cross-check
Skill1 starsChanged 12 days agoMITView on GitHub
以 Prophet 独立运行至少两个体系,保留分支和规则,轻量比较共识、冲突与独有信息;仅综合分析请求适用。
3 other projects use a version of this.
Adopted by
Most recently taken up by
- AstralumeLan/Prophet-toolkitword for word, first seen Nov 8, 2026
- jame-hv/brse-toolkittheir own version, first seen Nov 6, 2026
- xavierforge/skillstheir own version, first seen Aug 19, 2026
Other versions3 projects use a version of this.
Word for word · 1
- AstralumeLan/Prophet-toolkit★ 1100% same
Edited · 0
None found.
Wrote their own version · 2
- xavierforge/skills★ 4same name
- jame-hv/brse-toolkit★ 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
- ziweiSkill
The file
Files
轻量跨体系工作流
默认一个代理顺序完成,无需模型服务或额外依赖。运行:
bin/prophet cross-check run --person S01
bin/prophet cross-check run --person S02 --systems bazi,ziwei,western --include-charts- 明确对象、问题和时间精度。helper 经共享输入解析后独立调用各体系,东方默认统一 clock;可用
--time-standard true-solar。西占始终钟表转 UTC。规则差异仍须读取各 engine。 - 读取 summaries 各自的 facts / json_path、engine、warnings、invariants、branch_count。默认只携带精简事实,需要审计时才 include-charts。所有候选保留,不选中点。
- 分别使用 bazi / ziwei 技能形成短摘要,未看其他体系解释之前先固定本体系结论、证据、条件、反证。西占只解释实际算出的星位宫位,不将东方符号直接对应星座。
- helper 的 comparison 只比较可匹配的事实键。四柱集合相同仅为历法一致;unique 表示无同键可比,绝不等于其他体系反对。集合不同可能来自边界、代表小时、换年规则或分支取样,不自动认定计算错误。
- 对解释另建
agreements/conflicts/unique三组。每项写主题、各体系原判断、独立 evidence、条件与时间范围、尚待解决的问题。不同体系不强行投票;同源计算不能升级置信度。不把传统跨体系共识写成预测已获验证。 - Critic 检查人物一致、字段引用、规则差异、区间覆盖、虚构引文和相反解释。结构检验用 evidence check;它不检查语义。最终保留未决冲突。
可选深度模式仅在复杂问题确有需要且用户允许代理协作时使用:为各体系分配独立分析者,仅提供本体系原始盘与问题;汇总者对照摘要,评审者回查证据。不要为了普通问答默认启用多代理;不把它引入确定性核心。
完整数据协议、命令及局限见 工作流说明。
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.

