ziwei
Skill1 starsChanged 12 days agoMITView on GitHub
使用 Prophet 紫微 JSON 分析命身宫、星曜四化、三方四正与运限,逐分支引用证据并审核异说;不凭空排星。
6 other projects use a version of this.
Adopted by
Most recently taken up by
- AstralumeLan/Prophet-toolkitword for word, first seen Nov 8, 2026
- songgoldenwind-crypto/ziwei-skillstheir own version, first seen Nov 1, 2026
- CharlotteShen/astro-tarot-bazi-divination-skillstheir own version, first seen Oct 8, 2026
- LucasYanzy/DAshitheir own version, first seen Oct 5, 2026
- konglong87/xuanxue-skillstheir own version, first seen Sep 27, 2026
- shanrichard/ziwei-skilltheir own version, first seen Jul 27, 2026
Other versions6 projects use a version of this.
Word for word · 1
- AstralumeLan/Prophet-toolkit★ 1100% same
Edited · 0
None found.
Wrote their own version · 5
- shanrichard/ziwei-skill★ 9same name
- songgoldenwind-crypto/ziwei-skills★ 4same name
- konglong87/xuanxue-skills★ 3same name
- LucasYanzy/DAshi★ 1same name
- CharlotteShen/astro-tarot-bazi-divination-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- baziSkill
- cross-checkSkill
The file
Files
紫微分析
先读取 engine.name/version/rules、warnings 和 input。保留原始钟表时间、精度和所有候选;不把计算样本写成确认出生时间。以下路径以原始 CLI JSON 为根;[0] 仅示范索引,实际逐分支替换,不支持通配符。未返回的字段应写“未计算”,不能凭记忆补盘。
按问题选择工具 → 制定阶段计划 → 排盘 → 按条件检索本地语料 → 带证据回答 → Critic 复核。复用已有有效命盘,避免反复排盘和整库灌入上下文。技能本身不调用模型或网络,不改变核心规则。
工具与字段
bin/prophet ziwei chart ... --year YYYY;指定目标日的流限使用 ziwei horoscope --person CODE --date YYYY-MM-DD。
临时输入的 horoscope 用 --birth-date 指定出生日期;--date 永远是目标日。
先读 字段与规则。精确盘字段位于根下;约略盘逐 $.branches[i] 处理,不能将不同候选的星曜合成一盘。
分阶段分析
- 命身宫:核对命宫地支、身宫地支和十二宫顺序;以宫名找到宫索引再引用。身宫不是凭年龄移动的命宫。
- 主星:逐宫读主辅星及亮度学校;空宫、借星只能作为具名流派的条件解释。不得凭记忆添加未返回的星。
- 四化:生年四化来自
sihua;与流限flows.*.mutagen分开,不混成同一层。核对化星及落宫后才讨论主题。 - 三方四正:按十二宫地支关系列本宫、两三合宫与对宫,再读取这些宫的实际星曜。说明采用规则及推导,不把对宫当本宫。
- 大限流年:核对大限范围、年龄口径和目标年;chart 的 annual 是指定年七月一日参考值,完整流限另调用 horoscope。区分本命、限、年;不给无触发条件的确定事件。
同主题先提出本体系判断和相反解释,再参与跨体系对照。Renhuai 内部也使用 iztro,二者一致不能算两份独立证据。
Critic / evaluator
输出前另作一轮审核,返回 pass/revise/insufficient 和问题清单:
- 每条盘面事实是否来自当前人物、当前分支的实际工具输出?检查字段值,禁止编造星曜、干支和坐标。
- 每条解释是否有具体
json_paths、具名school/rule_id、检索query或真实段落id?查询只是待核出处,不能冒充已取得原文。 - 检索后是否核对段落、相邻上下文、条件、来源及许可?引用不等于规则适用;不虚构引文或段落 ID。
- 是否区分计算事实、经典规则和分析推论?计数不是旺衰评分,星曜标签不是人生事件。
- 是否列出支持和不支持条件、相反解释,以及约略时间改变的部分?不得把单分支结论写成区间共识。
- 是否混用流派、时间规则或把相同底层库重复计为独立证据?实际经历只能作外部反馈,不能伪装为推算。
- 标注 hallucination(不存在字段、虚构出处、无证据断语)、uncertainty(输入/规则/解释分别列出)和 counter-interpretations。缺证据时删改结论,不能只降低 confidence 后保留断言。
输出模板
按下列结构输出分析;evidence 中每条均遵循 证据协议,避免留下占位值:
对象与问题;engine / rules / warnings;时间精度与分支范围
盘面事实:字段路径 → 实际值
逐阶段分析:判断 → 成立条件 → evidence item → 反证/异说
稳定结论 / 分支结论 / 未决问题
Critic:status、hallucination、uncertainty、counter_interpretations、修订项使用 prophet evidence check FILE 检查 {chart: 原始命盘, evidence: [...]}。
验证通过只保证结构和字段存在,不保证解释正确;人工 Critic 仍需检查语义。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

