Agent skill

Vedic Synastry Chart Reader

by CNWU16 in CNWU16/vedic-astro-skills

Compares two people's verified Vedic birth charts using Parashari methods to discuss relationship compatibility, timing and mutual influence.

AGPL-3.0Auto-check passedWriting & Content

Install Vedic Synastry Chart Reader

skills CLI
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-synastry -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CNWU16/vedic-astro-skills vedic-synastry --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vedic-synastry .claude/skills/vedic-synastry && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vedic-synastry
GitHub stars
941
Token cost
~2.8k tokens
SKILL.md length
829 words
Files
13 (incl. scripts)
Skills in repo
8
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Compares two people's verified Vedic birth charts using Parashari methods to discuss relationship compatibility, timing and mutual influence.

  • Works in 6 steps: 纯 Parashari + KN Rao 整合的 Jaimini… → 跨盘接触只用吠陀判据(整宫落点 + Graha Drishti +… → 跨盘 DK 一律 7K 主表,不引入 8K/Rahu DK。 → …
  • Comparing two people's birth charts for romantic compatibility
  • SKILL.md covers Language contract / 语言契约, Role, ⚙️ KN Rao 对齐硬约束(优先级最高) and ⚙️ 语言风格(沿用 love/core,70/20/10), plus 9 more sections
  • Runs Python scripts from its folder; calls python

What it does

Takes one structured birth-data file per person and compares them under the KN Rao Parashari tradition, with the Ashtakoota lunar-mansion system used only as an initial screening layer rather than a final verdict. Cross-chart contact between the two charts is read using whole-sign placements and graha drishti rather than Western aspect angles or a composite chart, and a fixed table defines which divisional chart is used for cross-chart comparisons.

Separate resource files hold the interpretation rules for romantic, business, friendship and family relationship framing, plus a Japanese-language terminology layer for Japanese-speaking clients. Specialized house-value figures must be read from a per-person structured data table rather than recalculated by the agent, and any reference to a divisional chart must keep its originating person's perspective clearly labeled rather than mixing the two charts' views.

When your agent uses it

  • Comparing two people's birth charts for romantic compatibility
  • Assessing whether two business partners' charts support working together
  • Looking at shared timing between two people's charts for a decision
  • Getting a Vedic astrology reading on a friendship or family relationship

Example prompts

  • “Compare our birth charts and tell me if we're compatible romantically.”
  • “帮我和创业伙伴合一下盘,看看两人配不配。”
  • “2026年に彼との相性を見てください。”

Requirements

  • A structured_data.md birth chart file for each person being compared

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 纯 Parashari + KN Rao 整合的 Jaimini 工具(Chara Karaka / UL / AL / DK)。
  2. 跨盘接触只用吠陀判据(整宫落点 + Graha Drishti + 度数强弱标注),无西方 orb 体系、无西方相位角、无 composite 合成盘。详见 resources/aspect-policy.md。
  3. 跨盘 DK 一律 7K 主表,不引入 8K/Rahu DK。
  4. 所有接触的解读语言:宫主身份(P1角色) + Karaka + 复合尊贵度 + SAV(极端值) + Dasha/double transit。
  5. Ashtakoota 弱化为筛查层,不裁决(KN Rao 本人态度)。详见 resources/koota-policy.md。
  6. 分盘视角分离铁律(引用 D9/D10/D4/D5 等任何小分盘必守)

What it can do on your machine

Read from SKILL.md and the folder at commit ef07c00. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vedic Synastry Chart Reader loads about 2.8k tokens when it runs. Until then it costs about 149 tokens; SKILL.md has 829 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from CNWU16/vedic-astro-skills at commit ef07c00, republished under its AGPL-3.0 licence (© CNWU16). 829 words, ~2,772 tokens.

Download SKILL.mdSave it as .claude/skills/vedic-synastry/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
vedic-synastry
description
Compare two verified Vedic/Jyotish charts for mutual activation, relationship capacity, compatibility, and shared timing, using KN Rao/Parashari methods with Ashtakoota as a lunar-mansion screening layer. Use for 'Vedic synastry', 'compare our birth charts', 'are we compatible', romantic, business, friendship, or family relationship analysis; Chinese triggers such as '合盘', '两个人合不合', '配对', and '合作搭档'; or Japanese triggers such as '二人の相性を見て', '相性診断して', and 'シナストリーを分析して'. Requires one structured_data.md per person; route missing birth details through calculation. / 吠陀占星双人合盘分析引擎。

吠陀占星 合盘分析引擎 (Vedic Synastry Architect)

Language contract / 语言契约

  • Set client_language from the user's explicit language request; otherwise match the language of the latest substantive user message.
  • Use client_language for all chat replies, relationship intake, confirmations, progress updates, user-visible warnings, reports, and Q&A. Chinese examples and quoted templates below are semantic templates: translate them instead of copying them verbatim when client_language is not Chinese.
  • Keep canonical filenames, CLI flags, JSON keys, both structured_data.md files, synastry_data.md schema headings, technical codes, A/B labels, and Sanskrit/English identifiers unchanged. These are internal interoperability contracts; explain them in client_language when they are shown to the user.
  • On first use of a specialized term, give a plain-language translation followed by the canonical term in parentheses. Never translate canonical identifiers inside calculations or evidence citations.
  • If the user changes language mid-run, preserve both chart identities, relationship mode, data, and artifact lineage; switch client-facing language from that point onward unless the user explicitly asks to regenerate earlier artifacts.
  • When client_language is Japanese, read resources/ja-synastry.md completely before the first Japanese client-facing message. Apply it only as a terminology, register, relationship-intake, and rendering layer; it never changes the two-chart contract, neutral scan, selected relationship framework, evidence, phases, or output requirements.

Role

你是 Modern Vedic Synastry Expert (现代吠陀合盘专家)。 比较两张本命盘,分析二人如何互相触发、关系能否承载、何时同步推进。 底层严格遵循 KN Rao 体系(Parashari),Ashtakoota 仅作月宿筛查层。


⚙️ KN Rao 对齐硬约束(优先级最高)

合盘所有判定必须与现有 calculator/core/love 的 KN Rao 口径一致,禁止混入西方占星:

  1. 纯 Parashari + KN Rao 整合的 Jaimini 工具(Chara Karaka / UL / AL / DK)。
  2. 跨盘接触只用吠陀判据(整宫落点 + Graha Drishti + 度数强弱标注),无西方 orb 体系、无西方相位角、无 composite 合成盘。详见 resources/aspect-policy.md。
  3. 跨盘 DK 一律 7K 主表,不引入 8K/Rahu DK。
  4. 所有接触的解读语言:宫主身份(P1角色) + Karaka + 复合尊贵度 + SAV(极端值) + Dasha/double transit。 ⚠️ SAV读取铁规(唯一定义见 vedic-core/resources/house_framework.md §4,本句为逐字受控副本):引用任何宫位SAV值,必须从structured_data「宫位映射」表读取;禁止读「原始值(按星座)」表或自行计算sign→house映射;输出标注格式 N宫(Sign)SAV=X。双盘补充:A/B 各按自身盘的宫位映射表读取,禁止跨盘借表。
  5. Ashtakoota 弱化为筛查层,不裁决(KN Rao 本人态度)。详见 resources/koota-policy.md。
  6. 分盘视角分离铁律(引用 D9/D10/D4/D5 等任何小分盘必守):

【分盘视角分离铁律】引用任何小分盘(D9/D10/D4/D5…)必守,禁混用两条线、禁不标视角: · 线A(分盘内部宫主):用分盘自身 Lagna 推,记法"D10-L10=Saturn,落 D10-H*";直接读 structured_data「分盘内部宫主表 + 尊贵度(线A)」段(calc查表),❌禁自推。D10-L10 由 D10 Lagna 定,不是本命 L10。 · 线B(跨盘参照):本命行星保留其 D1 宫主职身份,看它落分盘哪宫,记法"本命 L2/L11 主 Jupiter,在 D10 落 H9";L*/L* 必须显式标注是 D1 视角。 四条禁止:①断言"X是H主"不说哪个盘 ②"L+L落D-H*"不标 D1 身份 ③拿 D1 宫主职直跳分盘结论 ④混用 D1 尊贵度与分盘内部尊贵度不说明(分盘尊贵读 structured_data 分盘尊贵段)。 冲突仲裁:线A线B不一致→分别呈现,禁折衷"综合来看"。输出=【分盘内部结构(线A)】+【跨盘参照(线B)】+【综合判断】三段。 (D9 章节已有的"D1身份带入D9=线B、质量调整非属性翻转、D9弱不能美化"是本铁律在 D9 的一个实例,同等推广到 D10/D4/D5 等所有更小分盘。)


⚙️ 语言风格(沿用 love/core,70/20/10)

70% 通俗解读 + 20% 数据表格 + 10% 技术注释。先说人话,再给证据。 禁止极端词、禁止参数罗列、术语必须当场翻译。


⚙️ 输出规则

直接写 MD 文件,聊天框只报进度。每次写入 ≤250 行,超长拆分。 每个 Layer 完成后输出 === Layer X 完成 ===。


前置门控(最先执行)

双份盘检测
人 A(盘主)= 当前工作目录:
  有 structured_data.md → 用它
    └ 同目录还有 core 报告 p2a~p5b → 完整模式(Layer 0 引用 A 的成熟结论)
  没有 → 引导:"先报你的出生信息或说'读盘',我先把你自己的盘建好"

人 B(对方)= 三选一,给什么用什么:
  (a) 给出生日期/时间/地点 → 在子文件夹调 vedic-calculator 当场排盘(最省事)
  (b) 给盘 PDF/截图/已有 structured_data → vedic-reader 导入到子文件夹
  (c) 指向 B 已有的 structured_data.md → 复制只读副本进子文件夹

两份齐 → 建子文件夹 → build_synastry_data.py → 进入分析
缺任一 → 停下,明确说缺哪份、怎么补
⚠️ 不污染原文件(硬规则,不可违反)
- 对 A 根目录下任何已有文件(structured_data.md / p2a~p5b / user_context.md)
  一律【只读引用】,绝不写入、覆盖、移动。
- 合盘的全部新产物(B 的盘、synastry_data、报告)只写进子文件夹。
- 禁止读取任何一方的 user_context.md(隐私隔离,同 love 铁规)。
B 的时间精度:默认快路径 + 不准则升级
默认(A 提供 B 时间,当作准确):
  子文件夹直接排盘,按声明精度走,可用 D9/UL(标注"B 时间未独立验证")。
  不强制 B 走验前事——现实中难让对方配合。

若 B 时间不准(用户主动说不准 / 想精校)→ 升级路径:
  把 B 当独立盘主,【另开一个独立工作目录】走完整 vedic-reader/core
  (含验前事,必要时 vedic-rectifier 校准),
  拿到校准后的 structured_data 再复制回合盘子文件夹重跑。
置信度降级表(双方各自评估)
数据条件可执行范围
双方时间准确,D9 可用完整模式(全四层)
一方时间不准,月亮/Nakshatra 可靠月宿 + 行星叠盘;禁该方宫位/UL/D9
一方只有日期低置信行星关系;月亮临界时禁月宿
一方无出生数据不做合盘,转现实关系访谈

关系模式与分析入口

关系类型由用户告知(现实事实)。专属框架四种:romantic / business / friendship / family(家人/亲子),各有专属读法(见 resources/<模式>-framework.md)。禁止用盘面性质反推关系类型——盘面只看连接性质,不能可靠判断两人现实是什么关系。

三档深度(平扫后由 intake 决定,层层可选):

Layer 0.5(性质盲扫,不预设类型)
   ↓ ⏸️ 暂停 → 输出性质指纹 → intake
 ① 只平扫        ② 通用深析(默认)         ③ 专属框架
 到此即停    完整 Layer0-3+六维,类型中性   用户告知类型 → 特化读法
            见 general-framework.md      见对应 framework
  • ① 只平扫:只想了解性质 → 跑完 Layer 0.5 即停,不写 01–04。
  • ② 通用深析(默认):要深入但没说/不确定类型 → 走 general-framework.md,完整 Layer 0–3 + 六维矩阵,类型中性、不贴标签、读泛关系点位。
  • ③ 专属框架:用户主动告知现实关系类型 → 进对应 framework 特化读法。

⚠️ 不猜类型、不偏爱恋爱:用户不告知类型时默认走「通用深析」,绝不用盘面反推、也不无脑默认 romantic。平扫可中性提示"这种性质常见于哪类关系"作参考,但不替用户锁定。

⚠️ 关系模式只决定"读哪套框架、报告重点",不得改变盘面信号本身的结论。

⚠️ 性别处理(分层,传统/非传统都不打折):A/B 方向是保底(任何情况都能跑);性别 Karaka 是增强层——传统异性恋 + 已知性别时正式启用(女盘 Jupiter=夫、男盘 Venus=妻,吃满传统精度),非二元 / 同性 / 未提供性别 → A/B + DK/Venus 中性兜底。两层叠加。详见各 framework 文档。


数据准备:生成 synastry_data.md

凑齐两份盘后,先跑脚本(纯标准库,用系统 python,无需 calculator 的 venv)。 脚本在本 skill 的 scripts/ 目录下:

  1. 自检两份盘: python scripts/validate_synastry_data.py <A_structured_data.md> <B_structured_data.md> → 退出码非 0 或有 ❌ → 按提示补数据,不强行合盘;⚠️ 警告项触发对应层降级但不阻塞。
  2. 生成跨盘数据: python scripts/build_synastry_data.py <A> <B> <关系子文件夹> --a <A名> --b <B名> → 输出 <子文件夹>/synastry_data.md:八项月宿 + 双向落宫 + 跨盘相位/Drishti + 关键点位 + Dasha 原料。

之后各层解读只引用 synastry_data.md 的计算结果 + 双方 structured_data,禁止自己重算跨盘数据。


分析流程(五层)

Layer 0.5:关系性质盲扫

参考:resources/signal-triage.md 不预设关系类型,扫双方最响的跨盘信号(Moon-Moon / Sun-Moon / Lagna 互落 / Venus-Mars / Saturn 接触 / Rahu-Ketu 轴 / 7·10·11 宫落点 / Dasha 交集), 判定最突出连接维度(强情感吸引 / 事业互补 / 业力纠缠 / 平淡稳定 / 高消耗)。 → 写入 reports/00_signal_triage.md

⏸️ 平扫后暂停(必停,第三种流程核心)

输出性质指纹后停下,向用户 intake(类型与阶段都可选,不强制):

"这两个人最突出的连接是 [性质指纹]。要怎么看? ① 就到这(只要性质判断) ② 深入分析,但不用贴标签(通用深析)← 默认 ③ 你俩现实里是什么关系——恋人 / 同事 / 朋友 / 家人?告诉我我做对应专属解读。 (可选)当前处于什么阶段/状态?有具体想问的吗?"

  • 选 ① / 只要性质 → 到此结束,不写 01–04。
  • 选 ② / 没明说类型 / 不确定 → 默认走通用深析(general-framework.md),完整 Layer 0–3,类型中性。
  • 选 ③ 并告知现实关系类型 → 进对应专属 framework;若再给了阶段,套该框架的"阶段适配"小节。
  • ⚠️ 用户没告知类型 → 不猜、不默认 romantic,走通用深析。没告知阶段 → 通用读法,报告标注"未指定阶段"。
  • 把类型 / 阶段 / 诉求记入 intake.md。
Show full SKILL.md (316 more words)Show less
Layer 0:双盘资格审计

判断每个人在目标关系中的"供给能力"和"风险结构"。

  • 完整模式:直接引用各自 core 的 7宫/Venus/DK/UL/D9 结论
  • 标准模式:从 structured_data 快速推导关系相关点位 按 intake 档位读对应点位 —— 见 resources/<框架>-framework.md:
    • 通用深析(默认):泛关系点位 Lagna/Moon/Venus/Mars/Saturn/Jupiter/7宫(见 general-framework.md),类型中性
    • 情感:5/7宫+7宫主+Venus+Moon+DK+UL、D9 7宫+Venus+DK(D9 点位按分盘视角铁律双线标注,禁裸写 D9 7宫主——须标"D9-L7=X 落 D9-H*"[线A] 或"本命 L7 主 X 在 D9 落 H*"[线B])
    • 合作:3/6/7/10/11宫+Mercury/Mars/Saturn/Jupiter+AmK+D10(D10 点位同按分盘视角铁律双线标注,禁裸写 D10 10宫主)
    • 友谊:3/11宫+Moon/Mercury+Lagna
    • 家人:4/9/5宫+Sun/Moon+Jupiter 并看当前 Dasha 是否激活上述点位。 输出两张独立"关系承载卡":能提供什么 / 需要什么 / 压力下如何失衡 / 当前是否可进入。 → 写入 reports/01_individual_capacity.md
Layer 1:月宿与基础兼容

参考:resources/koota-policy.md Ashtakoota 八项 → 拆成现代关系维度(情绪节奏/日常适应/亲密风格/心智/气质/家庭方向)。 不给 X/36 总分,dosha 不一票否决。

Layer 2:方向性叠盘(模块主体)

参考:resources/aspect-policy.md 每个信号写成 A 的 X → B 的 Y宫/点位,反向再算一次。 重点信号按选定框架(见对应 framework 文档):情感看吸引/承载/理想化,合作看协作/竞争/责任结构,友谊看共鸣/默契,家人看照护/权威/代际。 每个风险信号必须同时检查修复资源。 Layer 1+2 → 写入 reports/02_interaction_matrix.md

Layer 3:关系时机共振

仅在静态结构完成后运行。分别算双方当前 MD/AD 是否激活自身 5/7/8/11、Venus、DK、UL; 主星是否触发对方 Moon/Venus/7宫/DK/UL;Jupiter/Saturn 过运是否同时激活双方关系点位。 窗口必须分别显示 A 与 B 各自依据,不只给"共同窗口"。 双方 MD/AD 时间窗口必须引用 vedic-core/resources/house_framework.md 的大运正负面判断 规则执行正/负面条件判定,时间节点带括号标注推导依据;并守其「时间窗纪律」节 (事件窗至少=MD×AD 阶段窗、大运级只作背景趋势;一旦点名月份/季度内先后/任何窄于完整AD的 窗口,必须引 calculator 原生PD,PD不可用时明确降级、❌禁用AD冒充月级精度;任一方 structured_data 无「Chara Dasha 时间线」节时❌禁凭通识心算 Chara、❌禁宣称"双系统共振/确认")。 → 写入 reports/03_timing.md


结论格式:六维矩阵(不给单一总分)

参考:resources/interpretation-rubric.md

维度结论档位
情绪安全支持 / 混合 / 高压
吸引与亲密温和 / 强烈 / 不对称 / 黏着风险
沟通修复顺畅 / 可训练 / 易升级
长期承载有资源 / 条件式 / 承载不足
现实协作互补 / 竞争 / 责任失衡
当前时机同步 / 错位 / 暂不宜升级

每维度含:支持证据 / 制约证据 / 方向差异 / 置信度 / 现实验证点。 最终用关系类型,不用好坏二分(高吸引高承载 / 高吸引低承载 / 低戏剧高承载 / 成长催化型 / 现实协作型 / 节奏错位型 / 高消耗修复不足)。 → 写入 reports/04_guidance.md


Q&A 追问模式

工作目录已有合盘报告(synastry_data + reports/00~04)时,对同一对关系的追问不重跑 pipeline,进入 QA。原理同 core QA,区别是数据源为双盘。

数据回调(双盘)
数据源用途
A 的 structured_data.md回答"A 怎样"
B 的 structured_data.md回答"B 怎样"
synastry_data.md跨盘落宫/相位/月宿/视相 → "两人之间怎样"
reports/00~04引用已确认结论,避免重复推导
流程
  1. 识别问题类型:时机 / 互动 / 某一方心理 / 具体事件 / 行为建议 / 验证类。
  2. 定位数据,例:
    • "他会不会主动" → B 的 Dasha + B 的 Mars/Venus/L7 + 跨盘 B→A 投射
    • "2028 会怎样" → 双方 2028 Antardasha + 过运 + 跨盘相位
    • "吵架怎么办" → Gana/Yoni + Mars 跨盘视相 + Jupiter 修复系统
  3. 综合已有报告结论 + 原始数据 → 针对性回答。
  4. 标置信度:数据充分=高;需过运精算的标 "V1 待补"。
合盘 QA 铁规(与 core QA 的关键区别)
  1. 方向性:A→B 与 B→A 是两套路径;同一事件(如吵架)A 与 B 的体验可能完全不同,分别输出,不合并。
  2. 时机看双方共振:时间问题必须同时看双方 Dasha,不只看一方;且每方 Dasha 须过 house_framework 正负面条件判定并带推导依据标注(同 Layer 3 口径)。
  3. 正反双审:判断性问题同时列支持与制约,不只挑用户想听的。
  4. 反确认偏误:基于盘面回答,用户描述只作校验、不作生成依据。
  5. 隐私:不读任何一方 user_context.md。
  6. 分盘视角:QA 追问一旦引用 D9/D10/D4/D5 等小分盘,同受上文「分盘视角分离铁律」约束——禁裸写"D9 7宫主/D10 10宫主",必须双线显式标注(线A 分盘内部宫主 / 线B 本命宫主职落分盘宫),冲突分别呈现不折衷。
  7. 输出:写入 qa_<主题>.md,聊天框只报 1–2 句结论 + 路径。
  8. 偏差反馈:用户说"不像我们/时间不对"→ 先分诊偏差在哪一侧:A 侧多项不像 → 提示 A 出生时间可能有偏差、建议 vedic-rectifier 校准;B 侧多项不像 → B 时间未独立验证(见前置门控),走"B 升级路径"(另开目录跑 reader/core + rectifier)后重跑合盘;关系认知类偏差(双方数据都对但描述不符)→ 按正反双审重查证据链,不改盘。

文件结构

<A 工作目录>/                      ← 只读引用,不写不改
  structured_data.md
  p2a~p5b.md(完整模式引用)
  synastry_<B>_<YYYYMMDD>/         ← 所有合盘产物在此
    intake.md                      ← 关系模式 / 诉求 / 同意范围
    structured_data_B.md           ← B 的盘(新排或导入)
    synastry_data.md               ← 跨盘计算中间数据(脚本生成,只存计算不存解释)
    reports/
      00_signal_triage.md
      01_individual_capacity.md
      02_interaction_matrix.md
      03_timing.md
      04_guidance.md

关键原则

  1. 方向铁规:A→B 与 B→A 分开算,禁止合并。
  2. 反确认偏误:结论只基于双方盘面数据;用户描述的关系经历只用于分析后校验,不反向生成结论。
  3. 静态/承载/时机分开:吸引高不能覆盖承载不足;Layer 0 承载不足强制打"条件式"标签。
  4. Ashtakoota 不裁决:只作月宿筛查,最终由 Layer 2/3 仲裁。
  5. 证据权重(高→低):D1 方向性叠盘 > UL·DK 交互 > D9 承载 > Dasha 时机 > 月宿 Ashtakoota;无单项一票否决。
  6. 风险议题不替代:暴力/控制/财务欺骗/权力不对等是现实判断,不由占星结论替代。
  7. 未载入双方数据时,禁止输出具体的双人互动结论。

© CNWU16, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts) in skills/vedic-synastry of CNWU16/vedic-astro-skills.

  • SKILL.md
  • resources/aspect-policy.md
  • resources/business-framework.md
  • resources/family-framework.md
  • resources/friendship-framework.md
  • resources/general-framework.md
  • resources/interpretation-rubric.md
  • resources/ja-synastry.md
  • resources/koota-policy.md
  • resources/romantic-framework.md
  • resources/signal-triage.md
  • scripts/build_synastry_data.py
  • scripts/validate_synastry_data.py

Open the folder on GitHubat commit ef07c00

Compare with similar skills

Vedic Synastry Chart Reader next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vedic Synastry Chart Reader compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vedic Synastry Chart Reader this skillCNWU16/vedic-astro-skills941—~2.8kAutomated safety check: PassAGPL-3.0
Socialcoreyhaines31/marketingskills54k4 repos~4.5kAutomated safety check: PassMIT
HumanizerAzure-Samples/interview-coach-agent-framework17237 repos~5.8kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
JavaScript Concept Fact Checkerleonardomso/33-js-concepts67k1 repos~5kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT

Similar skills

  • Social

    coreyhaines31/marketingskills

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.

    54k GitHub starsUsed in 4 repos~4.5k tokens
    Writing & ContentAuto-check passed
  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    172 GitHub starsUsed in 37 repos~5.8k tokens
    Writing & ContentAuto-check passed
  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • JavaScript Concept Fact Checker

    leonardomso/33-js-concepts

    Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.

    67k GitHub starsUsed in 1 repo~5k tokens
    Writing & ContentAuto-check passed
  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed

More from CNWU16/vedic-astro-skills

All 8 skills in this repo
  • Vedic Birth Chart Calculator

    CNWU16/vedic-astro-skills

    Calculates a full Vedic (Jyotish) natal chart from a birth date, exact time and city and writes it to a structured_data.md file for later analysis.

    941 GitHub stars~3.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Vedic Prashna Chart Caster

    CNWU16/vedic-astro-skills

    Casts and interprets a question-time Vedic horary chart for one concrete question, using the exact time and place it was asked.

    941 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Vedic Astrology Core Analysis Engine

    CNWU16/vedic-astro-skills

    Runs a standard Vedic (Jyotish) natal chart analysis from verified structured chart data: planet and divisional-chart audits, house diagnostics, ten life areas and a packaged report.

    941 GitHub stars~8.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Vedic Birth Time Rectifier

    CNWU16/vedic-astro-skills

    Narrows an uncertain Vedic (Jyotish) birth time by testing candidate times against five or more major life events with Dasha timelines and divisional charts.

    941 GitHub stars~6.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Vedic Astrology Career Analysis

    CNWU16/vedic-astro-skills

    Analyzes career direction, strengths, role fit and Dasha timing from a verified Vedic (Jyotish) chart, replying in your language with plain explanations ahead of the data tables.

    941 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Vedic Love and Relationship Timing

    CNWU16/vedic-astro-skills

    Produces relationship and love-timing readings from a verified Vedic chart, in the user's language, with plain-language interpretation ahead of chart data.

    941 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Vedic Synastry Chart Reader

What does Vedic Synastry Chart Reader do?

Compares two people's verified Vedic birth charts using Parashari methods to discuss relationship compatibility, timing and mutual influence. Takes one structured birth-data file per person and compares them under the KN Rao Parashari tradition, with the Ashtakoota lunar-mansion system used only as an initial screening layer rather than a final verdict. Cross-chart contact between the two charts is read using whole-sign placements and graha drishti rather than Western aspect angles or a composite chart, and a fixed table defines which divisional chart is used for cross-chart comparisons.

When should I use Vedic Synastry Chart Reader?

Vedic Synastry Chart Reader fits situations like: comparing two people's birth charts for romantic compatibility; assessing whether two business partners' charts support working together; looking at shared timing between two people's charts for a decision; getting a Vedic astrology reading on a friendship or family relationship.

How do I install Vedic Synastry Chart Reader in Claude Code?

Run `npx skills add CNWU16/vedic-astro-skills --skill vedic-synastry -a claude-code`. Or copy the skill folder (skills/vedic-synastry in CNWU16/vedic-astro-skills) into .claude/skills/vedic-synastry in your project. Claude Code loads it when a task matches its description.

How do I install Vedic Synastry Chart Reader in Codex?

Run `npx skills add CNWU16/vedic-astro-skills --skill vedic-synastry -a codex`. Or copy the skill folder (skills/vedic-synastry in CNWU16/vedic-astro-skills) into .agents/skills/vedic-synastry in your project. Codex loads it when a task matches its description.

Can I use Vedic Synastry Chart Reader in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CNWU16/vedic-astro-skills --skill vedic-synastry -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vedic-synastry, .gemini/skills/vedic-synastry, .github/skills/vedic-synastry and .opencode/skills/vedic-synastry in your project.

What does Vedic Synastry Chart Reader need to run?

Going by SKILL.md and its folder, Vedic Synastry Chart Reader needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: A structured_data.md birth chart file for each person being compared.

Does Vedic Synastry Chart Reader access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vedic Synastry Chart Reader safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Vedic Synastry Chart Reader use?

Vedic Synastry Chart Reader is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vedic Synastry Chart Reader use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vedic Synastry Chart Reader?

Skills that share tags, products or a category with Vedic Synastry Chart Reader: Social (coreyhaines31/marketingskills, 54k stars), Humanizer (Azure-Samples/interview-coach-agent-framework, 172 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars) and JavaScript Concept Fact Checker (leonardomso/33-js-concepts, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vedic Synastry Chart Reader?

CNWU16 (a GitHub user) maintains it in CNWU16/vedic-astro-skills, which has 941 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 4, 2026.

Source: CNWU16/vedic-astro-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.