spreadsheet-analysis

spreadsheet-analysis is a skill for Claude Code, Codex from cass-2003/local-workflow-skill. It costs 58 tokens per session (1,531 once invoked), scanned A, original, MIT.

A spreadsheet-processing aid for Excel, XLSX, XLS, CSV, and TSV files. It covers cleaning, formulas, summaries, charts, validation, and checks that make results traceable.

In plain words
What is it for?
Use it to clean and combine sheets, build formulas and pivot summaries, create charts, check financial or operational data, and export verified workbooks.
Why use it?
It reduces errors from inconsistent types, duplicates, missing values, broken formulas, and unexplained spreadsheet changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to clean and combine sheets, build formulas and pivot summaries, create charts, check financial or operational data, and export verified workbooks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cass-2003/local-workflow-skill/spreadsheet-analysis
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 cass-2003/local-workflow-skill --skill spreadsheet-analysis
Clone the repo
git clone --depth 1 https://github.com/cass-2003/local-workflow-skill

Made for: Claude Code, Codex.

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 spreadsheet-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/spreadsheet-analysis/github.svg)](https://agentmods.dev/skills/cass-2003/local-workflow-skill/spreadsheet-analysis)
Your own site
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/spreadsheet-analysis"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/spreadsheet-analysis/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 spreadsheet-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/spreadsheet-analysis"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/spreadsheet-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,531 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.
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 $0.00058 $0.01531
Opus 5 $0.00029 $0.00766
Sonnet 5 $0.00012 $0.00306
Haiku 4.5 $0.00006 $0.00153

Measured 6d ago against content hash 1f011e57c4c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

spreadsheet-analysis 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 6d 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.

skills/data-analysis/community/spreadsheet-analysis/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spreadsheet Analysis

Spreadsheet Analysis 负责把 Excel、xlsx、csv 和多 sheet 表格处理成可复核的数据结果。目标是让来源、清洗、公式、透视、图表、异常和导出结果都能追溯。

适用范围

  • Excel、xlsx、xls、csv、tsv、电子表格、运营表、财务表、销售表、库存表和对账表。
  • 数据清洗、去重、拆分合并、类型转换、空值处理、异常检查和多 sheet 汇总。
  • 公式、透视表、图表、条件格式、数据验证、下拉选项、命名区域和保护工作表。
  • 指标口径核对、同比环比、分组统计、异常值、重复项、缺失项、跨表一致性和交付说明。

不适用范围

  • 大数据 ETL、数据仓库、调度平台、Spark/Flink/dbt/Airflow;这些走 data-engineering。
  • 数据库 schema、SQL 查询、索引、迁移和 Redis;这些走 database-engineering。
  • 只读学习、项目上手、仅识别文件扩展名,没有清洗、分析、生成或校验动作。

铁律

  1. 表格结论必须能回到原始数据、筛选条件、清洗步骤、公式和版本。
  2. 不覆盖原始 sheet;清洗、分析和输出应分层,必要时保留 raw、clean、analysis、summary。
  3. 金额、日期、百分比、ID、手机号、订单号和邮编必须先定类型;不能让 Excel 自动格式化误改。
  4. 公式要可读、可复制、可审计;跨 sheet 引用和绝对/相对引用必须明确。
  5. 透视和图表必须写清数据范围、刷新方式、过滤条件、单位和口径。
  6. 运营财务异常不能只看单个单元格;要检查重复、缺失、负数、极值、口径变化和跨表对不齐。
  7. 涉及个人信息、财务数据和客户名单时,输出样例、截图和日志必须脱敏。

强制流程

  1. 锁定目标:确认要回答的问题、输入文件、输出格式、指标口径、时间范围和验收方式。
  2. 保护原始:识别 sheet、列名、行数、编码、分隔符、隐藏列、合并单元格、公式和外部链接。
  3. 数据画像:检查类型、空值、重复、异常值、日期格式、金额单位、枚举、主键和跨表关系。
  4. 清洗转换:记录每一步去重、拆列、合并、过滤、映射、补全和类型转换规则。
  5. 分析汇总:用公式、透视、分组、图表或脚本计算;每个指标保留口径和来源列。
  6. 异常审计:对重复、缺失、负数、超阈值、跨表不一致、公式错误和手工覆盖做标记。
  7. 交付校验:打开或渲染检查工作簿,确认公式、图表、条件格式、数据验证和导出文件可用。
  8. 报告结果:输出关键结论、处理步骤、异常清单、未确认口径和验证证据。

场景执行卡

验收证据模板

  • xlsx/xls/csv 输出必须真实打开或用兼容工具加载;记录是否触发修复提示、公式错误、外链警告、宏提示、保护提示。
  • 计算验收要检查公式缓存、手动/自动计算模式、#VALUE!/#REF!/#N/A、透视缓存刷新、图表数据范围和控制合计。
  • raw/clean/analysis/output 要能对账:行数变化、主键唯一、金额合计、异常计数、抽样记录和处理步骤 sheet/说明文件。
  • 导出报告要记录 PDF/图片范围、打印区域、冻结窗格、筛选状态、隐藏行列和敏感字段脱敏结果。

清洗与汇总

  • 查:编码、表头、数据范围、隐藏行列、合并单元格、空行、重复主键和类型漂移。
  • 做:保留 raw,生成 clean;所有清洗规则写进说明或单独 sheet。
  • 验:行数变化、金额合计、主键唯一、空值数量和抽样记录。

透视与图表

  • 查:维度、指标、筛选条件、时间粒度、单位、排序和图表目的。
  • 做:透视表用于可交互汇总,图表用于表达趋势、构成、排名或异常。
  • 验:刷新范围正确,图例和单位明确,筛选条件没有遗漏。

运营财务异常检查

  • 查:订单号、流水号、金额、税费、退款、时间、渠道、客户和状态。
  • 做:按主键、时间、金额和状态做跨表核对;异常分级并保留原始行引用。
  • 验:重复、缺失、负数、超额、跨表差异和公式错误都有计数。

复杂对象与低级错误

  • CSV 要检查编码、BOM、分隔符、换行、引号转义和前导零;日期要检查 1900/1904、时区、locale 和文本日期。
  • 金额和 ID 要防止千分位/小数点漂移、长数字科学计数、手机号/订单号被截断、百分比被重复乘除。
  • 复杂对象包括透视表、切片器、图表、条件格式、数据验证、命名区域、保护工作表、批注/线程批注、外部链接和宏;不能静默破坏。
  • Google Sheets 任务必须补账号权限、公式 locale、导入导出格式、共享范围、筛选视图、保护范围和版本历史验证。

Read the full file on GitHub · 88 lines

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. 6d ago First seen · 88 lines · 58 tokens per session scan A 1f011e57c4c6

Subscribe to this mod's changes

spreadsheet-analysis is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,531 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.