python-office is a Python library that provides ready-to-use modules for automating office and media tasks such as PDF, Word, Excel, PowerPoint, email, WeChat, images, video, and OCR. It is for people who want to automate common work activities with short Python calls, including users with little Python experience. Its catalogue skills expose the library's individual automation areas to coding agents.
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 CoderWanFeng/python-office --skill excel_diffgit clone --depth 1 https://github.com/CoderWanFeng/python-officeWrote 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/coderwanfeng/python-office/excel_diff)<a href="https://agentmods.dev/skills/coderwanfeng/python-office/excel_diff"><img src="https://agentmods.dev/badge/skills/coderwanfeng/python-office/excel_diff/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/coderwanfeng/python-office/excel_diff"><img src="https://agentmods.dev/badge/skills/coderwanfeng/python-office/excel_diff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.00583 |
| Opus 5.5 | $0.00025 | $0.00233 |
| Sonnet 5.5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
excel_diff 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 12d 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_diff Skill
比对两份 Excel,输出单元格级差异,可导出差异表
功能描述
把两份 Excel 的同一张工作表做对比,返回每个变化的单元格、新增行、删除行和表头变化。 支持两种模式:按行号逐格比对(适合行顺序固定的表),或按主键配对后再比对 (适合行顺序会变、但每行有唯一编号的表)。
所属分类
skills/excel/excel_diff/
调用方式
from skills.excel import excel_diff
excel_diff(
before_path='上周报表.xlsx',
after_path='本周报表.xlsx',
key_column='订单号',
)
参数说明
| 参数 | 类型 | 必填 | 默认值 | 说明 |
|---|---|---|---|---|
before_path |
str | 是 | - | 变更前的 Excel 路径 |
after_path |
str | 是 | - | 变更后的 Excel 路径 |
sheet_name |
str | 否 | None |
工作表名,默认取第一个 |
key_column |
str | 否 | None |
主键列名;指定后按主键配对行 |
ignore_case |
bool | 否 | False |
文本比较是否忽略大小写 |
output_path |
str | 否 | None |
差异表输出路径,指定后写出 .xlsx |
返回值
dict,包含 mode、sheet、header、summary、changes、added_rows、
removed_rows、output_path 八个键。summary 中的 identical 表示两份表是否完全一致。
使用示例
from skills.excel import excel_diff
result = excel_diff('v1.xlsx', 'v2.xlsx', key_column='编号', output_path='差异.xlsx')
print(result['summary'])
for item in result['changes']:
print(item['key'], item['column'], item['before'], '->', item['after'])
原始函数
contributors/my12yyds/excel_diff.py
What ships with it
1 file 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.
- 12d ago First seen · 62 lines · 62 tokens per session scan A 4f581587beda
excel_diff is a skill published in the GitHub repository CoderWanFeng/python-office (1,371 stars, last pushed 10d ago), licensed Apache-2.0. It adds 62 tokens to every session and 583 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-27.
excel_diff compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| excel_diffCoderWanFeng/python-office | Skill | 1.4k | 10d ago | Apache-2.0 | A | 62 | Claude Code, Codex |
| xlsxHKUDS/DeepTutor | Skill | 57k | yesterday | Apache-2.0 | A | 88 | Claude Code, Codex |
| officecli-financial-modeliOfficeAI/OfficeCLI | Skill | 33k | 9d ago | Apache-2.0 | A | 222 | Claude Code, Codex |
| officecliiOfficeAI/OfficeCLI | Skill | 33k | 9d ago | Apache-2.0 | A | 56 | Claude Code, Codex |
| xberg-extracting-tablesxberg-io/xberg | Skill | 9.6k | today | MIT | A | 36 | Claude Code |
| cli-anything-wpsyb2460/harness-anything | Skill | 3.0k | 1mo ago | MIT | A | 37 | Claude Code, Codex |
| officecli-xlsxiOfficeAI/OfficeCLI | Skill | 33k | 9d ago | Apache-2.0 | C | 119 | Claude Code, Codex |