kingdee-k3cloud

kingdee-k3cloud is a skill for Claude Code, Codex from adamzhang1987/kingdee-k3cloud-skill. It costs 161 tokens per session (3,491 once invoked), scanned A, original, Apache-2.0.

A skill for working with Kingdee K3Cloud, a Chinese enterprise resource planning system used for records such as orders, inventory, materials, customers, and suppliers. It provides rules for querying the system through K3Cloud API tools.

In plain words
What is it for?
Use it to find business records, inspect individual documents, generate daily operational reports, query customer information, and split large searches into safe pages or date ranges.
Why use it?
It helps avoid failed queries caused by incorrect form IDs, field names, date filters, or status codes. It also helps prevent incomplete results when the system returns too much data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it to find business records, inspect individual documents, generate daily operational reports, query customer information, and split large searches into safe pages or date ranges.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud
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.

Any agent
npx skills add adamzhang1987/kingdee-k3cloud-skill --skill kingdee-k3cloud
Clone the repo
git clone --depth 1 https://github.com/adamzhang1987/kingdee-k3cloud-skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for kingdee-k3cloud

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud/github.svg)](https://agentmods.dev/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud)
Your own site
<a href="https://agentmods.dev/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud"><img src="https://agentmods.dev/badge/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for kingdee-k3cloud

Your own site · 80×15
<a href="https://agentmods.dev/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud"><img src="https://agentmods.dev/badge/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,491 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00161 $0.03491
Opus 5 $0.00081 $0.01746
Sonnet 5 $0.00032 $0.00698
Haiku 4.5 $0.00016 $0.00349

Measured 10d ago against content hash b96853634ec2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kingdee-k3cloud 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 10d ago.

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.

kingdee-k3cloud/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

金蝶云星空 ERP 操作技能

通过 MCP 工具与金蝶云星空 API 交互的核心指南。查询前务必先查阅本文件确认表单ID和字段命名规则,避免 500 错误。

前提条件:本 Skill 需配合金蝶云星空 MCP Server 使用,推荐 kingdee-k3cloud-mcp。确保 Claude Code 已配置好 MCP Server 并可访问 query_bill_jsonview_bill 等工具。


核心原则

  1. 分步查询:先用 query_bill_json 查列表(关键字段),再用 view_bill 看单条详情
  2. 日期过滤:半开区间 FDate >= 'YYYY-MM-DD' AND FDate < 'YYYY-MM-DD+1'
  3. FDate vs FCreateDateFDate 是业务日期(手填),FCreateDate 是系统创建时间。按"今天开的单"统计用 FCreateDate
  4. 单据状态码Z = 暂存草稿,A = 创建,B = 审核中,C = 已审核,D = 重新审核
  5. 控制数据量top_count 限制行数,只查必要字段,超过20行数据考虑创建 Excel
  6. 字段不确定时:先调用 query_metadata(form_id) 验证字段是否存在,避免试错浪费 token

大数据量查询流程(跨周/跨月/跨年必读)

关键限制:金蝶 ExecuteBillQuery 单次最多返回约 2000 行;MCP tool-result 上限 1MB。
查询结果中带有 "truncated": true 则说明数据被截断,必须继续翻页或分片

决策树

① 时间跨度 > 1 周,或不确定数据量
   → 先 count_bill(form_id, filter_string) 估算行数

② estimated_rows ≤ 500(is_exact=true)
   → 一次性 query_bill_json,top_count=500

③ estimated_rows ≤ 2000(is_exact=true)
   → 一次性 query_bill_json,top_count=2000

④ estimated_rows > 2000 或 is_exact=false(≥ 5000)
   → 优先调用(mcp ≥ 1.2.0):
       query_bill_range(
           form_id, field_keys,
           date_field="FDate", date_from="YYYY-01-01", date_to="YYYY+1-01-01",
           chunk="month", output_path="/tmp/output.ndjson"
       )
   → 兜底做法(mcp < 1.2.0):
       for month in 月份范围:
           query_bill_json(filter="FDate >= 'YYYY-MM-01' AND FDate < 'YYYY-MM+1-01'", top_count=2000)
           若返回 truncated=true → 在该月内继续翻页(start_row=next_start_row)

⑤ 累计行数 > 20 行
   → 必须写入 Excel / CSV 文件,不要把大量数据倾倒进对话
   → 使用 query_bill_to_file 或 query_bill_range(output_path=...) 直接落盘

⑥ 查询中途出 SESSION_EXPIRED
   → 只重试当前片,已翻过的月份无需重跑

推荐做法(mcp ≥ 1.2.0)— 直接落盘,无需手动循环

# 跨年查询,按月自动分片,流式写入本地文件
query_bill_range(
    form_id="SAL_SaleOrder",
    field_keys="FBillNo,FDate,FCustId.FName,FAllAmount",
    date_field="FDate",
    date_from="2025-01-01",
    date_to="2026-01-01",
    chunk="month",
    output_path="/tmp/sales_2025.ndjson"
)
# 返回:{"path": "/tmp/sales_2025.ndjson", "row_count": N, "bytes": M, "chunks": 12}

Read the full file on GitHub · 244 lines

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. 10d ago First seen · 244 lines · 161 tokens per session scan A b96853634ec2

Subscribe to this mod's changes

kingdee-k3cloud is a skill published in the GitHub repository adamzhang1987/kingdee-k3cloud-skill (30 stars, last pushed 3d ago), licensed Apache-2.0. It adds 161 tokens to every session and 3,491 once invoked, about $0.0008 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