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 YuYY2004/excel-skills --skill excel-deletegit clone --depth 1 https://github.com/YuYY2004/excel-skillsWrote 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/yuyy2004/excel-skills/excel-delete)<a href="https://agentmods.dev/skills/yuyy2004/excel-skills/excel-delete"><img src="https://agentmods.dev/badge/skills/yuyy2004/excel-skills/excel-delete/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/yuyy2004/excel-skills/excel-delete"><img src="https://agentmods.dev/badge/skills/yuyy2004/excel-skills/excel-delete.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 | $0.00188 | $0.03968 |
| Opus 5 | $0.00094 | $0.01984 |
| Sonnet 5 | $0.00038 | $0.00794 |
| Haiku 4.5 | $0.00019 | $0.00397 |
Grade A, and why
excel-delete 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill follows [[excel-safe-workflow]] four-step method. Must complete Requirement Parsing→Scout→Plan before execution, and Verify after. Must check formula dependencies before deletion. 本技能遵循 [[excel-safe-workflow]] 四步法。执行前必须完成 需求解析→勘察→规划,执行后必须验证。删除前必须检查公式依赖。
Excel Safe Delete (Row & Column) / Excel 安全删除(行列通用)
核心原则
| 模式 | 引擎 | 原因 |
|---|---|---|
| 行删除 | XML 直接操作 | 快 10 倍,格式/公式无损 |
| 列删除 | openpyxl delete_cols() |
列删除需逐行移除 cell,XML 太复杂 |
第零步:需求解析
自动识别删除类型
| 用户说 | 判定 |
|---|---|
| "删除列""去掉列""移除列""E列""第3列""空列" | → 列模式 |
| "删除行""去掉行""移除行""第5行""空行" | → 行模式 |
解析示例
| 用户说 | 提取 |
|---|---|
| "把E列删掉" | 列模式, 目标=列E |
| "删除第5行到第10行" | 行模式, 目标=[5,6,7,8,9,10] |
| "清理所有空行" | 行模式, 自动扫描空行 |
| "删掉申请日那一列" | 列模式, 目标=申请日(勘察定位) |
第一步:勘察(含公式依赖检查)
import os, sys
sys.stdout.reconfigure(encoding='utf-8')
from openpyxl import load_workbook
FILE = '目标文件.xlsx'
size_mb = os.path.getsize(FILE) / 1024 / 1024
print(f'文件大小: {size_mb:.1f} MB')
wb = load_workbook(FILE)
ws = wb.active
print(f'工作表: {ws.title}, 行: {ws.max_row}, 列: {ws.max_column}')
# 展示结构
print('\n=== 表头 ===')
for col_idx in range(1, ws.max_column + 1):
h = ws.cell(row=1, column=col_idx).value
if h:
col_letter = chr(64 + col_idx) if col_idx <= 26 else f'col{col_idx}'
print(f' 列{col_idx} [{col_letter}]: {h}')
targets = [] # 列模式:列号列表;行模式:行号列表
# ⚠️ 关键:公式依赖检查
print('\n=== 公式依赖检查 ===')
wb2 = load_workbook(FILE, data_only=True)
ws2 = wb2.active
has_risk = False
if MODE == 'column':
for col_idx in range(1, ws.max_column + 1):
if col_idx in targets:
continue
for row_idx in range(1, min(50, ws.max_row + 1)):
v_raw = ws.cell(row=row_idx, column=col_idx).value
if v_raw and isinstance(v_raw, str) and v_raw.startswith('='):
for tc in targets:
col_letter = chr(64 + tc) if tc <= 26 else ''
if col_letter and col_letter in v_raw:
print(f' ⚠️ 列{col_idx}行{row_idx}引用被删列{col_letter}: {v_raw[:60]}')
has_risk = True
elif MODE == 'row':
for col_idx in range(1, ws.max_column + 1):
for row_idx in range(1, min(50, ws.max_row + 1)):
if row_idx in targets:
continue
v_raw = ws.cell(row=row_idx, column=col_idx).value
if v_raw and isinstance(v_raw, str) and v_raw.startswith('='):
for tr in targets:
if str(tr) in v_raw:
print(f' ⚠️ 列{col_idx}行{row_idx}引用被删行{tr}: {v_raw[:60]}')
has_risk = True
wb2.close()
if has_risk:
print('\n⚠️ 发现公式依赖,删除后可能产生 #REF! 错误。')
print(f'\n准备删除 {len(targets)} 个{MODE}: {targets}')
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.
- 9d ago First seen · 375 lines · 188 tokens per session scan A 0299e85e9cff
excel-delete is a skill published in the GitHub repository YuYY2004/excel-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 188 tokens to every session and 3,968 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
spreadsheets
Use when creating, reading, or fixing spreadsheets (.xlsx, .csv). Covers formulas, formatting, charts, data cleaning, and handling the messy real-world files that are not actually tabular.
Excel工具
A guide for using Excel tools to read, write, and recalculate spreadsheet files. It includes a rule for treating the first row as data when a spreadsheet has no column headings.
huashu-data-pro
All-in-one data analysis and productivity assistant. Covers end-to-end workflows for data processing, analytical insights, report writing, PPT creation, and data visualisation. Always approaches tasks from an expert perspective — thinks one step ahead for the user. Proactively confirms with the user when uncertain.…
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…
thinkcell
Generate, update, and automate think-cell charts and elements in PowerPoint and Excel. Use ANY time the user mentions think-cell, thinkcell, or .ppttc files, or asks to create/update PowerPoint charts following think-cell conventions (waterfall, Mekko, stacked column, Gantt, Harvey ball, scatter/bubble, etc.) …
bug-report-writer
Converts rough notes, casual descriptions, console errors, or quick observations into professional, complete bug reports — exported as a formatted Excel (.xlsx) file ready for Excel, Google Sheets, Jira, or Azure DevOps. Use this skill whenever the user mentions: "write a bug report", "log a bug", "report this issue"…