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 rojim666/SztuCode --skill excel-generationgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/excel-generation)<a href="https://agentmods.dev/skills/rojim666/sztucode/excel-generation"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/excel-generation/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/rojim666/sztucode/excel-generation"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/excel-generation.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 | $0.00118 | $0.04018 |
| Opus 5 | $0.00059 | $0.02009 |
| Sonnet 5 | $0.00024 | $0.00804 |
| Haiku 4.5 | $0.00012 | $0.00402 |
Grade A, and why
tencent-docs-sheet-generation scanned grade A with 1 finding 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 today.
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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.check_call([sys.executable, "-m", "pip", "install", "--quiet", "openpyxl>=3.1.0"]) How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excel 生成链路 (tencent-docs-sheet-generation)
本 skill 默认采用 openpyxl 直写 范式：主代理读取设计准则与范式后，直接编写 openpyxl 建表脚本一次性生成整份工作簿，不委派子代理。最终产出本地 xlsx 文件。
适用范围与拒绝条件
适用：
- 用户没有提供任何源
.xlsx/.xls/.csv文件 - 用户表达明确的"创建/生成/新建/做一份"等意图
- 目标产出是单个 xlsx 工作簿
- 支持将参考素材用于从零生成本地工作簿
- 支持随附本地 pdf/docx/pptx 附件作为内容参考（如"基于这份 pdf 帮我整理成 Excel"、"按这个 ppt 做一份汇总表"）
- 支持以在线文档（
docs.qq.com链接 /file_id，含跨品类的 doc / slide / 在线 sheet）作内容 / 样式参考（用 MCP 读取，见 Step 2）
不适用（routing 已过滤；如确实出现，告知用户并退出本 skill）：
- 用户实际给了源 xlsx / xls / csv（任何编辑场景） → 退出，让 routing 重新决策
- 用户要求生成 docx / pptx / md 等非表格 → 不在本 skill 范围
- 本地附件类型非 pdf / docx / pptx（如 zip / 图片 / 本地 csv） → 告知用户当前仅支持 pdf / docx / pptx 本地附件（在线文档参考除外，走 Step 2 的 MCP 读取）
执行流程（5 步）
Step 1: Reasoning & Naming
核心：推断目标 title，全程不反问用户。
从用户需求推断两样即可：展示标题与落盘位置。
- 推断标题：从用户原话 / 附件名取一个简洁标题；用户明确指定的名字优先，实在无线索用
workbook_<YYYYMMDD_HHMMSS>。用户指定的是目录（"放到/放在/保存到"或目录路径）时只取作落盘目录，标题仍独立推断；只有显式文件名路径才拆 dirname/basename，并从 basename 去掉.xlsx（避免Q1.xlsx.xlsx、避免把整条路径当标题）。 <sanitized_title>（文件系统用）：对推断标题（未截断）做 sanitize——删\ / : * ? " < > |、trim 首尾空格、中间空格转_、≤ 50 字符；只用于文件名 / 目录名，不碰路径分隔符。<title>（展示用）：即推断标题原样，用于 OOXML 显示标题。
产出本地 xlsx，纸面算出（写进脚本的必须是绝对路径）：
- 落盘目录：用上面从文件名 / 路径拆出的目录；无则默认 cwd。
~先展开成绝对路径。 <output_xlsx>=<落盘目录>/<sanitized_title>.xlsx（最终交付物）；已存在则加_<YYYYMMDD_HHMMSS>，不覆盖、不询问。<work_dir>= 同目录下的.<output_xlsx 的 stem>.ref/（基名与<output_xlsx>一致：撞名带了时间戳时同步带上，二者始终配对；存 build.py / extract 产物）。
Step 1 只做纸面计算；工作目录在 Step 2 创建，其余文件按后续步骤生成。
Step 2: 附件预处理
先建工作目录（本 skill 落盘的根——Step 2 参考产物、Step 4 的 build.py 都在其下）：mkdir -p "<work_dir>"。
再判断有无内容参考素材，按来源分流（无参考 → 直接进 Step 3）：
| 来源（如何识别） | 动作 |
|---|---|
在线文档参考（docs.qq.com 链接 / file_id，可能是 doc / slide / 别的在线 sheet；作为普通参考素材处理） |
用 MCP 读其数据 + 样式（doc 用文档读取工具；sheet 用 read_table / get_cell_ranges 含样式） |
| 本地 pdf/docx/pptx（消息里的文件路径 +「基于这份 pdf / 参照 docx / 按这个 ppt」等） | 用 extract.py 抽取（命令见下），落到 <work_dir>/reference/<sanitized_input_stem>/；<sanitized_input_stem> 为输入文件去扩展名后按 Step 1 sanitize 规则处理 |
| 本地非 pdf/docx/pptx（zip / 图片 / csv） | 见「不适用」段，不抽取 |
What ships with it
8 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.
- references/design_patterns/calendar.md 1.5 KB
- references/design_patterns/dashboard.md 1.8 KB
- references/design_patterns/form_print.md 1.5 KB
- references/design_patterns/model.md 1.7 KB
- references/design_patterns/plan.md 1.6 KB
- references/design_patterns/progress.md 1.5 KB
- references/design_patterns/stats.md 1.8 KB
- references/schema_principle.md 26 KB
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.
- today First seen · 187 lines · 118 tokens per session scan A e329a0642f16
tencent-docs-sheet-generation is a skill published in the GitHub repository rojim666/SztuCode (64 stars, last pushed today), licensed MIT. It adds 118 tokens to every session and 4,018 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
Gmail, Google Calendar, Drive, Docs, Sheets and Contacts for a connected Google account: read and search mail, send and reply, book and move meetings, find files, read and write Docs and Sheets, look people up. Use whenever the user mentions their email, inbox, calendar, meetings, Drive, a Google Doc or Sheet.
xlsx-official
Use this skill to build, edit, clean, or inspect a spreadsheet file (.xlsx, .xlsm, .xltx, .csv, or .tsv) when that file is the deliverable or the record being changed: financial and operating models, formula-driven summaries, template fills, cell and row patches, messy-data repair, sheet-to-CSV export, and workbook…
business-data-structuring
Inspect messy CSV/XLSX tables and create a reviewed clean business dataset with normalized headers, types, dates and amounts. Use for preparing a table; do not operate CRM entities or turn the preparation step into business analysis.
spreadsheet-analyst
Use when the user asks to inspect, clean, analyze, transform, calculate, or produce CSV or spreadsheet workbooks. Inspect sheets, schemas, formulas, and available spreadsheet tools first, preserve source data, and validate results with independent totals and rendered or structural checks.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
xlsx
Create/edit/analyze/verify spreadsheet workbooks including XLSX/CSV/TSV.