{
  "schemaVersion": "1.0",
  "item": {
    "slug": "data-reconciliation-exceptions",
    "name": "Data quality & reconciliation with exception",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/KOwl64/data-reconciliation-exceptions",
    "canonicalUrl": "https://clawhub.ai/KOwl64/data-reconciliation-exceptions",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/data-reconciliation-exceptions",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=data-reconciliation-exceptions",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/matching-rules.md",
      "assets/exceptions-report-template.csv"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/data-reconciliation-exceptions"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/data-reconciliation-exceptions",
    "agentPageUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions/agent",
    "manifestUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "PURPOSE",
        "body": "Reconciles data sources using stable identifiers (Pay Number, driving licence, driver card, and driver qualification card numbers), producing exception reports and “no silent failure” checks."
      },
      {
        "title": "WHEN TO USE",
        "body": "TRIGGERS:\n\nReconcile these two data sources and produce an exceptions report with reasons.\nMatch names and payroll numbers across files and flag anything that does not join.\nBuild a ‘no silent failure’ check that stops the pipeline if counts do not match.\nCreate a weekly variance report for missing records, duplicates, and date gaps.\nDesign a data quality scorecard with thresholds and red flags.\n\n\nDO NOT USE WHEN…\n\nYou need open-ended fuzzy matching without acceptance criteria.\nThere are no stable identifiers in any source."
      },
      {
        "title": "INPUTS",
        "body": "REQUIRED:\n\nAt least two datasets (CSV/XLSX) with Pay Number and/or driver document numbers.\nWhich fields must match (e.g., Name, expiry date).\n\n\nOPTIONAL:\n\nNormalization rules (case, spaces, punctuation).\nThresholds for gates/scorecard (max % missing, etc.).\n\n\nEXAMPLES:\n\nPayroll export + compliance register\nTwo weekly exports from different systems"
      },
      {
        "title": "OUTPUTS",
        "body": "Reconciliation plan (matching rules, normalization, join strategy).\nExceptions report spec (CSV columns + reason codes) and variance checks.\nOptional artifacts: assets/exceptions-report-template.csv + references/matching-rules.md.\nSuccess = every record is categorized (matched/missing/duplicate/mismatch/invalid) with an explicit reason; pipelines stop on anomalies."
      },
      {
        "title": "WORKFLOW",
        "body": "Confirm sources and key priority (Pay Number → Driver Card → Driving Licence → DQC).\nNormalize columns:\n\ntrim spaces; standardize case; strip common punctuation for document numbers.\n\n\nValidate keys:\n\nflag blanks/invalid formats; identify duplicates per source.\n\n\nJoin:\n\nexact join on Pay Number; then attempt secondary joins only for remaining unmatched items.\n\n\nProduce exception categories with reasons:\n\nMissing in A/B, Duplicate key, Field mismatch, Invalid key.\n\n\n“No silent failure” gates:\n\ncounts within tolerance; unmatched rate below threshold; duplicate spikes flagged.\n\n\nSTOP AND ASK THE USER if:\n\ncolumns are not mapped,\nmultiple competing IDs exist with no priority,\nexpected tolerances are unspecified."
      },
      {
        "title": "OUTPUT FORMAT",
        "body": "exception_type,reason,source_a_id,source_b_id,pay_number,name,field,source_a_value,source_b_value\n\nReason codes: MISSING_IN_A, MISSING_IN_B, MISMATCH, DUPLICATE_KEY, INVALID_KEY."
      },
      {
        "title": "SAFETY & EDGE CASES",
        "body": "Read-only by default; don’t auto-edit source data. Route exceptions to review.\nDeterministic matching rules first; avoid fuzzy matching unless explicitly requested.\nAlways produce an exceptions report; never drop unmatched rows."
      },
      {
        "title": "EXAMPLES",
        "body": "Input: “Payroll vs compliance; match by Pay Number; flag name mismatch.”\nOutput: join plan + mismatch reasons + exceptions report schema.\n\n\nInput: “Some rows have blank Pay Number.”\nOutput: secondary key matching + invalid-key exceptions for truly unmatchable rows."
      }
    ],
    "body": "Data quality & reconciliation with exception reporting and no silent failure\nPURPOSE\n\nReconciles data sources using stable identifiers (Pay Number, driving licence, driver card, and driver qualification card numbers), producing exception reports and “no silent failure” checks.\n\nWHEN TO USE\nTRIGGERS:\nReconcile these two data sources and produce an exceptions report with reasons.\nMatch names and payroll numbers across files and flag anything that does not join.\nBuild a ‘no silent failure’ check that stops the pipeline if counts do not match.\nCreate a weekly variance report for missing records, duplicates, and date gaps.\nDesign a data quality scorecard with thresholds and red flags.\nDO NOT USE WHEN…\nYou need open-ended fuzzy matching without acceptance criteria.\nThere are no stable identifiers in any source.\nINPUTS\nREQUIRED:\nAt least two datasets (CSV/XLSX) with Pay Number and/or driver document numbers.\nWhich fields must match (e.g., Name, expiry date).\nOPTIONAL:\nNormalization rules (case, spaces, punctuation).\nThresholds for gates/scorecard (max % missing, etc.).\nEXAMPLES:\nPayroll export + compliance register\nTwo weekly exports from different systems\nOUTPUTS\nReconciliation plan (matching rules, normalization, join strategy).\nExceptions report spec (CSV columns + reason codes) and variance checks.\nOptional artifacts: assets/exceptions-report-template.csv + references/matching-rules.md. Success = every record is categorized (matched/missing/duplicate/mismatch/invalid) with an explicit reason; pipelines stop on anomalies.\nWORKFLOW\nConfirm sources and key priority (Pay Number → Driver Card → Driving Licence → DQC).\nNormalize columns:\ntrim spaces; standardize case; strip common punctuation for document numbers.\nValidate keys:\nflag blanks/invalid formats; identify duplicates per source.\nJoin:\nexact join on Pay Number; then attempt secondary joins only for remaining unmatched items.\nProduce exception categories with reasons:\nMissing in A/B, Duplicate key, Field mismatch, Invalid key.\n“No silent failure” gates:\ncounts within tolerance; unmatched rate below threshold; duplicate spikes flagged.\nSTOP AND ASK THE USER if:\ncolumns are not mapped,\nmultiple competing IDs exist with no priority,\nexpected tolerances are unspecified.\nOUTPUT FORMAT\nexception_type,reason,source_a_id,source_b_id,pay_number,name,field,source_a_value,source_b_value\n\n\nReason codes: MISSING_IN_A, MISSING_IN_B, MISMATCH, DUPLICATE_KEY, INVALID_KEY.\n\nSAFETY & EDGE CASES\nRead-only by default; don’t auto-edit source data. Route exceptions to review.\nDeterministic matching rules first; avoid fuzzy matching unless explicitly requested.\nAlways produce an exceptions report; never drop unmatched rows.\nEXAMPLES\n\nInput: “Payroll vs compliance; match by Pay Number; flag name mismatch.”\nOutput: join plan + mismatch reasons + exceptions report schema.\n\nInput: “Some rows have blank Pay Number.”\nOutput: secondary key matching + invalid-key exceptions for truly unmatchable rows."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/KOwl64/data-reconciliation-exceptions",
    "publisherUrl": "https://clawhub.ai/KOwl64/data-reconciliation-exceptions",
    "owner": "KOwl64",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions",
    "downloadUrl": "https://openagent3.xyz/downloads/data-reconciliation-exceptions",
    "agentUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions/agent",
    "manifestUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/data-reconciliation-exceptions/agent.md"
  }
}