Jinshuju Table

What it does

When your agent uses it

• Tasks that involve Excel spreadsheets
• Tasks that involve CSV and tabular files

Example prompts

• “/jinshuju-table”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1先看再动：操作未知数据表前，先 get_table 拿列结构——每列的 api_code、选项列的 choices[].api_code。create_entry / update_entry 的键必须是列 api_code，传中文列名会被服务端丢弃。
2. 2filters 优先：list_entries 支持 filters=[{field, operator, value}] 下推过滤，比拉全量再本地筛选快几个数量级。单次上限 50 行，超过用 next（serial_number 游标）翻页。
3. 3先列再改：批量操作前先 list_entries 拉出命中行展示给用户，用户确认后再执行——批量更新用 patch_entries 一次提交（≤200/批）；删除仍逐行循环 delete_entry，每 20 行汇报一次进度。
4. 4永不主动开 PUT：update_entry 默认 is_put=false（PATCH，只改提供的列）。is_put=true 会把未提供列全部清空，只有用户明确说"整行替换"且已列全所有列时才允许，且需二次确认。
5. 5脱敏展示：输出手机号/邮箱默认打码（138****1234），除非用户明确要求原文。
6. 6不静默吞错：列类型不支持、套餐限制、权限不足、未开通新版表格的报错原文回显并给出替代方案。

What it can do on your machine

Read from SKILL.md and the folder at commit 91b77ea. It shows what the files ask for, not the result of running them.

• Tool permissions

  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.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • jinshuju.net

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jinshuju Table loads about 2.1k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 501 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~76

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~6.9k

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.

Safety

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.

SKILL.md

The full file from infometa/workbuddyskills at commit 91b77ea, republished under its MIT licence (© infometa). 501 words, ~2,086 tokens.

name

jinshuju-table

description

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的数据表格：创建 / 编辑数据表与列（含自动计算的公式列）；查询、新增（单条或批量）、更新、批量更新、删除行数据；用上传凭证把本地文件写入附件列；查询账户套餐额度与团队成员。仅在用户操作其金数据数据表时使用——触发信号：提到 金数据表格 / Jinshuju 表格 / 数据表，或要在金数据上建表、加改列、批量维护行数据。不要用于：用代码开发表格系统、处理本地文件或表格（Excel / CSV）、搭建对外收集的表单 / 问卷、图片 / 票据 OCR，以及与金数据平台无关的通用数据处理。

slug

jinshuju-table

displayName

金数据AI表格

version

1.0.0

author

Jinshuju

license

MIT

platforms

macos, linux, windows

1. create_table，传 name + fields（列定义列表）
   - 列类型见「支持的列类型」；单选/多选列（RadioButton / CheckBox）传 choices
   - 需要跨列自动计算传 FormulaField（公式列）
2. 返回表结构与 token

1. get_table → 记下现有列的 api_code
2. edit_table，用 fields 原子操作：
   - add: 新增列（同 create_table 的列定义）
   - remove: 传要删列的 api_code 数组（删有数据的列会永久清除该列数据，先确认）
   - update: 改列属性，带 api_code 保持 identity
   - update_choices: 增删改选项（改名用 update 保留 api_code）

1. get_table → 记下列 api_code 和选项 api_code
2. list_entries（form_token 传表 token）用 filters 下推条件（选项列传 api_code 不是 label）
3. next 翻页拿全部数据
4. Markdown 表格展示，表头用 get_table 的列 label，敏感列脱敏
5. 询问用户是否需要生成 CSV artifact

1. get_table → 拿目标列 api_code + 目标选项 api_code
2. list_entries + filters 拉出命中集，展示前 10 行 + 总数
3. 用户确认后，用 patch_entries 一次提交（每行 { serial_number, entry }，PATCH 只改提供列，每批 ≤200 自行分批）
4. 读返回的 updated_count + failed_rows（按 serial_number），向用户汇总成功/失败

1. get_table → 拿目标列 api_code + 选项 api_code
2. 把每行整理成 { api_code: value } 对象（选项传 api_code）
3. create_entries 一次提交（每批 ≤200，超过自行分批循环）
4. 读返回的 created_count + errors（按下标），向用户汇总成功/失败
   注意：不幂等，重复提交会产生重复行；失败后不要整批重发，按 errors 下标只补失败行

echo -n "YOUR_API_KEY:YOUR_API_SECRET" | base64

{
  "mcpServers": {
    "jinshuju-table": {
      "url": "https://jinshuju.net/mcp",
      "headers": { "Authorization": "Basic <BASE64>" }
    }
  }
}

{
  "mcpServers": {
    "jinshuju-table": { "url": "https://jinshuju.net/mcp" }
  }
}

© infometa, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in experts/jinshuju-table-expert/skills/jinshuju-table of infometa/workbuddyskills.

• SKILL.md
• references/examples.md
• references/guide.md
• references/tools.md
• scripts/setup.py

Open the folder on GitHubat commit 91b77ea