TimesFM Forecasting
google-research/timesfm
Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.
Casts and interprets a question-time Vedic horary chart for one concrete question, using the exact time and place it was asked.
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CNWU16/vedic-astro-skills vedic-prashna --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/vedic-prashna .claude/skills/vedic-prashna && rm -rf skills-srcUse ~/.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/
Install the "vedic-prashna" agent skill from https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashna into .claude/skills/vedic-prashna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vedic-prashna", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashnaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CNWU16/vedic-astro-skills vedic-prashna --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/vedic-prashna .agents/skills/vedic-prashna && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vedic-prashna" agent skill from https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashna into .agents/skills/vedic-prashna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vedic-prashna", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CNWU16/vedic-astro-skills vedic-prashna --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/vedic-prashna .cursor/skills/vedic-prashna && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "vedic-prashna" agent skill from https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashna into .cursor/skills/vedic-prashna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vedic-prashna", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CNWU16/vedic-astro-skills.git --path skills/vedic-prashna--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CNWU16/vedic-astro-skills vedic-prashna --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/vedic-prashna .gemini/skills/vedic-prashna && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "vedic-prashna" agent skill from https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashna into .gemini/skills/vedic-prashna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vedic-prashna", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CNWU16/vedic-astro-skills vedic-prashnaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/vedic-prashna .github/skills/vedic-prashna && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "vedic-prashna" agent skill from https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashna into .github/skills/vedic-prashna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vedic-prashna", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CNWU16/vedic-astro-skills vedic-prashna --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CNWU16/vedic-astro-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/vedic-prashna .opencode/skills/vedic-prashna && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "vedic-prashna" agent skill from https://github.com/CNWU16/vedic-astro-skills/tree/main/skills/vedic-prashna into .opencode/skills/vedic-prashna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vedic-prashna", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
vedic-prashnaCasts and interprets a question-time Vedic horary chart for one concrete question, using the exact time and place it was asked.
This skill builds an independent astrological chart from the exact moment and place a specific question is asked, rather than from a birth chart, following a classical standard derived from the Shatpanchasika text as filtered through more recent published practice. Two further analytical stacks - Tajika and a KP-based horary method numbered 1 through 249 - stay isolated from that default layer and only run when the user explicitly turns them on, and the skill is explicit that its default layer does not provide production-grade event dates, only whether the matter looks likely to succeed, be pending, or fail, plus the conditions and timing-module availability behind that call.
Every run reads a fixed sequence of reference files in order - covering source labeling and admission rules, how to classify the question type, which house and significator apply, the applicable rule ledger, and the Moon's current-fact boundaries - and reads further optional files only when Tajika, KP, a cross-reference against a natal chart, or a follow-up on an existing chart is specifically requested.
Language handling is explicit: replies, intake questions and judgments all follow the client's own language, canonical filenames, flags, JSON keys and Sanskrit or English technical identifiers stay unchanged regardless of language, and any specialized term gets a plain-language gloss alongside its canonical name on first use; mid-run language switches keep the existing chart data and stack boundaries intact unless the user explicitly asks to regenerate earlier results.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c1a94c3. It shows what the files ask for, not the result of running them.
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.
Ships 7 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Vedic Prashna Chart Caster loads about 3k tokens when it runs. Until then it costs about 147 tokens; SKILL.md has 858 words of instructions outside code blocks.
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.
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.
The full file from CNWU16/vedic-astro-skills at commit c1a94c3, republished under its AGPL-3.0 licence (© CNWU16). 858 words, ~2,979 tokens.
.claude/skills/vedic-prashna/SKILL.md (or your agent's skills folder). This skill also uses 23 other files; get the full folder from GitHub.client_language from the user's explicit language request; otherwise match the language of the latest substantive user message.client_language for all chat replies, intake questions, confirmations, progress updates, user-visible warnings, judgments, 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.structured_prashna.md and optional-stack schema headings, technical codes, and Sanskrit/English identifiers unchanged. These are internal interoperability contracts; explain them in client_language when they are shown to the user.client_language is Japanese, read resources/ja-prashna.md completely before the first Japanese client-facing message. Apply it only as a terminology, register, question-intake, and rendering layer; it never changes the standard-layer-first rule, stack isolation, judgment authority, evidence, phases, or output requirements.用一个具体问题产生时的时间和地点建立独立提问盘。默认层是:
Shatpanchasika-rooted classical Prashna,经 KN Rao/Bharatiya Vidya Bhavan 实践兼容性筛选。
不要把它写成“KN Rao 自创的完整 Prashna 体系”。KN Rao 的公开材料支持谨慎使用 Prashna、有限 snapshot 实例及其对 Shatpanchasika 的认可,但不支持把他的本命 Jaimini、Dasha、分盘或 SAV 工具自动迁入提问盘。
默认层回答:
时间副层不改三档;不成档不给时间,也不承诺精确到某天某时。
描述题(失物在哪、什么方向多远、是谁拿的)、雨季天气、胎儿性别、父亲是否在外地 只给原文查表结果,原文歧义两说并列,不出三档、不给时间。
按顺序完整读取:
resources/standard-layer.md:来源标签、准入、白名单;resources/question-taxonomy.md:单问与 A/B/C 支持级;resources/house-karaka-map.md:一个主事项宫和专题入口;resources/judgment-rubric.md:适用规则账本和三档组合;resources/moon-policy.md:Moon 当前事实的使用边界;resources/timing-layer.md:时间副层(只在成/悬档运行)。只在用户显式启用时读取:
resources/tajika-optional.mdresources/kp-optional.mdresources/cross-natal-policy.mdresources/qa_rules.mdvedic-calculator/scripts/engine.py;不向共享 engine 增加
Prashna、Tajika、KP 或 Void 字段。scripts/format_prashna_standard.py 生成;禁止调用共享本命
formatter.py 后再删段。prashna_<yyyymmdd_HHMMSS>_<label>/,文件名
structured_prashna.md 和 prashna_judgment_<label>.md。时间副层只在该目录
增加 timing_overlay.md;显式 Tajika overlay 只在该目录增加
tajika_overlay.md。KP 只写入独立 kp_horary_<yyyymmdd_HHMMSS>_<label>/,文件名 structured_kp.md、
structured_kp.json 和 kp_judgment_<label>.md。user_context.md。scripts/build_timing_overlay.py 生成:标准 builder 不导入
它,它也不导入 Tajika/KP。prashna_* 目录;追问只沿用当前盘。不得消费或输出:
P-I.3 注的
Ayer 功能吉凶,从被占据/照射的星座起算,不是 P1);只允许 rising Navamsa(序号、座主及座主标签)与 Lagna 所在 drekkana 两项有限数据,
因为 P-I.4、P-I.7、P-VI.1~2、P-VI.4、P-VII.13 明确使用它们;禁止由此展开
完整 D9、D3 解读。
必收:
| 输入 | 规则 |
|---|---|
| 具体问题 | 一个可观察结果;不能同时问两个独立事项 |
| 提问时刻 | 显式时刻,或用户说“现在”;保留秒和可用的小数秒 |
| 提问地点 | 城市或经纬;必须能确定 IANA 时区 |
执行:
question-taxonomy.md 澄清单问;question-taxonomy.md §2.7 归到一行,求职/考试类按 §2.8,
房屋、出行、返回、疾病、名誉、谈判、投资、亏损、开庭、失物找回等按 §2.12;
操控/打听类不判,一句话说明并给替代问法;
描述题、天气按 §2.10/§2.11 查表;生死、寿命、读心、他人隐私按 §2.13 不判;进入下一阶段条件:问题唯一、支持级为A或B(或为查表题)、时间地点完整。
运行:
python scripts/build_prashna_data.py \
--datetime "<YYYY-MM-DD HH:MM[:SS[.ffffff]]|now>" \
--lat <lat> --lon <lon> --tz "<IANA>" \
--question "<single observable question>" \
--label "<kebab-case>" --out-parent "<parent>"build_prashna_data.py 只读共享 engine,并用 Prashna 专用 formatter 输出白名单。
检查 structured_prashna.md:
若输入误差可能改变 Lagna 或 rising Navamsa,标记 输入敏感 并取得更准确输入;
不能声称城市中心近似必然不影响结论。输入敏感性只影响实际消费该字段的规则;
若本题账本不使用 rising Navamsa,须分别写“该字段敏感”和“主结论所用 D1 结构
是否稳定”,不得把两者合成一个模糊置信度。
进入下一阶段条件:产物存在、默认白名单无越权字段、敏感性已处理或明确降置信度。
house-karaka-map.md 选择一个主事项宫;P rule_id;question-taxonomy.md §2.7/
§2.8/§2.12 和 house-karaka-map.md 取 rule_id 与事项宫;structured_prashna.md 宫表的 Ayer 功能吉凶标签
(standard-layer.md §2.1);正文点名行星的规则按点名读,不换标签;judgment-rubric.md §10 输出。建立并在聊天和判读单中完整显示:
| rule_id | 支持级 | 适用理由 | 原始证据 | 方向 | 权重 | 冲突 |
|---|
规则账本只消费 structured_prashna.md 白名单。没有 rule_id 的解释不能进入结论。
进入下一阶段条件:至少一条适用主规则,所有规则有范围和原始字段,没有 U/M/T/KP
混入默认账本。
读取 moon-policy.md:
禁止:
进入下一阶段条件:Moon 每条判断都说明适用 rule_id,或明确标为背景。
严格按 judgment-rubric.md:
P,且无同级救援。单一行星、单一宫位、单一缺失或单一强弱因素不得全局否决。 查表题不出三档。
输入敏感只有在可能改变本题账本实际使用的 Lagna、rising Navamsa、事项宫或宫主 结构时才能影响档次。未被本题规则消费的临界字段只报告,不改票。
成败档次与时间副层分开:时间远近不改档,给不出精确日期也不把“成”降为“悬”。
进入下一阶段条件:结论可从已显示账本逐条复核。
读取 timing-layer.md。结论为成或悬时运行:
python scripts/build_timing_overlay.py \
--datetime "<与 Phase 1 完全相同>" \
--lat <lat> --lon <lon> --tz "<IANA>" \
--matter-house <1-12> --mode general|return \
--verdict favorable|pending \
--out-dir "<当前 prashna_* 目录>"--mode 按 timing-layer.md §4 取;人的归来/到达题用 return;
查表题不运行。进入下一阶段条件:成/悬档已有 timing_overlay.md,或不成档已写明不给时间。
写入 prashna_judgment_<label>.md,并在聊天中显示支持级、规则账本、结论和
时间。固定结构:
# Prashna 判读单:<问题>
## 一、先说人话
**结论**:[成/悬/不成;紧跟普通语言解释]
**更可能发生什么**:<可观察结果,不写术语>
**主要阻力**:<现实含义,不写宫位或行星名称代替解释>
**现在能做什么**:<可执行建议>
**大概什么时候**:<成:约……;悬:如果能成,大约……;不成:不给时间及白话原因>
## 二、这张盘的范围
**提问时刻/地点**:
**来源支持级**:[A/B;说明这是来源覆盖,不是概率]
**输入稳定性**:[本题实际消费字段稳定/敏感及原因]
**体系状态**:[标准层/实验候选]
## 三、现实条件
**利好**:
**阻力**:
**建议**:
## 四、时间
<成/悬:摘 `timing_overlay.md` 的主时间、最近的触发日和参考;不成:不给时间及原因>
## 五、适用规则账本
| rule_id | 支持级 | 适用理由 | 原始证据 | 方向 | 权重 | 冲突 |
## 六、Moon 当前事实
<专题输入或背景;说明 rule_id>
## 七、体系边界
默认层不含 natal Dasha/Chara Karaka/SAV/完整分盘/Transit/Tajika/KP。查表题的判读单:“一、先说人话”用白话写查表结果,两说都写;“二、这张盘的范围”
照常;“三”~“五”合并为一张查表(judgment-rubric.md §10);不写三档和时间。
天气条件不满足时写“原文无反面判据”,不写“不会下雨”。
语言要求:先说人话,再列证据;术语出现即翻译;不使用极端或宿命化措辞。判读单
开头必须让不懂占星的用户直接看懂“更可能发生什么、主要阻力是什么、现在能做什么、
大概什么时候”。“先说人话”一节禁止出现未经翻译的行星名、宫位号、rule_id、
Yoga 名称、mixed、promise、cusp、sub-lord、Itthasala 或生产状态码;
这些只能放在白话结论之后的核对区。不能用“混合配置”“支持级 B”或“实验候选”
代替事件结论,必须先说明它们在现实中意味着什么。
情感类问题(复合、联系、分手后等)的安抚写在“先说人话”里,守六条:
默认关闭。只有用户显式要求 Tajika/Itthasala/applying-separating 时才读取
tajika-optional.md。
先完成标准层 Phase 2,取得 Lagna lord 和唯一事项宫主,再运行独立
scripts/build_tajika_overlay.py。不得在标准 builder 上增加
--enable-tajika。查表题、不判题,以及问者星与事项星为同一颗(事项宫为 1 宫
或与 Lagna 同一座主)时不运行,按 tajika-optional.md 用一句白话说明,不拿
Karaka 或其他宫主顶替。
当前实现按 Tajika Nilakanthi 2.3–59 输出十六 Yoga 分类,并保留
Uttama/Madhyama/Sama/Adhama 的 Kamboola 16 档、严格 Shunyamarga、
Radda/Durapha 优先级及换座候选。它仍是实验候选,不能进入默认主结论。
只有主星直接 Itthasala 才可显示原典“度差 × 12 日”比例候选;这不是天文保证,
也不得进入标准层。它和标准层时间副层来自不同体系,不互相校正,主答案以判读单
§四 为准。全部出版例盘与边界测试完成前不得解除实验标签。
tajika_overlay.md 同时承担人类可读副层判读:必须先说直接接触、过程修正、
现实含义和 timing 状态,再显示十六 Yoga 明细;Yoga 名称第一次出现时必须紧跟
白话含义,不能把十六项布尔表当作判读;“先说人话”一节不得出现 deeptamsha、
Yoga 名称或原始状态码;仍不得生成标准层三档结论。
默认关闭。只有用户明确要求 KP/sub-lord 时才读取 kp-optional.md。经典 KP
Horary 必须由用户给出 1–249 数字;不得从时刻、文字或随机数代取。
关系题必须先确认可观察结果范围:现有 love-materialization 只回答是否建立
明确、双方确认并持续推进的恋爱关系。仅恢复联系、互动回暖、恢复暧昧或秘密心意
不在该公式范围内,必须在起盘前失败关闭;不得擅自把低门槛问题改写成“关系落实”。
题型不收或范围失败关闭时,按 kp-optional.md“不收时的出口”回答:说明原因,
给出改用标准层或换成已收问法两个选项,不替用户切换。
KP 与 Tajika 在计算、文件和结论权限上互斥;用户可以显式要求分别查看两套结果,
但不得在任一栈内读取另一栈或拼票。只有 Q&A 的跨栈比较模式可以并列解释已经生成
的结果。KP 是独立判读栈,不运行标准 builder,也不与默认层拼票。
使用 scripts/build_kp_horary.py 生成独立 kp_horary_* 目录。当前已实现
Krishnamurti ayanamsa、number-derived Placidus cusps、A/B/C/D significator
chain、node constellation/sign-lord agent、Reader VI 已锁定的恋情落实/商业
合作题型宫组、Ruling Planets、边界距离,以及独立的 horary Moon 四级 period、
RP 交集与 Moon/Sun/Jupiter 过运 timing。婚姻重聚因原文存在多个不同语境而失败
关闭。Readers 未给 Rahu/Ketu 自身 orb,因此 node conjunction/aspect agency
继续失败关闭;任何 operative promise 路径穿过该缺口时,promise 与 timing 都不得
宣称完整。整栈在全部出版例盘套件完成前不能标“生产级”。
每次运行必须同时生成 structured_kp.md/json 与人类可读
kp_judgment_<label>.md;判读单只翻译 KP 自身 promise、门控与 timing,不换算成
标准层的“成/悬/不成”。判读单必须先回答“当前偏向什么、为什么、能否给时间”,
并把命中的宫组翻译成该题型的现实支持或阻力;再把 cusp/sub-lord/RP/period
状态码放入技术核对区。
本命交叉默认关闭。用户明确要求时读取 cross-natal-policy.md;当前版本因旧裁决
规则未完成来源重审而失败关闭,不能调用不存在的 build 参数,也不能用 SAV、
本命 Dasha 或分盘升降 Prashna 结论。
已有盘追问不重起,读取 qa_rules.md,且只访问当前 prashna_* 目录。
若追问对象是 KP,则只访问当前 kp_horary_* 目录,不读取或拼接
prashna_*。
prashna_* 的标准产物;tajika_overlay.md,但不改标准结论;kp_horary_*;进入完成条件:每条回答能回查对应栈文件,未跨目录偷读,未给不成档补时间, 也未把跨栈比较写成一个新的混合占星结论。
U/M/T/KP 越界?prashna_*,KP 是否只写入独立
kp_horary_*?kp_horary_* 目录?© 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
SKILL.md and 23 other files (scripts) in skills/vedic-prashna of CNWU16/vedic-astro-skills.
Open the folder on GitHubat commit c1a94c3
Vedic Prashna Chart Caster 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Vedic Prashna Chart Caster this skillCNWU16/vedic-astro-skills | 947 | — | ~3k | Automated safety check: Pass | AGPL-3.0 | |
| TimesFM Forecastinggoogle-research/timesfm | 34k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| StatsmodelszLanqing/codex-claude-academic-skills | 4.7k | 15 repos | ~4.9k | Automated safety check: Pass | BSD-3-Clause | |
| Timesfm ForecastingzLanqing/codex-claude-academic-skills | 4.7k | 3 repos | ~7.5k | Automated safety check: Notes | Apache-2.0 | |
| Find Hypertable Candidatestimescale/pg-aiguide | 1.9k | 1 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Pensieve Searcharkohut/pensieve | 1.4k | — | ~8.2k | Automated safety check: Pass | Apache-2.0 |
google-research/timesfm
Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.
zLanqing/codex-claude-academic-skills
Statistical models library for Python. An agent skill from zLanqing/codex-claude-academic-skills.
zLanqing/codex-claude-academic-skills
Zero-shot time series forecasting with Google's TimesFM foundation model.
timescale/pg-aiguide
A skill your agent uses to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables.
arkohut/pensieve
Search the user's local Pensieve screenshot archive by text, app, or time range.
ninehills/skills
Market prediction skill using Kronos. An agent skill from ninehills/skills.
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.
CNWU16/vedic-astro-skills
Compares two people's verified Vedic birth charts using Parashari methods to discuss relationship compatibility, timing and mutual influence.
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.
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.
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.
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.
Categories
Casts and interprets a question-time Vedic horary chart for one concrete question, using the exact time and place it was asked. This skill builds an independent astrological chart from the exact moment and place a specific question is asked, rather than from a birth chart, following a classical standard derived from the Shatpanchasika text as filtered through more recent published practice. Two further analytical stacks - Tajika and a KP-based horary method numbered 1 through 249 - stay isolated from that default layer and only run when the user explicitly turns them on, and the skill is explicit that its default layer does not provide production-grade event dates, only whether the matter looks likely to succeed, be pending, or fail, plus the conditions and timing-module availability behind that call.
Vedic Prashna Chart Caster fits situations like: casting a horary chart for one specific yes-or-no question; interpreting whether a specific matter looks likely to succeed; following up on an existing Prashna chart with a new question.
Run `npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a claude-code`. Or copy the skill folder (skills/vedic-prashna in CNWU16/vedic-astro-skills) into .claude/skills/vedic-prashna in your project. Claude Code loads it when a task matches its description.
Run `npx skills add CNWU16/vedic-astro-skills --skill vedic-prashna -a codex`. Or copy the skill folder (skills/vedic-prashna in CNWU16/vedic-astro-skills) into .agents/skills/vedic-prashna in your project. Codex loads it when a task matches its description.
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-prashna -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-prashna, .gemini/skills/vedic-prashna, .github/skills/vedic-prashna and .opencode/skills/vedic-prashna in your project.
Going by SKILL.md and its folder, Vedic Prashna Chart Caster needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: The exact time and place the question was asked.
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.
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.
Vedic Prashna Chart Caster 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.
About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Vedic Prashna Chart Caster: TimesFM Forecasting (google-research/timesfm, 34k stars), Statsmodels (zLanqing/codex-claude-academic-skills, 4.7k stars), Timesfm Forecasting (zLanqing/codex-claude-academic-skills, 4.7k stars) and Find Hypertable Candidates (timescale/pg-aiguide, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
CNWU16 (a GitHub user) maintains it in CNWU16/vedic-astro-skills, which has 947 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 10, 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.