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.
npx skills add nexus-research-lab/nexus --skill xlsxgit clone --depth 1 https://github.com/nexus-research-lab/nexusWrote 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.
[](https://agentmods.dev/skills/nexus-research-lab/nexus/xlsx)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/xlsx"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/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.
<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/xlsx"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/xlsx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.01054 |
| Opus 5 | $0.00050 | $0.00527 |
| Sonnet 5 | $0.00020 | $0.00211 |
| Haiku 4.5 | $0.00010 | $0.00105 |
Grade A, and why
xlsx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Excel 工作簿
| 任务 | 路径 |
|---|---|
| 快速读取 XLSX | 运行自带读取脚本，保留工作表、行列和公式信息 |
| 读取 CSV/TSV | 用 Python csv 或通用文本工具；保留原始字段类型约束 |
| 新建或编辑工作簿 | 用 openpyxl 处理公式、格式、表格和图表 |
| 大批量数据清洗 | 标准库足够时直接使用；确有需要再用 pandas |
旧版 .xls |
用 LibreOffice 转为 .xlsx，保留原件 |
工作契约
- 只读问题不保存、重算或导出工作簿。
- 写操作默认另存新文件；模板和既有格式优先于默认样式。
- 先直接使用当前环境。
import openpyxl失败且任务需要写文件时，取得用户同意后在隔离环境安装${CLAUDE_SKILL_DIR}/requirements.txt，不要静默修改系统 Python。
读取
python3 "${CLAUDE_SKILL_DIR}/scripts/read_spreadsheet.py" "<input.xlsx>"
python3 "${CLAUDE_SKILL_DIR}/scripts/read_spreadsheet.py" "<input.xlsx>" --sheet "<sheet-name>" --max-rows 1000 --max-columns 100
python3 "${CLAUDE_SKILL_DIR}/scripts/read_spreadsheet.py" "<input.xlsx>" --output "<new-output.md>"
脚本同时显示公式文本和文件内缓存值。关键结论要定位到工作表与单元格，并沿公式引用核对输入； 缓存可能过期，不能把它当成刚刚重算的结果。
创建与编辑
在 workspace 或临时目录写一个可重复运行的短 Python 脚本，再用 openpyxl 输出文件。
- 数值、日期、百分比和货币写成真实类型，格式代码只负责显示；ID、邮编等标识符才写文本。
- 派生结果使用可读公式并引用输入单元格，不把 Python 计算值或魔法数字写死在计算区。
- 跨表引用始终给工作表名加单引号，例如
='Assumptions'!B5；正确使用绝对和相对引用。 - 读取公式与缓存值时分别打开两次。绝不能保存以
data_only=True打开的工作簿，否则公式会丢失。 - 编辑时延续相邻格式、公式模式、条件格式、表格和图表范围；不要对成熟模板做全表重排。
.xlsm使用keep_vba=True，并保持宏格式输出。外部链接、透视表、切片器和高级图表可能在往返保存时变化， 只修改必要区域并明确验证范围。
完成条件
- 含公式时先在单独目录用 LibreOffice 重算，检查转换结果后再作为最终文件，不能直接覆盖未验证的源文件。
- 用读取脚本回读关键范围，确认公式仍存在、缓存值已更新，并扫描
#REF!、#DIV/0!、#VALUE!、#NAME?、#N/A等错误。 - 用 LibreOffice 导出 PDF 或工作表预览，检查每张非空工作表的标题、表头、关键数字、图表、分页和打印区域。
- 缺少 LibreOffice 时可以继续不依赖重算的读取；含公式的写任务必须说明结果尚未由表格引擎重算。
- 最终只交付用户要求的 XLSX/XLSM/CSV/TSV，不附带构建脚本和预览文件。
What ships with it
3 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.
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.
- 10d ago First seen · 69 lines · 100 tokens per session scan A fb1f55518dbd
xlsx is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 1,054 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
Google Workspace
Handle Google Docs, Sheets, Drive, and related Workspace tasks through the narrowest available API or browser workflow.
data-analysis
Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to…
xlsx
Read, edit, or create Microsoft Excel .xlsx workbooks. Trigger this skill whenever the user mentions a spreadsheet, .xlsx file, workbook, sheet, formula, pivot table, or asks to extract tabular data, modify a sheet, or build a workbook from rows. Three execution paths: structured inspection, in-place cell edits, and…
meta-knowledge-base-bootstrap
Bootstrap a domain knowledge base from a single seed (URL / PDF path / git repo / free-text topic): classify source → ingest with the right tool → persist to memory + xlsx index.
meta-multi-format-export-pack
From one piece of source content, render four deliverables: .docx report, .pptx slides, .xlsx data, and an HTML/PDF public version.
meta-spreadsheet-insight
Turn an Excel workbook into business insight: structured read → trend/anomaly summary → write back to a new 'Insights' sheet → persist KPIs to memory.