Cell Sci Magic logo

Cell Sci Magic

Community
yrui-cmd
cell_sci_magic

Cell 科研玄学:实排个人四柱,分层估算月令旺衰、格局线索与扶抑喜用候选,计算起运及大运,并结合运年流月比较投稿时间。特殊格与不稳定取用不强判,不用通用或固定冲合分冒充完整命理;民俗取象不预测录用。

Overview

Publisheryrui-cmd
RepositoryCell
Skill namecell_sci_magic
Stars
111
Forks
1
Bundled files
29
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 29 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by yrui-cmd on GitHub. Read the source before you install it.

Installation

Install the Cell Sci Magic AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/yrui-cmd/Cell/tree/main/skills/cell_sci_magic
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/yrui-cmd/Cell.git /tmp/Cell
mkdir -p .claude/skills
cp -r /tmp/Cell/skills/cell_sci_magic .claude/skills/cell_sci_magic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cell Sci Magic in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cell Sci Magic on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cell Sci Magic is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cell 科研玄学|个人八字投稿择时

主要功能与客户入口

主要功能是根据出生日期、出生时间与出生地排四柱,再结合个人命盘及现实安排选初投、修回或基金提交时间。使用本包 scripts/personal.py;个人八字资料不足时停止个人计算,不能默认用通书结果替代。只读取本包知识和脚本,不转调其他 Skill。

客户可直接说:

用 cell_sci_magic,按我的生辰八字选未来七天投稿时间。我出生于【年月日,阳历/农历,农历注明是否闰月】【当地几点几分】,出生地【国家、省市】,现在在【城市】,稿件【何时准备好】,最晚【日期时间及其时区】提交。

首次缺资料时,集中询问:出生年月日和阴阳历、出生钟表时间及大致误差、出生城市、当前实际投稿城市,以及传统排运参数(或明确顺逆)。具体地点需能确定IANA时区与经度;可以用有来源的城市中心经度近似,明确来源与近似值,不猜经度,不要求详细地址。同名城市、历史计时或夏令时歧义仅澄清必要项。不索取姓名。排大运需要传统排运参数yun_gender(male/female),或用户明确指定yun_direction(forward/backward),不可根据姓名猜性别或顺逆。此参数只用于传统排运算法。

只说“未来七天个人投稿时间”但没给生辰:先收集上述资料,不能给个人分数。用户明确只想看通用日期时才用 oracle.py rank,并标明“不含个人八字”。五方通用请求走 regional.py public。

已实现的个人八字流程

  1. 验证出生资料、真实时区、夏令时和农历闰月,计算出生UTC瞬间。
  2. 出生地经度与NOAA均时差近似校正出生真太阳时,实际瞬间定节气年/月,当地太阳时定日/时。立春换年、节令换月、23点换日(sect=1)。
  3. 实排年、月、日、时四柱,输出日主、各柱天干五行、藏干、十神。历法库与版本检查先执行。
  4. 近似太阳时误差缓冲为2分钟,叠加用户出生时间误差;跨越四柱边界时不做唯一盘面和推荐,先核实时间或明确分别排盘。
  5. 按当前投稿地点的经度计算候选日时四柱,切开太阳时辰及节气边界,在近似边界留缓冲。结合准备完成时间、截止、不可用时间与当地09:00—21:00筛选。
  6. 用 scripts/natal_analysis.py 估算月令季节力量、四柱透干与藏干生扶制泄、通根及支持比例;公开系数和敏感性试算,不把工程比例说成客观旺衰概率。
  7. 从月令藏干透出、建禄/阳刃、官杀印食等关系列格局候选与结构线索,分别列“月令格局用神”与“扶抑用神候选”,不能混用术语。按强弱给条件喜忌,绝不按五行缺项补用神。
  8. 按出生实际瞬间到顺/逆相邻节计算起运,库sect=2;传统年干阴阳与排运参数定顺逆,也支持明确指定顺逆。给出12步大运,起运实际时刻按十周年换运,传播出生时间误差。
  9. 每个候选加入当时大运、立春流年和节令流月,重新估算生扶制泄和扶抑偏好;分别比较本命与运势上下文两种情境,取较保守比较值。格局辅助路径只有与扶抑喜向一致时参与。
  10. 候选日时干支按上述喜忌贡献排序,冲合仅作0.2权重辅助;撤销v1固定印星/食神奖励。通书日忌和候选日支冲本命日支仍排除。个人比较值与通书分分别输出。
  11. 三合/三会字齐、天干合、月令多透或逢冲、极端从格/专旺可能、旺衰敏感性跨类、中和未定用或换运不确定,标记review_required。只展示待复核分析,不输出唯一首选、不暗回退v1/通用。默认免确认不代表允许强判存疑事项。

方法见 references/analysis-v2.md、rules/analysis-v2.json;出生排盘方法仍见 references/personal-v1.md。本版覆盖四柱—旺衰估算—格局线索—扶抑取用候选—起运大运—运年流月—时窗比较的分析链,但不是全流派、全命局的专家判断。不得宣传“完整八字大师”“喜用神唯一正确”或格局已必成;复杂格局成败、合化从化与逐日司令调候尚未自动裁决。

执行与保存

无需用户确认评分规则,不执行 approve、不伪造批准记录。缺出生资料与缺计算依赖是实际缺口,不能以免确认跳过。出生数据仅为本次本地计算使用;客户未要求保存时用临时输入文件,任务后移除临时文件,不把真实生辰写入技能目录、测试、日志或安装包。JSON完整依据包含生辰派生字段,仅在客户需要时导出到其工作区。

已知会话时区和日期优先;“未来七天”默认明日起7天,执行主机日期不同则显式传 --start/--end。未知当前投稿地点须询问,不能拿出生地当现居地。无已知截止可先计算并注明;默认最短窗口20分钟,截止前30分钟缓冲。正式截止、材料完备和作者安排优先。

命令

Windows 使用 python -X utf8。输入schema与示例见 references/personal-v1.md。

bash
python -X utf8 scripts/oracle.py doctor
python -X utf8 scripts/personal.py chart --profile 出生资料.json
python -X utf8 scripts/personal.py rank --profile 出生资料.json --timezone Asia/Shanghai --longitude 116.4 --days 7
python -X utf8 scripts/personal.py rank --profile 出生资料.json --timezone Europe/Berlin --longitude 13.405 --event revision --days 7
python -X utf8 -m unittest discover -s tests

personal rank 支持 --start、--end、--days(1—93)、--ready-at、--deadline、--deadline-buffer、--exclude-date、--block(带UTC偏移起止ISO/ISO)、--minimum-minutes、--top、--output(Markdown)、--audit(JSON)。birth timezone、出生经度在profile内;当前投稿timezone、longitude在CLI中,不能混淆。

通用与其他能力

  • oracle.py rank:通书通用择时,不含个人八字。支持初投、修回、基金、答辩、会谈、签约、出行、搬家、实验安排及一般问事。通书日宜忌60/黄道日15/吉时25,中性事件30;不把分数叫个人匹配度。
  • regional.py public:默认仅北京时间明天的通用与五方结果,按省份或方位筛选。五方只辅助同分排序,不是个人排盘。
  • doctor、rules、Markdown/JSON导出;五行、八卦、八字、奇门和六爻知识解释;按真实结果改写口播。不运行奇门、紫微、六爻起卦,不预测审稿人行为,不操作投稿系统,不自动建定时任务。
  • 通书计算细节见 references/method.md、references/scoring-v1.md;五方见 references/regions-v1.md;概念见 references/systems.md;输入见 references/inputs.md;源资料见 references/sources.md。

输出

明确标记“个人八字”或“通用不含八字”。个人报告先列输入时区、经度、校正时刻和四柱,再给首选与备选、个人栏目分/通书分及可核验的冲合或十神依据。报告必须包含旺衰依据与敏感性、格局候选、分层用神、大运顺逆与起运、当时大运/流年/流月及候选取用贡献;存疑时给待复核解释。不输出未计算的命理结论,不暗用通用数据冒充个人化。无合格候选则说明没有,不延长用户范围或错过截止。末尾一句:民俗取象,仅供娱乐;分数不是录用概率,稿件完备与正式截止优先。

通用输出:客户截图所含字段

通用查询默认采用日期块,不输出评分表、判词或完整命理分析。每个日期显示:公历年月日、星期;其下每个可用时窗显示传统时辰名称、具体HH:MM—HH:MM、位置。示例结构仅是格式,不提供预填吉日:

公历【年】年【月】月【日】日(周【几】) 【地支】时(【起始】—【结束】) 位置:【实际计算方位】方

日期、时辰、星期与方位全部实际计算,不能抄用户截图中的日期或方位。“位置”固定采用lunar_python当前时辰的时喜神方getTimePositionXiDesc,公开此口径;截图没说明其取法,不能声称与截图算法相同。时喜神方与东方/南方等五方地域栏目不同,也不是个人喜用方。时辰及方位按北京时间通书,海外具体时段显示当地时间并说明北京时间时辰口径。

oracle.py rank与regional.py public默认--report-style brief,保留--report-style detailed查看原评分与详细报告,JSON事实保留分数和方位来源。普通通用请求用oracle.py;只有明确请求五方才分区,五方全部的brief先呈现全国通用,逐区对比用detailed。个人八字报告继续使用完整分析,不套用此简版。不得用截图里个别录用评论推断效果或承诺录用。

通用每日默认范围

每次通用投稿查询默认只给北京时间明天一天(当天日期+1),不自动扩展到未来七天、不创建每日定时任务。“通用”“通用投稿”“投稿通用时间”“按截图格式给结果”均按明天通用解释;只有用户明确要求个人八字才进入个人资料流程。明确指定其他日期或日期范围时按用户所指执行。

oracle.py rank与regional.py public未传日期范围时均默认明天一天;宿主会话日期与主机不一致时显式传--start和--end为同一明天日期。沿用公历日期、星期、时辰、具体时段与位置的简版格式。明天没有合格时段就说明没有,不拿后天或下周日期补位。个人八字查询的日期规则单独保留。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cell Sci Magic AI skill do?

Cell 科研玄学:实排个人四柱,分层估算月令旺衰、格局线索与扶抑喜用候选,计算起运及大运,并结合运年流月比较投稿时间。特殊格与不稳定取用不强判,不用通用或固定冲合分冒充完整命理;民俗取象不预测录用。

Why use Cell Sci Magic on TypingMind?

Because you install it once and use it with any model. Cell Sci Magic is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cell Sci Magic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/yrui-cmd/Cell/tree/main/skills/cell_sci_magic. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cell Sci Magic?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cell Sci Magic?

As many as you like. As long as a model supports skills, you can use Cell Sci Magic with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cell Sci Magic AI skill free?

Yes. It is published on GitHub by yrui-cmd under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇