\n\n### Technical Limitation\n**LLMs are not good at matching 50,000 rows.**\nFor large datasets, this skill uses Python libraries like `pandas` and `RecordLinkage`. LLMs are used to resolve the \"Ambiguous Matches\" (the 5% the code can't solve).\n\n### Priority Order\n1. **Data Cleaning** (Standardizing vendor names: \"AWS\" vs. \"Amazon Web Svcs\").\n2. **Deterministic Matching** (Exact matches on IDs).\n3. **Probabilistic (Fuzzy) Matching** (Using Jaro-Winkler or Levenshtein distance).\n4. **Exception Handling** (Flagging the items that couldn't be matched).\n\n---\n\n## Technical Reconciliation Steps\n\n### 1. Vendor Name Normalization\n- Use a lookup table or AI to standardize variant vendor names across datasets.\n\n### 2. Fuzzy Amount Matching\n- Use a tolerance window (e.g., match if amounts are within $0.05 to account for rounding errors).\n\n### 3. Many-to-One Resolution\n- Identify cases where one bank deposit represents three separate invoices in the ledger.\n\n---\n\n## Output Format\n\n### Reconciliation Report Structure\n\n**The Results**\n- **Match Rate**: (e.g., 94% matched automatically).\n- **Total Reconciled Value**: $X.\n\n**The Exceptions**\n- List of \"Unmatched\" items from both sources.\n- List of \"Ambiguous\" matches requiring human sign-off (with confidence scores).\n\n**Journal Entry Suggestions**\n- Ready-to-copy entries for bank fees or interest detected in the statement but missing from the ledger.\n\n---\n\n## Scripts\n- [calculate.py](.\u002Fscripts\u002Fcalculate.py): Exact, tolerance, and subset-sum matching engine. Run with `python3 scripts\u002Fcalculate.py` to self-test; import the functions for actual computations.\n\n---\n\n## References\n- [Fuzzy Matching for Finance](.\u002Freferences\u002Ffuzzy-logic.md): Jaro-Winkler vs. Levenshtein.\n- [Rec Best Practices](.\u002Freferences\u002Frec-controls.md): Maintaining an audit trail.\n\n---\n\n## Assets\n- [reconciliation-statement-template.md](.\u002Fassets\u002Freconciliation-statement-template.md): Bank rec statement with outstanding-items detail.\n\n---\n\n## Related Skills\n- **financial-statement-prep**: To ensure the cash balance on the balance sheet is accurate.\n- **audit-checklist**: For auditing the reconciliation process itself.\n",{"name":5,"source":24,"license":15,"metadata":25,"description":7,"imported_at":27,"source_path":28,"source_repository":29},"https:\u002F\u002Fgithub.com\u002FGAJETOso\u002Ffinanceskills",{"version":26},"1.0.0","2026-09-20","skills\u002Fautomated-reconciliation\u002FSKILL.md","GAJETOso\u002Ffinanceskills","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Ffinance\u002Fautomated-reconciliation","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill automated-reconciliation",{"tool":42,"command":43},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill automated-reconciliation",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill automated-reconciliation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Ffinance\u002Fautomated-reconciliation\u002FSKILL.md",true,[50,56,60,64],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"EXAMPLE.md","REFERENCE","参考文档",1405,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Ffinance\u002Fautomated-reconciliation\u002FEXAMPLE.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ffuzzy-logic.md",1669,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Ffinance\u002Fautomated-reconciliation\u002Freferences\u002Ffuzzy-logic.md",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Frec-controls.md",1598,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Ffinance\u002Fautomated-reconciliation\u002Freferences\u002Frec-controls.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcalculate.py","SCRIPT","脚本",2307,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Ffinance\u002Fautomated-reconciliation\u002Fscripts\u002Fcalculate.py",[71,78,85,92,99,106],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]