Jinshuju

What it does

When your agent uses it

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

Example prompts

• “/jinshuju”

Requirements

• Python 3

Workflow steps

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

1. 1先看再动：操作未知表单前，先 get_form 拿字段结构——每个字段的 api_code、选项的 choices[].api_code、表格的 dimensions[].api_code。create_entry / update_entry 的键必须是…
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 条，超过用 next（serial_number 游标）翻页。
3. 3先列再改：批量操作前先 list_entries 拉出命中记录展示给用户，用户确认后再逐条循环调用 update_entry / delete_entry，每 20 条汇报一次进度。
4. 4永不主动开 PUT：update_entry 默认 is_put=false（PATCH，只改提供的字段）。is_put=true 会把未提供字段全部清空，只有用户明确说"整条替换"且已列全所有字段时才允许，且需二次确认。
5. 5脱敏展示：输出手机号/邮箱/身份证默认打码（138****1234），除非用户明确要求原文。
6. 6不静默吞错：字段类型不支持、套餐限制、权限不足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 loads about 2k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 482 words of instructions outside code blocks.

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

~84

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

~2k

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

~23k

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). 482 words, ~2,023 tokens.

name

jinshuju

description

通过金数据（Jinshuju，jinshuju.net）MCP 操作用户托管在金数据平台上的在线表单：创建 / 复制 / 编辑表单与主题，含自动判分的考试表单、选项计分的测评表单；查询、新增（单条或批量）、更新、删除、批量修改数据；用上传凭证上传本地图片或文件；查询账户套餐额度与团队成员。仅在用户操作其金数据平台数据时使用——触发信号：提到 金数据 / Jinshuju / jinshuju.net、给出 form_token，或要操作一张已托管在金数据上的表单或数据。不要用于：用代码开发表单 / 问卷系统、处理本地文件或表格（Excel / CSV）、图片 / 票据 OCR、物流或监控等与平台无关的自动化，以及与金数据平台无关的通用数据处理。

slug

jinshuju

displayName

金数据（Jinshuju）

version

1.6.1

author

Jinshuju

license

MIT

platforms

macos, linux, windows

1. create_form，传字段列表 + setting
   （考试 / 测评场景改用 create_exam_form / create_evaluation_form，
    create_form 的 scene 已不支持 exam / evaluation）
2. 返回表单链接和 form_token
3. 如需特殊样式，追加 edit_theme（可用 generate_header_image 让 AI 生成头图，
   本地已有图片则先 prepare_form_image_upload（type=header）上传）

1. get_form → 记下字段 api_code 和选项 api_code
2. list_entries 用 filters 下推条件（选项字段传 api_code 不是 label）
3. next 翻页拿全部数据
4. Markdown 表格展示，表头用 get_form 的 label，关键字段脱敏
5. 询问用户是否需要生成 CSV artifact

1. get_form → 拿目标字段 api_code + 目标选项 api_code
2. list_entries + filters 拉出命中集，展示前 10 条 + 总数
3. 用户确认后，逐条循环 update_entry（is_put=false）
4. 每 20 条汇报进度，结束时汇总成功/失败数

1. list_entries + filters 拉出命中集，记录 serial_number
2. 必须得到用户显式"确认删除"
3. 逐条循环 delete_entry
4. 每 20 条汇报进度

1. get_form → 拿目标字段 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数据；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": {
      "url": "https://jinshuju.net/mcp",
      "headers": { "Authorization": "Basic <BASE64>" }
    }
  }
}

{
  "mcpServers": {
    "jinshuju": { "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-expert/skills/jinshuju of infometa/workbuddyskills.

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

Open the folder on GitHubat commit 91b77ea