Skip to main content
Glama
ChesterRa

命盘 Mingpan

by ChesterRa

大六壬排盤

daliuren_basic

Calculate a Da Liu Ren divination chart from Gregorian date/time, returning the plates, four lessons, three transmissions, and twelve generals in Markdown for AI interpretation.

Instructions

大六壬排盤(基礎排盤)。

大六壬是中國古老三大占卜術之一,與奇門遁甲、太乙神數並稱三式。

【推薦用法】直接輸入公曆起課時間,系統自動推得節氣、月將、日干支、時干支:

  • year/month/day/hour(+ 可選 minute、timezone、isLunar)

【專家模式】也可顯式指定曆法量(一般無需使用):

  • jieqi:節氣(如:立春、驚蟄,簡繁均可)

  • dayGanZhi / hourGanZhi:完整干支(如:甲子、乙丑)

返回完整的六壬盤面:

  • 天地盤(月將加時辰起盤)

  • 四課(日干支推演)

  • 三傳(九宗門推演:賊尅、比用、涉害、遙尅、昴星、別責、八專、伏吟、返吟)

  • 十二天將(貴人、螣蛇、朱雀、六合、勾陳、青龍、天空、白虎、太常、玄武、太陰、天后)

  • 格局判斷

  • 神煞(日馬、月馬、丁馬、華蓋、閃電)

本工具只負責排盤,斷課解讀交給 Agent。

輸出為 Markdown 格式,便於 AI 分析解讀。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dayNo起課日期(1-31)
hourNo起課時辰(0-23)
yearNo起課年份(公曆,推薦用法)
jieqiNo【專家模式】節氣(如:立春、驚蟄,簡繁均可)
monthNo起課月份(1-12)
minuteNo分鐘(0-59),默認 0
isLunarNo輸入是否為農曆,默認 false
timezoneNoIANA 時區名(默認北京時間)
dayGanZhiNo【專家模式】日干支(如:甲子、乙丑)
hourGanZhiNo【專家模式】時干支(如:甲子、乙丑)
lunarMonthNo【專家模式】農曆月份(1-12)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changedv0.1.8
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / day
      Added value: +{
      +  "description": "起課日期(1-31)",
      +  "maximum": 31,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / dayGanZhi / description
      Previous value: -"日干支(如:甲子、乙丑等)"New value: +"【專家模式】日干支(如:甲子、乙丑)"
    • removedInput schema / properties / guirenMethod
      Removed value: -{
      -  "default": 0,
      -  "description": "貴人起法:0=標準, 1=另一種",
      -  "enum": [
      -    0,
      -    1
      -  ],
      -  "type": "number"
      -}
    • addedInput schema / properties / hour
      Added value: +{
      +  "description": "起課時辰(0-23)",
      +  "maximum": 23,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / hourGanZhi / description
      Previous value: -"時干支(如:甲子、乙丑等)"New value: +"【專家模式】時干支(如:甲子、乙丑)"
    • addedInput schema / properties / isLunar
      Added value: +{
      +  "default": false,
      +  "description": "輸入是否為農曆,默認 false",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / jieqi / description
      Previous value: -"節氣(如:立春、雨水、驚蟄等)"New value: +"【專家模式】節氣(如:立春、驚蟄,簡繁均可)"
    • changedInput schema / properties / lunarMonth / description
      Previous value: -"農曆月份(1-12)"New value: +"【專家模式】農曆月份(1-12)"
    • addedInput schema / properties / minute
      Added value: +{
      +  "description": "分鐘(0-59),默認 0",
      +  "maximum": 59,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • addedInput schema / properties / month
      Added value: +{
      +  "description": "起課月份(1-12)",
      +  "maximum": 12,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedInput schema / properties / timezone
      Added value: +{
      +  "description": "IANA 時區名(默認北京時間)",
      +  "type": "string"
      +}
    • addedInput schema / properties / year
      Added value: +{
      +  "description": "起課年份(公曆,推薦用法)",
      +  "maximum": 2100,
      +  "minimum": 1900,
      +  "type": "integer"
      +}
    • removedInput schema / required
      Removed value: -[
      -  "jieqi",
      -  "lunarMonth",
      -  "dayGanZhi",
      -  "hourGanZhi"
      -]
  2. First observedv0.1.3

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses that this is a pure computation/chart-casting tool with no interpretation ('只負責排盤') and specifies the output is Markdown for AI consumption. It does not mention permissions or error behavior, but for a side-effect-free calculation that gap is minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Headings and bullet lists front-load the recommended usage, and every section maps to something actionable. It is somewhat long, and the brief 三式 background sentence is ornamental, but the size is defensible for an 11-parameter tool with two input modes and no output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description compensates by enumerating the returned chart components and the Markdown format, which is exactly what the agent needs to plan interpretation. The absence of any tool-selection guidance relative to its many siblings is the one remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real value by grouping the 11 flat parameters into two coherent modes (recommended Gregorian year/month/day/hour vs expert jieqi/dayGanZhi/hourGanZhi) and noting simpl./trad. character acceptance for jieqi, semantics the schema alone does not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource (排盤 for 大六壬) and explicitly bounds scope: '本工具只負責排盤,斷課解讀交給 Agent'. It also situates the tool within the 三式 tradition and enumerates exactly what the chart contains (天地盤、四課、三傳、十二天將、格局、神煞), so an agent can distinguish it from qimen/bazi/ziwei siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly separates a 推薦用法 (input Gregorian time, system derives the rest) from a 專家模式 (explicit calendar quantities, '一般無需使用'), which tells the agent which parameters to reach for. What it does not do is explain when to choose this tool over the other 17 divination siblings for a given question, leaving tool-selection to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.