XLSX Spreadsheet Toolkit
XiaomiMiMo/MiMo-Code
Builds, edits, cleans, recalculates and reads Excel workbooks and CSV files with openpyxl and pandas, plus LibreOffice for recalculation and PDF export.
Builds, edits and cleans Excel workbooks inside BiSheng's code executor using openpyxl, with LibreOffice recalculation and a pre-delivery check.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add dataelement/bisheng --skill bisheng-xlsx -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dataelement/bisheng bisheng-xlsx --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dataelement/bisheng.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx .claude/skills/bisheng-xlsx && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bisheng-xlsx" agent skill from https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx into .claude/skills/bisheng-xlsx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bisheng-xlsx", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsxType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dataelement/bisheng --skill bisheng-xlsx -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dataelement/bisheng bisheng-xlsx --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dataelement/bisheng.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx .agents/skills/bisheng-xlsx && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bisheng-xlsx" agent skill from https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx into .agents/skills/bisheng-xlsx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bisheng-xlsx", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dataelement/bisheng --skill bisheng-xlsx -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dataelement/bisheng bisheng-xlsx --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dataelement/bisheng.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx .cursor/skills/bisheng-xlsx && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bisheng-xlsx" agent skill from https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx into .cursor/skills/bisheng-xlsx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bisheng-xlsx", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dataelement/bisheng.git --path src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dataelement/bisheng --skill bisheng-xlsx -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dataelement/bisheng bisheng-xlsx --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dataelement/bisheng.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx .gemini/skills/bisheng-xlsx && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bisheng-xlsx" agent skill from https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx into .gemini/skills/bisheng-xlsx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bisheng-xlsx", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dataelement/bisheng bisheng-xlsxInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dataelement/bisheng --skill bisheng-xlsx -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dataelement/bisheng.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx .github/skills/bisheng-xlsx && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bisheng-xlsx" agent skill from https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx into .github/skills/bisheng-xlsx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bisheng-xlsx", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dataelement/bisheng --skill bisheng-xlsx -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dataelement/bisheng bisheng-xlsx --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dataelement/bisheng.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx .opencode/skills/bisheng-xlsx && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bisheng-xlsx" agent skill from https://github.com/dataelement/bisheng/tree/main/src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx into .opencode/skills/bisheng-xlsx/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bisheng-xlsx", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
bisheng-xlsxBuilds, edits and cleans Excel workbooks inside BiSheng's code executor using openpyxl, with LibreOffice recalculation and a pre-delivery check.
The skill is written in Chinese for BiSheng's code interpreter, where openpyxl is the only supported way to generate .xlsx files and formulas written by it carry no values until LibreOffice recalculates them. It covers new data, summary, budget, financial model, quotation and ledger sheets, filling in uploaded templates, and cleaning .xlsx, .xls or .csv files with pandas before writing a standard workbook. Charts as images, Word and PowerPoint are out of scope.
It spells out environment facts: no markitdown or Node, no pip install and no network, relative paths only, deliverables in `output/` and drafts in `scratch/`, per-run time limits, and a log rule where only stderr or only stdout comes back depending on the exit code. Builds go through a script written to a file, with helper scripts for inspecting a workbook, recalculating it and checking it, plus references on Chinese table design and an openpyxl cookbook. If the sandbox hides the skill scripts, it falls back to inline openpyxl and says that recalculation was skipped.
10 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ed3b461. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 3 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pipnpmpythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip and npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
BiSheng XLSX Workbook Builder loads about 1.7k tokens when it runs, and up to ~5.1k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 396 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from dataelement/bisheng at commit ed3b461, republished under its Apache-2.0 licence (© dataelement). 396 words, ~1,728 tokens.
.claude/skills/bisheng-xlsx/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.这一轮只读文档,不要在同一轮里并行调用别的工具。 读完本文件(必要时再读 references)之后, 下一轮才开始动手。把「读 SKILL.md」和「产出交付物」放进同一轮并行调用,等于技能没读。
本技能要求已勾选代码执行器(bisheng_code_interpreter)。 没有它就无法生成 .xlsx ——
直接告诉用户「请在工具里勾选代码执行器后重试」,不要用 Markdown 表格顶替。
| 项 | 事实 |
|---|---|
| 生成方式 | 只有 openpyxl(后端 pyproject.toml 的正式依赖),import openpyxl 直接可用 |
| 公式重算 | 靠 LibreOffice(soffice)。openpyxl 写出的公式没有值,不重算等于交了张空表 |
| 不存在的东西 | markitdown、Node/npm、defusedxml、pdftoppm、zip/unzip 命令 |
xlsxwriter | 在,但只能新建、不能读改已有文件,也不能和 openpyxl 混用 → 一律用 openpyxl |
| 其它可用库 | pandas/numpy、Pillow、PyMuPDF(fitz)、matplotlib、python-docx、python-pptx、lxml |
| 禁止 | pip install、npm install、任何联网假设(生产多为离线内网) |
| 工作目录 | 执行器 cwd = 工作区根,一律用相对路径 |
output/ | 唯一交付区。每次运行自动创建 |
scratch/ | 中间产物区,不会交付,需自己 os.makedirs;跨轮追问时会丢 |
uploads/ | 用户上传的原件在这里。跨轮追问时和 output/ 一起被带进新会话 |
skills/bisheng-xlsx/ | 本技能包,脚本和参考资料在这里,只读 |
| 绝对禁止 | 写 /output/xxx.xlsx 这种带前导斜杠的路径 —— 文件被静默丢弃,用户拿不到 |
| 单次执行上限 | 本地执行器 600 秒;E2B 沙箱 300 秒。构建、重算、体检分多次调用 |
| 日志规则 | 二选一:returncode != 0 只回 stderr(stdout 整段丢弃);returncode == 0 只回 stdout(stderr 整段丢弃)→ 一切诊断用 print(),且子进程的 stdout 和 stderr 都要各自打印一遍 |
| 可见性 | exitcode 0 时执行器把本轮新建/修改的文件同步进工作区,之后 ls/read_file 一般能看到。但判断是否产出以 exitcode 0 + 日志为准,不要因为一次 ls 没看到就重做 |
| 轮次 | 最后两轮工具收窄到 write_file/edit_file/导出,代码执行器会被拦掉 → 表要尽早产出,不要拖到收尾 |
| E2B 沙箱 | 沙箱模式下 skills/ 结构性不可见(copy-in 快照早于技能物化)→ 调包内脚本必 FileNotFoundError。一旦报这个错,就改走纯 openpyxl 内联写法:不调本包脚本,公式改成 Python 算好写数值,并在收尾里说明没做重算与体检 |
import shutil
try:
import openpyxl
print("openpyxl OK", openpyxl.__version__)
except ImportError:
print("openpyxl MISSING")
print("soffice:", shutil.which("soffice") or shutil.which("libreoffice") or "无 —— 公式无法重算,见 §4 降级方案")openpyxl MISSING:正常部署不会出现。不要 pip install(共享的离线环境,装了会污染所有租户)。
如实告诉用户环境缺依赖,需要运维补装。soffice 没有、或重算时报「没有 Calc 组件」:见 §4 的降级方案,不要假装重算过了。| 情况 | 做法 |
|---|---|
| 用户给了数据(或让你先查再整理),要一张新表 | §3 从零构建 |
| 用户上传了 .xlsx 要改内容 / 填数 | §5 改已有文件(先读懂它的约定,再动手) |
| 用户上传了 .csv/.xls 要清洗成规范表 | pandas 读进来清洗 → 按 §3 写出 |
| 用户要的是图表图片、Word、PPT | 不属于本技能 |
第 1 步 · 定结构。先想清楚分几个表、每个表的列。复杂测算把假设单独放一个表。
草稿写 scratch/,不要写进 output/ —— 交付物按类型排序,.md/.docx/.pdf/.html 排在
.xlsx 前面,所以 output/ 里只要有一个 .md,它就永远压过你的表成为用户看到的头条交付物。
不是「同一轮才会」,是只要在就会。
第 2 步 · 写构建脚本。用 write_file 把完整脚本写到 scratch/build_sheet.py,
不要把整段代码塞进代码执行器的参数里 —— 参数过长会被截断,导致反复重试却总差一截。
写法读 /skills/bisheng-xlsx/references/openpyxl-cookbook.md(表格、样式、数字格式、公式、
图表、批注都有可直接抄的片段),规范读 /skills/bisheng-xlsx/references/design-zh.md。
第 3 步 · 执行:
import subprocess, sys
r = subprocess.run([sys.executable, "scratch/build_sheet.py"], capture_output=True, text=True)
print(r.stdout or "(no stdout)")
print(r.stderr[-2000:] if r.stderr else "(no stderr)")为什么不直接写
python scratch/build_sheet.py:PATH 里的python未必是后端那个解释器, 用sys.executable才能保证跑在装了 openpyxl 的环境里。下面所有脚本调用都用这个写法。
第 4 步 · 重算(有公式就必做),见 §4。
第 5 步 · 体检并返修,见 §6。返修用 edit_file 定点改 scratch/build_sheet.py 再重跑,
不要每次重写整份脚本。
openpyxl 写出的公式只是字符串,没有结果。不重算的话,pandas、data_only=True、
以及多数预览器读到的全是空 —— 用户打开看到的是一张有公式没数字的表。
import subprocess, sys
r = subprocess.run([sys.executable, "skills/bisheng-xlsx/scripts/recalc_check.py", "output/xxx.xlsx"],
capture_output=True, text=True)
print(r.stdout or "(no stdout)")
print(r.stderr[-2000:] if r.stderr else "(no stderr)")LibreOffice 会算完所有公式、就地重写文件,然后脚本回读并列出所有错误单元格。
一次重算连冷启动约 10–30 秒;超时就加 --timeout 120。
看结论:
重算完成 —— 公式都能算出结果。这不是交付条件,还要过 §6 的体检。重算未通过 + 错误单元格清单 —— 逐个改完再重算。[未重算] —— 环境问题(没有 soffice、或只装了 writer 没装 calc、或超时)。这时不要硬撑:
改成在 Python 里把数算好直接写数值,并在表里用一列文字说明计算口径,
同时如实告诉用户「本环境无法重算公式,已改为写入计算结果,修改输入不会自动重算」。能算 ≠ 算对。 区间差一行、引用错行,照样是一张干净的错数字表。 铺开整张表之前,先写 2–3 个关键公式,重算一次,肉眼核对结果符不符合预期。
import subprocess, sys
r = subprocess.run([sys.executable, "skills/bisheng-xlsx/scripts/inspect_workbook.py",
"uploads/原表.xlsx", "--content-only"], capture_output=True, text=True)
print(r.stdout or "(no stdout)")
print(r.stderr[-2000:] if r.stderr else "(no stderr)")它按单元格坐标打印内容和公式(这是 markitdown 在本环境的替代品,而且比它多给坐标,
所以可以据此规划改哪一格)。然后:
load_workbook(path) 打开(不要加 data_only=True,那样保存会把公式全变成字面量)。.xlsm 要 keep_vba=True,否则宏全丢。output/,不要覆盖 uploads/ 里的原件。import subprocess, sys
r = subprocess.run([sys.executable, "skills/bisheng-xlsx/scripts/inspect_workbook.py", "output/xxx.xlsx"],
capture_output=True, text=True)
print(r.stdout or "(no stdout)")
print(r.stderr[-2000:] if r.stderr else "(no stderr)")输出分两段:
_xlfn. 前缀伪装)、
_xlfn. 缺前缀、跨表引用引号、百分比存成文本、百分比存整数、数字带单位存成文本、
公式无缓存值、重算后仍是错误值、缺表头、列宽不足导致 ###、合并区丢值、年份千分位、
残留占位符、硬编码系数、除法未保护。
同一条规则在同一列命中多次时只列 3 例 + 一句「同类还有 N 处」,按同样办法一次改完。改完重新生成 → 重算 → 再体检,直到最后一行是 结论: 通过。
只有 ERROR 挡交付;结论: 通过 之后仍要把 WARN 逐条看一遍,确实无碍再交付。
XLOOKUP / XMATCH / SORT / FILTER / UNIQUE / SEQUENCE / LET / LAMBDA
—— openpyxl 写不出溢出元数据,LibreOffice 要么报 #NAME?,要么只填左上角一个值
而且重算报 0 错误。查表用 INDEX/MATCH;排序、去重、筛选在 Python 里做完再写值。
加 _xlfn. 前缀救不了这一组:=_xlfn.SORT(...) 实测照样 #NAME?,体检也照样拦。TEXTJOIN / CONCAT / IFS / SWITCH / MAXIFS / MINIFS 必须带 _xlfn. 前缀,
裸写 → #NAME?。='假设 输入'!$B$5。用 sheet_ref() 自动处理。set_pct(),它会在你传 15 时直接报错。output/ 里只放最终的 .xlsx。草稿、构建脚本、中间版本一律放 scratch/。output/2024年度经营分析.xlsx。markitdown 读表 —— 环境里没有,用 §5 的 --content-only。pip install 任何东西。/output/...。load_workbook(..., data_only=True) 之后 save() —— 会永久毁掉所有公式。ls 没看到刚生成的文件就重做一遍 —— exitcode 0 + 日志就是产出的凭据。"15%"、"1,250,000" 这种字符串 —— 不参与求和,体检会拦。© dataelement, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (scripts, references) in src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx of dataelement/bisheng.
Open the folder on GitHubat commit ed3b461
BiSheng XLSX Workbook Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| BiSheng XLSX Workbook Builder this skilldataelement/bisheng | 12k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| XLSX Spreadsheet ToolkitXiaomiMiMo/MiMo-Code | 14k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Excel Spreadsheet Builderagentscope-ai/QwenPaw | 35k | — | ~1.8k | Automated safety check: Pass | Proprietary | |
| Spreadsheetdavila7/claude-code-templates | 32k | 1 repos | ~1.3k | Automated safety check: Notes | Apache-2.0 | |
| Openai Spreadsheettrailofbits/skills-curated | 512 | — | ~1.3k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Excel Spreadsheet Creation and Editinganthropics/skills | 180k | 4 repos | ~2.1k | Automated safety check: Pass | Proprietary |
XiaomiMiMo/MiMo-Code
Builds, edits, cleans, recalculates and reads Excel workbooks and CSV files with openpyxl and pandas, plus LibreOffice for recalculation and PDF export.
agentscope-ai/QwenPaw
Creates, edits, cleans and analyzes Excel and CSV files with openpyxl and pandas, recalculating formulas through LibreOffice so files are delivered without formula errors.
davila7/claude-code-templates
A skill your agent uses when tasks involve creating, editing, analyzing, or formatting spreadsheets (.xlsx, .csv, .tsv) using Python (openpyxl, pandas), especially when formulas, references, and…
trailofbits/skills-curated
A skill your agent uses when tasks involve creating, editing, analyzing, or formatting spreadsheets (.xlsx, .csv, .tsv) using Python (openpyxl, pandas), especially when formulas, references, and…
anthropics/skills
Creates, edits and analyzes spreadsheets (.xlsx, .xlsm, .csv, .tsv) with openpyxl and pandas, writing live formulas and recalculating to confirm zero formula errors.
HKUDS/DeepTutor
Reads, creates and edits Excel workbooks with openpyxl, including formulas, styles, charts and CSV or TSV tables, with advice on formula values openpyxl cannot compute.
dataelement/bisheng
Builds or edits Word .docx documents inside BiSheng's code executor with python-docx, handling Chinese fonts, tables of contents, page numbers and official-document layout.
dataelement/bisheng
Builds PowerPoint decks in BiSheng's code executor with python-pptx, from scratch, from a supplied template or by rewriting an existing file, with Chinese layout rules.
dataelement/bisheng
Reviews BiSheng spec, design and tasks documents with checklists for PRD gaps, handover readiness and acceptance traceability, producing a report or an LGTM.
dataelement/bisheng
Runs a light convention check on one finished spec-driven task, choosing checks by task type and ending in pass, pass-with-notes or needs-fix.
dataelement/bisheng
Maps BiSheng's approval-center architecture to exact service files and methods, so a change to approval logic can be located without searching the whole repo.
dataelement/bisheng
Runs a seven-dimension code review on a finished feature, comparing the diff against a base branch and the feature's spec, design and task files.
Categories
Builds, edits and cleans Excel workbooks inside BiSheng's code executor using openpyxl, with LibreOffice recalculation and a pre-delivery check. xlsx files and formulas written by it carry no values until LibreOffice recalculates them.csv files with pandas before writing a standard workbook.
BiSheng XLSX Workbook Builder fits situations like: building a budget, quotation or ledger spreadsheet from scratch; exporting prepared data to a workbook with formulas and formatting; cleaning an uploaded CSV or XLS file into a standard sheet; filling a user's xlsx template with new numbers.
Run `npx skills add dataelement/bisheng --skill bisheng-xlsx -a claude-code`. Or copy the skill folder (src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx in dataelement/bisheng) into .claude/skills/bisheng-xlsx in your project. Claude Code loads it when a task matches its description.
Run `npx skills add dataelement/bisheng --skill bisheng-xlsx -a codex`. Or copy the skill folder (src/backend/bisheng/linsight/builtin_skills/bisheng-xlsx in dataelement/bisheng) into .agents/skills/bisheng-xlsx in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dataelement/bisheng --skill bisheng-xlsx -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bisheng-xlsx, .gemini/skills/bisheng-xlsx, .github/skills/bisheng-xlsx and .opencode/skills/bisheng-xlsx in your project.
Going by SKILL.md and its folder, BiSheng XLSX Workbook Builder needs Python for the scripts in its folder and the command-line tools its instructions call (pip, npm and python). Our summary lists: BiSheng's code executor with openpyxl; LibreOffice for formula recalculation.
SKILL.md contains no URLs. Its commands use pip and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
BiSheng XLSX Workbook Builder is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with BiSheng XLSX Workbook Builder: XLSX Spreadsheet Toolkit (XiaomiMiMo/MiMo-Code, 14k stars), Excel Spreadsheet Builder (agentscope-ai/QwenPaw, 35k stars), Spreadsheet (davila7/claude-code-templates, 32k stars) and Openai Spreadsheet (trailofbits/skills-curated, 512 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
dataelement (a GitHub organization) maintains it in dataelement/bisheng, which has 12,028 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 8, 2026.
Source: dataelement/bisheng on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.