lark-sheets skillA
lark-sheets is agent-read markdown (skill) from dropfan/claude-code-plugins: 飞书电子表格：创建和操作电子表格。支持工作表与行列结构（增删/合并/尺寸/隐藏/冻结/分组）、单元格读写（值/公式/样式/批注/单元格图片）、区域复制移动排序填充、查找替换、批量更新，图表、透视表、条件格式、筛选器与筛选视图、下拉列表、迷你图、浮动图片等对象的创建与维护，以及公式校验、历史版本回滚、本地 Excel/CSV 与飞书表格的导入导出。当用户需要创建或编辑表格、统计汇总与可视化、表格美化、公式计算（含 Excel 公式迁移）、金融/财务建模（DCF、三张表、预算、Sensitivity 等）时使用。多维表格（Base/bitable）请改用 lark-base；若用户是想按名称或关键词搜索云空间（云盘/云存储）里的表格文件，请改用 lark-drive 的 drive +search 先定位资源。当用户给出 doubao.com 的 /sheets/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
<!-- cowork-exec-note --> > **⚙️ Cowork / Claude Desktop 执行环境说明（自动注入）** > > 本技能依赖本地 `lark-cli`（`@larksuite/cli`，可用 `command -v lark-cli` 定位）及其 `~/.lark-cli` 登录态（应用密钥存于 macOS keychain）。 > > 在 Cowork 中运行任何 `lark-cli` 命令时，**必须在本地 macOS 上执行**（使用 Desktop Commander 的 `start_process` / `interact_with_process`，或其它本地 shell 工具），**不要用隔离的 Linux 沙箱** `mcp__workspace__bash`——沙箱里没有 lark-cli、也读不到 keychain。 > 执行前确保 npm 全局 bin 目录（`npm prefix -g` 输出目录下的 `bin`）在 PATH 中。 > > （在 Claude Code 中可忽略本说明，lark-cli 在本机 shell 直接可用。） # sheets **CRITICAL — 开始前 MUST 先用 Read 工具读取 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md)，其中包含认证、权限处理。** ## 场景 → 命令速查 > 按当前动作选行；下一步必须 Read 该行 reference，读取完成前不得执行命令。只读命中的文档；含公式 / 样式等横切动作时再读对应规范，禁止用目录枚举代替 Read。 | 你要做的事 | ✅ 正确写法 | 动手前读（先 Read 再动手） | | --- | --- | --- | | 读数据 | `+csv-get`（纯值/CSV）、`+cells-get`（公式/样式/批注） | 读 `references/lark-sheets-read-data.md` | | 写入数据 | `+csv-put`（无类型歧义纯文本）、`+table-put`（typed；量值/真日期；标签/编号/前导零/文本数字用 object，禁裸 csv-put）、`+cells-set`（公式/富写入）、`+cells-set-style`（样式）、`+cells-set-image`（单元格图片） | 读 `references/lark-sheets-write-cells.md` | …
Read the whole file at its exact version.
How to install
mdr add dropfan/claude-code-plugins/lark-sheets@v3.5.2mdr add dropfan/claude-code-plugins/lark-sheets@sha256:6a02f176828b394aPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_5uvzijkjvtbbsxqp)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v3.5.2 latest | 2026-09-21 | b87b343 | 28,658 B | A | view · diff |
| v3.0.2 | 2026-07-21 | 541a021 | 37,951 B | A | view · diff |
| v3.0.0 | 2026-07-05 | b88ef94 | 25,410 B | A | view · diff |
| v3.0.0 | 2026-06-29 | 1a6aead | 25,390 B | A | view · diff |
| v2.0.0 | 2026-06-05 | 6d9b4c7 | 22,466 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (28658 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
dropfan/claude-code-plugins · 8 stars · license MIT · pushed 2026-09-21 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_5uvzijkjvtbbsxqp GET https://markdownregistry.com/api/v1/resolve?ref=dropfan/claude-code-plugins/lark-sheets GET https://markdownregistry.com/api/v1/blob/6a02f176828b394a0fc5a10bd4ff2914ab72ad093693a68542d1f6ec592b85bf
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from dropfan/claude-code-plugins
Every file in dropfan/claude-code-plugins