Excel / XLSX

安装解析

{
  "artifact": {
    "downloadUrl": "/api/v1/download?slug=excel-xlsx&version=1.0.2&ownerHandle=ivangdavila",
    "format": "zip",
    "generated": true,
    "kind": "skillArchive",
    "sha256": "2013e398ea5f86d53a6af8a412aae1f453190238cf1bfdd5a6c846fb163aeee4",
    "size": 8276
  },
  "owner": {
    "displayName": "Iván",
    "handle": "ivangdavila",
    "id": "7e964c28-026c-413c-9e4f-86a87b6ac0ca",
    "verified": false
  },
  "skill": {
    "displayName": "Excel / XLSX",
    "latestVersion": "1.0.2",
    "license": "MIT-0",
    "name": "excel-xlsx",
    "ownerHandle": "ivangdavila",
    "slug": "excel-xlsx",
    "stats": {
      "downloads": 75311,
      "installs": 2677,
      "stars": 288
    },
    "summary": "Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation...",
    "tags": [
      "integrations",
      "CSV"
    ],
    "type": "skill",
    "updatedAt": "2026-07-06T10:48:45.260Z"
  },
  "sourceHandoff": null,
  "version": {
    "checksum": null,
    "checksumAlgorithm": null,
    "id": "a0d021d5-a6f1-4dba-aef1-c02f861019cd",
    "publishedAt": "2026-03-11T15:32:46.499Z",
    "size": null,
    "version": "1.0.2",
    "artifactStorageKey": null,
    "changelog": "Tightened formula anchoring, recalculation, and model traceability after a stricter external spreadsheet audit.",
    "manifest": {
      "clawhub": {
        "tags": {
          "latest": "1.0.2"
        },
        "owner": "ivangdavila",
        "stats": {
          "stars": 288,
          "comments": 1,
          "installs": 2677,
          "versions": 3,
          "downloads": 75311
        },
        "topics": [
          "CSV"
        ],
        "categories": [
          "integrations"
        ]
      },
      "install": "openclaw skills install @ivangdavila/excel-xlsx"
    },
    "readme": "---\nname: Excel / XLSX\nslug: excel-xlsx\nversion: 1.0.2\nhomepage: https://clawic.com/skills/excel-xlsx\ndescription: \"Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation. Use when (1) the task is about Excel, `.xlsx`, `.xlsm`, `.xls`, `.csv`, or `.tsv`; (2) formulas, formatting, workbook structure, or compatibility matter; (3) the file must stay reliable after edits.\"\nchangelog: Tightened formula anchoring, recalculation, and model traceability after a stricter external spreadsheet audit.\nmetadata: {\"clawdbot\":{\"emoji\":\"📗\",\"requires\":{\"bins\":[]},\"os\":[\"linux\",\"darwin\",\"win32\"]}}\n---\n\n## When to Use\n\nUse when the main artifact is a Microsoft Excel workbook or spreadsheet file, especially when formulas, dates, formatting, merged cells, workbook structure, or cross-platform behavior matter.\n\n## Core Rules\n\n### 1. Choose the workflow by job, not by habit\n\n- Use `pandas` for analysis, reshaping, and CSV-like tasks.\n- Use `openpyxl` when formulas, styles, sheets, comments, merged cells, or workbook preservation matter.\n- Treat CSV as plain data exchange, not as an Excel feature-complete format.\n- Reading values, preserving a live workbook, and building a model from scratch are different spreadsheet jobs.\n\n### 2. Dates are serial numbers with legacy quirks\n\n- Excel stores dates as serial numbers, not real date objects.\n- The 1900 date system includes the false leap-day bug, and some workbooks use the 1904 system.\n- Time is fractional day data, so formatting and conversion both matter.\n- Date correctness is not enough if the number format still displays the wrong thing to the user.\n\n### 3. Keep calculations in Excel when the workbook should stay live\n\n- Write formulas into cells instead of hardcoding derived results from Python.\n- Use references to assumption cells instead of magic numbers inside formulas.\n- Cached formula values can be stale, so do not trust them blindly after edits.\n- Check copied formulas for wrong ranges, wrong sheets, and silent off-by-one drift before delivery.\n- Absolute and relative references are part of the logic, so copied formulas can be wrong even when they still \"work\".\n- Test new formulas on a few representative cells before filling them across a whole block.\n- Verify denominators, named ranges, and precedent cells before shipping formulas that depend on them.\n- A workbook should ship with zero formula errors, not with known `#REF!`, `#DIV/0!`, `#VALUE!`, `#NAME?`, or circular-reference fallout left for the user to fix.\n- For model-style work, document non-obvious hardcodes, assumptions, or source inputs in comments or nearby notes.\n\n### 4. Protect data types before Excel mangles them\n\n- Long identifiers, phone numbers, ZIP codes, and leading-zero values should usually be stored as text.\n- Excel silently truncates numeric precision past 15 digits.\n- Mixed text-number columns need explicit handling on read and on write.\n- Scientific notation, auto-parsed dates, and stripped leading zeros are common corruption, not cosmetic issues.\n\n### 5. Preserve workbook structure before changing content\n\n- Existing templates override generic styling advice.\n- Only the top-left cell of a merged range stores the value.\n- Hidden rows, hidden columns, named ranges, and external references can still affect formulas and outputs.\n- Shared strings, defined names, and sheet-level conventions can matter even when the visible cells look simple.\n- Match styles for newly filled cells instead of quietly introducing a new visual system.\n- If the workbook is a template, preserve sheet order, widths, freezes, filters, print settings, validations, and visual conventions unless the task explicitly changes them.\n- Conditional formatting, filters, print areas, and data validation often carry business meaning even when users only mention the numbers.\n- If there is no existing style guide and the file is a model, keep editable inputs visually distinguishable from formulas, but never override an established template to force a generic house style.\n\n### 6. Recalculate and review before delivery\n\n- Formula strings alone are not enough if the recipient needs current values.\n- `openpyxl` preserves formulas but does not calculate them.\n- Verify no `#REF!`, `#DIV/0!`, `#VALUE!`, `#NAME?`, or circular-reference fallout remains.\n- If layout matters, render or visually review the workbook before calling it finished.\n- Be careful with read modes: opening a workbook for values only and then saving can flatten formulas into static values.\n- If assumptions or hardcoded overrides must stay, make them obvious enough that the next editor can audit the workbook.\n\n### 7. Scale the workflow to the file size\n\n- Large workbooks can fail for boring reasons: memory spikes, padded empty rows, and slow full-sheet reads.\n- Use streaming or chunked reads when the file is big enough that loading everything at once becomes fragile.\n- Large-file workflows also need narrower reads, explicit dtypes, and sheet targeting to avoid accidental damage.\n\n## Common Traps\n\n- Type inference on read can leave numbers as text or convert IDs into damaged numeric values.\n- Column indexing varies across tools, so off-by-one mistakes are common in generated formulas.\n- Newlines in cells need wrapping to display correctly.\n- External references break easily when source files move.\n- Password protection in old Excel workflows is not serious security.\n- `.xlsm` can contain macros, and `.xls` remains a tighter legacy format.\n- Large files may need streaming reads or more careful memory handling.\n- Google Sheets and LibreOffice can reinterpret dates, formulas, or styling differently from Excel.\n- Dynamic array or newer Excel functions like `FILTER`, `XLOOKUP`, `SORT`, or `SEQUENCE` may fail or degrade in older viewers.\n- A workbook can look fine while still carrying stale cached values from a prior recalculation.\n- Saving the wrong workbook view can replace formulas with cached values and quietly destroy a live model.\n- Copying formulas without checking relative references can push one bad range across an entire block.\n- Hidden sheets, named ranges, validations, and merged areas often keep business logic that is invisible in a quick skim.\n- A workbook can appear numerically correct while still failing because filters, conditional formats, print settings, or data validation were stripped.\n- A workbook can be numerically correct and still fail visually because wrapped text, clipped labels, or narrow columns were never reviewed.\n\n## Related Skills\nInstall with `clawhub install <slug>` if user confirms:\n- `csv` — Plain-text tabular import and export workflows.\n- `data` — General data handling patterns before spreadsheet output.\n- `data-analysis` — Higher-level analysis that can feed workbook deliverables.\n\n## Feedback\n\n- If useful: `clawhub star excel-xlsx`\n- Stay updated: `clawhub sync`\n"
  }
}

版本