xlsx

xlsx is a skill for Claude Code from HybridAIOne/hybridclaw. It costs 61 tokens per session (1,543 once invoked), scanned A, original, MIT.

A guide for creating, editing, inspecting, and analyzing Excel .xlsx workbooks and turning CSV or TSV tables into spreadsheets.

In plain words
What is it for?
Use it to build polished Excel files, import tabular data, reshape tables, inspect workbooks, and recalculate formulas.
Why use it?
It reduces manual spreadsheet work while keeping formulas and calculated results intact.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use it to build polished Excel files, import tabular data, reshape tables, inspect workbooks, and recalculate formulas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hybridaione/hybridclaw/xlsx
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HybridAIOne/hybridclaw --skill xlsx
Clone the repo
git clone --depth 1 https://github.com/HybridAIOne/hybridclaw

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for xlsx

README.md
[![agentmods](https://agentmods.dev/badge/skills/hybridaione/hybridclaw/xlsx/github.svg)](https://agentmods.dev/skills/hybridaione/hybridclaw/xlsx)
Your own site
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/xlsx"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/xlsx/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for xlsx

Your own site · 80×15
<a href="https://agentmods.dev/skills/hybridaione/hybridclaw/xlsx"><img src="https://agentmods.dev/badge/skills/hybridaione/hybridclaw/xlsx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01543
Opus 5 $0.00030 $0.00772
Sonnet 5 $0.00012 $0.00309
Haiku 4.5 $0.00006 $0.00154

Measured 8d ago against content hash 63b6c5a0f00f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

xlsx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/create_xlsx.cjs, scripts/import_delimited.cjs, scripts/recalc.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/xlsx/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XLSX

Use this skill whenever the user asks to create, inspect, analyze, or edit an .xlsx workbook, or to turn delimited tabular data into a polished .xlsx file.

Default Workflow

  1. For creation tasks, use skills/xlsx/scripts/create_xlsx.cjs to create a new workbook from headers/rows or JSON data. Fall back to a workspace .cjs script only when the bundled script cannot handle the requirement.
  2. Use skills/xlsx/scripts/import_delimited.cjs for messy CSV or TSV inputs when it saves time, then polish the workbook with xlsx-populate.
  3. Do table reshaping in plain JavaScript, then write the final workbook with xlsx-populate.
  4. After meaningful formula edits, run LibreOffice-backed recalculation when soffice is available so cached values and error checks are current.
  5. Save the finished workbook inside the workspace and return the .xlsx artifact.

Rules

  • Keep formulas as formulas. Do not replace derived cells with hardcoded values unless the user explicitly asks for static outputs.
  • Keep formulas dynamic. Put user-editable assumptions and drivers in dedicated cells or sheets instead of burying hardcoded constants inside long formulas.
  • xlsx-populate does not recalculate formulas. Keep formula strings intact and use LibreOffice-backed verification when cached values matter and the runtime says soffice is available.
  • After significant formula edits, run node skills/xlsx/scripts/recalc.cjs workbook.xlsx --json when soffice is available and fix any #REF!, #DIV/0!, #VALUE!, #N/A, or #NAME? errors before delivery.
  • Match existing workbook conventions exactly when editing templates or established models. Existing fonts, fills, borders, number formats, freeze panes, filters, named ranges, and color conventions override generic style rules.
  • For new user-facing workbooks without a template, use consistent professional styling: one readable font, explicit header styling, sensible widths, and alignment or freeze panes where they help readability.
  • Preserve existing worksheets, named ranges, freeze panes, filters, and formats unless the user asked for a redesign.
  • Prefer .xlsx as the final deliverable. Only fall back to CSV/TSV if the user explicitly wants a flat export.
  • Use number formats, explicit column widths, alignment, and header styling for user-facing workbooks.
  • For creation tasks ("make a spreadsheet", "create an xlsx"), always use skills/xlsx/scripts/create_xlsx.cjs first. Only write a custom workspace script if the user's requirements exceed what the bundled script supports.
  • Treat skills/ as bundled tooling. Do not write generated task scripts under skills/xlsx/ or skills/office/ for normal workbook jobs.
  • Put new helper scripts in workspace scripts/ or the workspace root, then run them from there. Use skills/xlsx/scripts/... and skills/office/... only as shipped helper commands.

Read the full file on GitHub · 130 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 130 lines · 61 tokens per session scan A 63b6c5a0f00f

Subscribe to this mod's changes

xlsx is a skill published in the GitHub repository HybridAIOne/hybridclaw (132 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,543 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories