fcakyon/claude-codex-settings / plugins/anthropic-office-skills/skills/xlsx
xlsx
VerifiedUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
scripts/office/validate.py
View on GitHub"""
Command line tool to validate Office document XML files against XSD schemas and tracked changes.
Usage:
python validate.py <path> [--original <original_file>] [--auto-repair] [--author NAME]
The first argument can be either:
- An unpacked directory containing the Office document XML files
- A packed Office file (.docx/.pptx/.xlsx or .dotx/.potx/.xltx template) which will be unpacked to a temp directory
Auto-repair fixes:
- paraId/durableId values that exceed OOXML limits
- Missing xml:space="preserve" on w:t elements with whitespace
"""
import argparse
import sys
import tempfile
import zipfile
from pathlib import Path
import defusedxml.ElementTree as ET
from defusedxml.common import DefusedXmlException
from helpers import OOXML_FAMILY, rezip, safe_extract
from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator
WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
def _fail(message: str):
print(f"Error: {message}", file=sys.stderr)
sys.exit(2)
def _has_tracked_changes(unpacked_dir: Path) -> bool:
document = unpacked_dir / "word" / "document.xml"
if not document.is_file():
return False
try:
root = ET.parse(document).getroot()
except (ET.ParseError, DefusedXmlException):
return False
tracked = {f"{{{WORD_NS}}}ins", f"{{{WORD_NS}}}del"}
return any(elem.tag in tracked for elem in root.iter())
def main():
parser = argparse.ArgumentParser(description="Validate Office document XML files")
parser.add_argument(
"path",
help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx or .dotx/.potx/.xltx)",
)
parser.add_argument(
"--original",
required=False,
default=None,
help="Path to original file (.docx/.pptx/.xlsx or .dotx/.potx/.xltx). If omitted, all XSD errors are reported and redlining validation is skipped.",
)
parser.add_argument(
"-v",
"--verbose",
action="store_true",
help="Enable verbose output",
)
parser.add_argument(
"--auto-repair",
action="store_true",
help="Automatically repair common issues (hex IDs, whitespace preservation). "
"Modifies the input in place: repairs to a packed file are written back to it.",
)
parser.add_argument(
"--author",
default=None,
help="The name you are redlining under. Passing it turns on the "
"tracked-change check: any text differing from --original without a "
"<w:ins>/<w:del> recording it is reported. Untracked edits carry no "
"author, so the check covers them whoever made them — the name marks "
"the run as redlining work and is not used to filter. Requires "
"--original; docx only.",
)
args = parser.parse_args()
if args.author is not None and not args.original:
_fail("--author requires --original")
path = Path(args.path)
if not path.exists():
_fail(f"{path} does not exist")
original_file = None
if args.original:
original_file = Path(args.original)
if not original_file.is_file():
_fail(f"{original_file} is not a file")
if original_file.suffix.lower() not in OOXML_FAMILY:
_fail(f"{original_file} must be one of: {', '.join(sorted(OOXML_FAMILY))}")
family = OOXML_FAMILY.get((original_file or path).suffix.lower())
if family is None:
_fail(
f"Cannot determine file type from {path}. Use --original or provide one of: {', '.join(sorted(OOXML_FAMILY))}."
)
if args.author is not None and family != "docx":
_fail(f"--author only applies to docx files, not {family}")
packed_file = None
temp_dir_ctx = None
if path.is_file() and path.suffix.lower() in OOXML_FAMILY:
packed_file = path
temp_dir_ctx = tempfile.TemporaryDirectory()
unpacked_dir = Path(temp_dir_ctx.name)
try:
with zipfile.ZipFile(path, "r") as zf:
safe_extract(zf, unpacked_dir)
except (zipfile.BadZipFile, ValueError, OSError) as e:
_fail(f"cannot unpack {path}: {e}")
else:
if not path.is_dir():
_fail(f"{path} is not a directory or Office file")
unpacked_dir = path
match family:
case "docx":
validators = [
DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
]
if args.author is not None:
validators.append(
RedliningValidator(unpacked_dir, original_file, verbose=args.verbose)
)
elif original_file and _has_tracked_changes(unpacked_dir):
print(
"Note: this document has tracked changes; they were not "
"checked against the original (pass --author to check)."
)
case "pptx":
validators = [
PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose),
]
case "xlsx":
exts = ", ".join(k for k, v in sorted(OOXML_FAMILY.items()) if v == "xlsx")
print(
f"No XSD schema validation is performed for xlsx-family files ({exts}). "
"For formula-error checking, use scripts/recalc.py instead."
)
sys.exit(0)
case _:
print(f"Error: Validation not supported for file type {family}")
sys.exit(1)
if args.auto_repair:
total_repairs = sum(v.repair() for v in validators)
if total_repairs:
print(f"Auto-repaired {total_repairs} issue(s)")
if packed_file is not None:
rezip(unpacked_dir, packed_file)
print(f"Wrote repaired file to {packed_file}")
success = all([v.validate() for v in validators])
if temp_dir_ctx is not None:
temp_dir_ctx.cleanup()
if success:
print("All validations PASSED!")
sys.exit(0 if success else 1)
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |