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.
npx skills add adamzhang1987/kingdee-k3cloud-skill --skill kingdee-k3cloudgit clone --depth 1 https://github.com/adamzhang1987/kingdee-k3cloud-skillWrote 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.
[](https://agentmods.dev/skills/adamzhang1987/kingdee-k3cloud-skill/kingdee-k3cloud)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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_json、view_bill等工具。
核心原则
- 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 - 日期过滤:半开区间
FDate >= 'YYYY-MM-DD' AND FDate < 'YYYY-MM-DD+1' - FDate vs FCreateDate:
FDate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 - 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 - 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 - 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}
What ships with it
11 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.
- LICENSE 1.2 KB
- references/common-errors.md 8.1 KB
- references/customer-query-guide.md 3.0 KB
- references/customization-guide.md 3.6 KB
- references/daily-report-workflow.md 3.6 KB
- references/gl-voucher-guide.md 3.3 KB
- references/inventory-analysis-workflow.md 4.9 KB
- references/order-tracking-workflow.md 5.4 KB
- references/periodic-report-workflow.md 5.8 KB
- references/sales-analysis-workflow.md 5.6 KB
- references/verified-fields.md 24 KB
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.
- 10d ago First seen · 244 lines · 161 tokens per session scan A b96853634ec2
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.
Other skills, from other repositories
kingdee-agent-rules
A set of usage rules for AI agents that connect to Kingdee Cloud Starry Sky, also known as K3Cloud, an enterprise business system.
decision-matrix
Compare options with weighted scoring, pros and cons, pre-mortems, opportunity costs, and ICE prioritization. Use when a user wants to reason through a choice, expose assumptions, or rank alternatives.
meeting-note-summarizer
Turn meeting notes or transcripts into factual summaries, decisions, questions, and action items. Use when a user wants a concise recap or needs explicit owners and deadlines extracted without filling in missing details.
daily-standup-journal
Generate concise daily standups, reflection prompts, and weekly retrospectives for individuals or teams. Use for planning a day, surfacing blockers, reviewing user-provided entries, or drafting a check-in without assuming prior history.
skillhub-cli
Connect an Agent to a SkillHub registry and use the official SkillHub CLI to search, install, list, or explicitly upgrade SkillHub skills. Use when a user asks to connect SkillHub, install a SkillHub skill, or manage skills previously installed from SkillHub.
anysearch
Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.