lark-sheets

A tool for creating and managing Feishu spreadsheets, which are online workbooks with sheets, cells, formulas, and data objects such as charts and pivot tables.

In plain words
What is it for?
Use it to enter or update data, manage rows and columns, apply formulas and formatting, build summaries and financial models, and create charts, filters, pivot tables, and other spreadsheet objects.
Why use it?
It reduces manual spreadsheet editing and supports repeatable updates while preserving existing values, layout, and formatting where required.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/larksuite/cli/lark-sheets
Any agent
npx skills add larksuite/cli --skill lark-sheets
Clone the repo
git clone --depth 1 https://github.com/larksuite/cli

Made for: Claude Code, Codex.

Per session 257 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,996 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00257 $0.13996
Opus 5 $0.00129 $0.06998
Sonnet 5 $0.00051 $0.02799
Haiku 4.5 $0.00026 $0.01400

Measured today against content hash 09393e1be052, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lark-sheets 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 today.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/lark_chart_layout_check.py, scripts/lark_detect_subtables.py, scripts/lark_inspect_workbook.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/lark-sheets/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sheets

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理。

术语约定

同一对象的交替说法,按此映射解析用户口语:工作表(sheet)= 子表 / tab / 标签页(sheet_id 是稳定标识);电子表格(spreadsheet)= 工作簿 / 表格(顶层容器,由 --url--spreadsheet-token 定位);reference_id = 表内对象的稳定标识,即各对象主键 flag 接受的值(与 --image-uri 图片上传句柄不是一回事)。

每类对象用各自的主键 flag 定位(命名不统一,按此表对照,不要凭直觉拼):

对象 主键 flag 对象 主键 flag
工作表 sheet --sheet-id 条件格式规则 --rule-id
图表 chart --chart-id 筛选视图 --view-id
透视表 pivot --pivot-table-id 迷你图(按组) --group-id
浮动图片 --float-image-id

飞书表格编辑准则(动手前必守,所有编辑类任务一律生效)

下列准则横切所有飞书表格任务,动手前先过一遍——被索引直接路由进某个工具参考时也一律生效;展开与边界见括注的 reference。

  1. 最小改动:除任务要改的单元格 / 列外,原表其它单元格、行列结构、Sheet 名、合并区、格式 1:1 保持;中间结果放原数据右侧或新建空白 Sheet,禁止删 / 改名 / 隐藏 / 移动已存在 Sheet(用户明示要求的除外,确认影响后执行,见 lark-sheets-workbook);改写类任务精确圈定行列,不该转的原值 1:1 保留;补齐类只写空单元格,已有值(哪怕看着可疑)一律不动,最多在交付说明备注。原表数值列的显示格式(小数位 / 千分位 / 是否科学计数法)同属不可改动项;仅当原值已被压成科学计数法或丢小数位时补 number_format 恢复可读,底层值不动。新增的计算列 / 汇总行(均值、占比、金额)必须显式设 number_format——公式默认吐出的多位小数(3.64507772)会被判为格式不合格,按语义定位数(比率两位小数、占比百分比、金额千分位)并与原表同列风格对齐。
  2. 真实写回 + 回读校验:交付必须是对在线表格的真实写入,写完用 +csv-get / +cells-get / +<对象>-list 回读确认生效(顺带确认无截断 / 溢出 / 科学计数法)——返回 ok 只代表请求被接受,不代表结果符合预期。回读值可能带「值(样式)」注记(如 49.6(V-Align: bottom)),据此回写前先剥离注记只留纯值;写公式后用 +cells-get --include formula 核对真实落格(仅看显示值不能证明联动);筛选 / 排序后核对前几行,删除后确认已空。不要只在文本里声称"已完成"。
  3. 读全再写:批量填充 / 补齐 / 修正类任务先确认真实数据末行再写,只探前 N 行会漏写表尾(确定末行流程见 lark-sheets-read-data)。
  4. 公式优先于硬编码:凡可由表内其它单元格推导的值(总计 / 占比 / 增长率 / 提取 / 查找)一律写公式,即使用户没说"联动 / 自动更新"——本地算好再静默写进单元格,交付的是改输入不重算的死表。提取类产出同行源列的连续原文片段(逐字保真、不跨列取材,一格含多个片段要全列出);语义判断类(无固定分隔符 / 模式可循)公式表达不了,逐行写静态值,别用固定偏移 / 通用正则硬套。输入列可能为空时公式先判空返回空(空格按 0 参与算术产出无错误码的错值,IFERROR 拦不住)。写聚合公式(SUM / COUNTIF / AVERAGE 等)前先确认区间的起止两端:起点跳过表头行、终点覆盖真实末行——漏掉末行或把表头算进计数是最常见的错值来源,且结果看着合理、不报错;写完抽查区间首尾两格确认落在数据内。写飞书公式前读 lark-sheets-formula-translation,落表后用 +formula-verify 诊断。试错 3 次仍失败可降级静态值,交付说明写明「静态值 + 失败原因 + 不随源数据更新」。
  5. 续写 / 扩展继承样式:续写、补齐、复制区块、新增行列时禁止只读值只写值——原表的字体 / 字号 / 颜色、四边框、对齐、底色(含奇偶行交替)、行高列宽、合并都要一并延续到新区域,判分与验收都按"新区域与相邻原始区域视觉一致"来看
    • 新增行 / 列优先用 +dim-insert --inherit-style before(或 after,样式由原生继承,比"往空白区直接写值再补刷样式"可靠得多(后者最易整片丢失交替底色与边框)。它只选继承哪一侧,不是插入方向。行高是例外,不随样式继承:插行填长文本前读相邻行 row_height,补 +rows-resize(可与插入链合批)。
    • 已经写进空白区、或要对齐非相邻区域时,先 +cells-get --include style 读原区样式,再随值一起写回(清单见 lark-sheets-write-cells,四边框最易漏)。
    • 新增列后把原跨列合并的标题扩展到新末列;插入行复制邻近行的合并分段,按分组合并前逐组核对边界行号,错界会吞掉组名。
  6. 多步写入分流:美化收尾(样式 / 合并 / 行高列宽 / 冻结的任意组合)→ 一次 +styles-put 声明式规格交付(见 lark-sheets-styles-put);同一个写操作打多个区域 → 用该命令自身的复数形态(--ranges / map 入参);只有跨类型、有顺序依赖的操作链(如插列 → 写表头 → 回填数据)才用 +batch-update(high-risk-write:按下方审批协议先获用户同意再带 --yes;失败处置语义见 lark-sheets-batch-update)。
  7. 分组汇总优先用透视表:参考速查表「分组汇总 / 透视」行;SUMIF / 本地脚本拼假透视表可能丢失原生透视能力,作为风险记录。
  8. 回复里声称的每一项,产物里都要能指到位置:交付说明 / 回复正文写了"已生成趋势分析报告""图中对比了两个资产""覆盖 11 种格式",就必须在产物中真实存在对应的 sheet / 图表对象 / 文字段落,并能说出它在哪张表第几行。文字描述不能替代产物——判分只认产物里能被读到的内容,回复里的描述一概不计分。交付前逐条对照自己写的每句"已完成 X",指不到位置的要么补做,要么把该句删掉改成"未完成 + 原因"。

Read the full file on GitHub · 253 lines

Files

What ships with it

28 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.

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. today Changed · +1 lines 09393e1be052
  2. 2d ago First seen · 252 lines · 257 tokens per session scan A 8984c32687cc

Subscribe to this mod's changes

lark-sheets is a skill published in the GitHub repository larksuite/cli (16,925 stars, last pushed today), licensed MIT. It adds 257 tokens to every session and 13,996 once invoked, about $0.0013 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 2026-08-30.

Related

Other skills, from other repositories

dcf-model

Build discounted cash flow valuation workbooks in Excel.

NousResearch/hermes-agent · 14 tokens

xlsx

当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要:打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件(例如添加列、计算公式、格式化、制图、清理混乱数据);从头创建新的电子表格或从其他数据源创建;或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及(如"我下载目录里的 xlsx")——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件(格式错误的行、错位的表头、垃圾数据)清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets…

agentscope-ai/QwenPaw · 232 tokens

audit-xls

Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…

anthropics/financial-services · 104 tokens

google-drive-sheets

Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.

yc-software/qm · 31 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

sn-da-large-file-analysis

万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl readonly 流式读取(iterrows 支持 10 万行以上)、Parquet 转换加速、内存优化、分块处理和大文件写入模式。遇到以下任一情况就主动使用本 skill:①数据行数 ≥ 10k(由 sn-da-excel-workflow 的行数评估步骤触发);②用户出现触发词:大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing;③直接使用…

OpenSenseNova/SenseNova-Skills · 218 tokens