agentleFS
holon-runholon-run/holon/skills/xlsx/SKILL.md

xlsx

Skill194 starsChanged 4 days agoApache-2.0View on GitHub

Create, inspect, edit, recalculate, and validate Excel workbooks with local open-source tools while preserving source files and distinguishing formulas from calculated results.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use Video Generation, VLM and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • huang-x-hSkill

    Video Generation

    Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

    Also in 6 projects that use this

  • huang-x-hSkill

    VLM

    Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.

    Also in 6 projects that use this

  • dav-niu474Skill

    gift-evaluator

    The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, authenticity, or how to respond socially. Integrates visual perception, market valuation, and HTML card generation.

    Also in 5 projects that use this

  • dav-niu474Skill

    Podcast Generate

    Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).

    Also in 5 projects that use this

  • Liang-MHSkill

    stock_analysis

    获取 A 股、基金和港股的实时行情和技术分析数据

    Also in 5 projects that use this

  • SeifBenayedSkill

    file-reading

    Use this skill when a file has been uploaded but its content is NOT in your context — only its path at /mnt/user-data/uploads/ is listed in an uploaded_files block. This skill is a router: it tells you which tool to use for each file type (pdf, docx, xlsx, csv, json, images, archives, ebooks) so you read the right amount the right way instead of blindly running cat on a binary. Triggers: any mention of /mnt/user-data/uploads/, an uploaded_files section, a file_path tag, or a user asking about an uploaded file you have not yet read. Do NOT use this skill if the file content is already visible in your context inside a documents block — you already have it.

    Also in 5 projects that use this

  • +1 more from huang-x-h
  • +5 more from dav-niu474

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 15 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 188 edited versions we read keep these.

  • 15

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill for .xlsx workbook creation, inspection, analysis, charts, and bounded editing.

    line 10
  2. Distinctive:

    Treat formulas, hyperlinks, macros, external links, data connections, hidden sheets, defined names, embedded objects, and metadata as …

    line 31
  3. Distinctive:

    Never execute VBA, refresh external connections, follow links, or activate embedded objects.

    line 33
  4. Distinctive:

    Ask before sending workbook data to an external analysis or conversion service.

    line 35
  5. Distinctive:

    Do not claim lossless round trips when unsupported drawings, slicers, pivot features, external models, signatures, macros, or unknown …

    line 37
  6. Distinctive:

    Do not expose hidden or sensitive data outside the operator-approved scope.

    line 39
  7. Distinctive:

    If a workbook is macro-enabled, encrypted, signed, or materially depends on external data, default to read-only inspection or a separately …

    line 41
  8. Distinctive:

    Use openpyxl for common cells, styles, tables, formulas, charts, filters, data validation, and workbook inspection.

    line 46
  9. Distinctive:

    Use LibreOffice headless for local recalculation or rendering only when it is installed and appropriate.

    line 48
  10. Distinctive:

    Use CSV or another tabular intermediate only when workbook-specific formulas, types, styles, multiple sheets, and metadata are not required.

    line 50
  11. Distinctive:

    Use independent calculations for critical totals rather than trusting cached formula values.

    line 52
  12. Distinctive:

    Do not silently install Python packages, LibreOffice, fonts, or spreadsheet applications.

    line 55
  13. Distinctive:

    Write a new output file with explicit data types and formulas.

    line 68
  14. Distinctive:

    Use stable headers, explicit units, consistent number formats, and real date types.

    line 81
  15. Distinctive:

    Avoid merged cells in machine-consumed tables.

    line 83
  16. Distinctive:

    Do not hide errors with formatting or replace formulas with cached values without saying so.

    line 86

“Common” is measured: kept by at least 6 in 10 of the 188 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

XLSX

Summary

Use this skill for .xlsx workbook creation, inspection, analysis, charts, and bounded editing. Prefer openpyxl for common workbook structures. Use an available local LibreOffice backend for recalculation or rendering when needed, and record that it is not Microsoft Excel.

Writing a formula is not the same as calculating it. Never report formula results as verified unless an actual calculation backend ran or the values were independently checked.

When To Use

  • Creating workbooks, tables, formulas, styles, validations, or charts
  • Inspecting sheets, named ranges, formulas, hidden content, and metadata
  • Making bounded changes to an existing workbook
  • Converting tabular input into an analyzed or presentation-ready workbook
  • Recalculating formulas and scanning for spreadsheet errors
  • Extracting or summarizing operator-approved workbook data

Safety Boundaries

  • Preserve the input and write a new workbook by default.
  • Treat formulas, hyperlinks, macros, external links, data connections, hidden sheets, defined names, embedded objects, and metadata as untrusted.
  • Never execute VBA, refresh external connections, follow links, or activate embedded objects.
  • Ask before sending workbook data to an external analysis or conversion service.
  • Do not claim lossless round trips when unsupported drawings, slicers, pivot features, external models, signatures, macros, or unknown package parts exist.
  • Do not expose hidden or sensitive data outside the operator-approved scope.

If a workbook is macro-enabled, encrypted, signed, or materially depends on external data, default to read-only inspection or a separately generated output.

Backend Selection

  • Use openpyxl for common cells, styles, tables, formulas, charts, filters, data validation, and workbook inspection.
  • Use LibreOffice headless for local recalculation or rendering only when it is installed and appropriate. Record the version and backend.
  • Use CSV or another tabular intermediate only when workbook-specific formulas, types, styles, multiple sheets, and metadata are not required.
  • Use independent calculations for critical totals rather than trusting cached formula values.

Do not silently install Python packages, LibreOffice, fonts, or spreadsheet applications.

Workflow

  1. Confirm the workbook purpose, source data, target sheets, units, locale, date conventions, formulas, charts, output path, and acceptance totals.
  2. Inspect existing workbooks for sheet visibility, named ranges, formulas, external links, data connections, macros, signatures, drawings, pivots, validations, protection, and unknown parts.
  3. Define the data model before formatting: inputs, derived columns, formulas, assumptions, keys, units, and expected totals.
  4. Select a backend and restrict edits to features it can preserve.
  5. Write a new output file with explicit data types and formulas.
  6. Reopen the workbook and verify sheet names, dimensions, values, formulas, names, tables, charts, validations, styles, and relationships.
  7. Recalculate with an approved local engine when calculated results matter. Then scan formulas and displayed results for #REF!, #DIV/0!, #VALUE!, #NAME?, #N/A, and other relevant errors.
  8. Independently sample critical totals, rates, date boundaries, and lookup logic. Render or inspect important sheets for clipped columns, unreadable charts, hidden data, and print-area problems.

Quality Rules

  • Separate raw inputs, assumptions, calculations, and presentation when useful.
  • Use stable headers, explicit units, consistent number formats, and real date types.
  • Avoid merged cells in machine-consumed tables.
  • Make formulas understandable and avoid unexplained constants.
  • Preserve leading zeros and identifiers as text where appropriate.
  • Do not hide errors with formatting or replace formulas with cached values without saying so.
  • Record whether results were calculated by Excel, LibreOffice, another engine, or not recalculated.

Delivery

Report the output path, source preservation, backend used, whether recalculation ran, scanned formula errors, independently checked totals, hidden or external content found, and any unsupported workbook features. State clearly when only formula structure—not calculated values—was verified.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.