A project-specific guide for working on 命语, an AI application for Chinese fortune analysis. It covers 八字 and 紫微斗数 chart work, AI reading prompts, and the application’s frontend and backend integration.

Use it when analyzing a birth chart, designing fortune-related features, editing chart displays, or working on the project’s FastAPI and Next.js integration.

It keeps chart interpretations grounded in calculated facts and preserves the product’s gentle conversational style. It also identifies important project files and protects deployment settings from accidental changes.

mingyu — Skill for Codex by gaowei90098-creator

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add gaowei90098-creator/mingyu-skill --skill mingyu

Clone the repo

git clone --depth 1 https://github.com/gaowei90098-creator/mingyu-skill

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gaowei90098-creator/mingyu-skill/mingyu/github.svg)](https://agentmods.dev/skills/gaowei90098-creator/mingyu-skill/mingyu)

Your own site

<a href="https://agentmods.dev/skills/gaowei90098-creator/mingyu-skill/mingyu"><img src="https://agentmods.dev/badge/skills/gaowei90098-creator/mingyu-skill/mingyu/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gaowei90098-creator/mingyu-skill/mingyu"><img src="https://agentmods.dev/badge/skills/gaowei90098-creator/mingyu-skill/mingyu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,358 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00130	$0.01358
Opus 5	$0.00065	$0.00679
Sonnet 5	$0.00026	$0.00272
Haiku 4.5	$0.00013	$0.00136

Measured 9d ago against content hash d74a97320593, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mingyu scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/calculate_chart.py, scripts/calculate_ziwei.cjs, scripts/install.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to mingyu — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude-code/skills/mingyu/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

命语

Use this skill to operate as a project-aware 命语 collaborator: combine deterministic 八字/紫微 chart facts, classical reasoning, and the product's gentle "水滴" AI companion voice.

First Moves

Identify whether the user wants analysis, product/design work, or code changes.
For chart analysis, gather birth data before interpreting: name or nickname, solar birth date, birth time, gender, birthplace, and whether true solar time matters.
For repo work, read references/project-guide.md first, then inspect only the files relevant to the task.
Do not change deployment files unless the user explicitly asks. Treat frontend/vercel.json, backend/render.yaml, Dockerfile, start.sh, Procfile, and runtime files as deployment-owned.

Deterministic Chart Workflow

Prefer factual chart data over memory or hand calculation.

The skill remains useful without local script dependencies. If Python or Node dependencies are unavailable, use the reference files to guide the conversation and tell the user deterministic chart scripts were not run.

If working inside the 命语 repo, use the project functions when available:
- backend/demo.py: calculate_bazi, calculate_ziwei
- backend/analyzer.py: 八字格局、身强弱、用神、神煞、冲合制化
- frontend/api/ziwei_runner.cjs: Next/Vercel-side 紫微 runner
If using this skill standalone and dependencies are installed, run scripts/calculate_chart.py for 八字 and scripts/calculate_ziwei.cjs for 紫微.
- To prepare dependencies, run python3 scripts/setup_env.py.
- To verify deterministic helpers, run python3 scripts/validate.py or npm test.
After obtaining a chart, lock hard facts before interpretation:
- four pillars, day master, hidden stems, ten gods
- qi-yun and complete da-yun chain
- Zi Wei palaces, body/soul palace, four mutagens, current/future decadal palace
Never invent missing chart facts. Ask for the missing birth field or state the uncertainty.

Example:

python3 scripts/calculate_chart.py --year 1995 --month 8 --day 15 --hour 14 --minute 30 --gender 男
printf '{"birthday":"1995-08-15","time_idx":7,"gender":"男"}' | node scripts/calculate_ziwei.cjs

Read the full file on GitHub · 106 lines

Files

What ships with it

15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 106 lines · 130 tokens per session scan A d74a97320593

Subscribe to this mod's changes

mingyu is a skill published in the GitHub repository gaowei90098-creator/mingyu-skill (3 stars, last pushed 3mo ago), licensed MIT. It adds 130 tokens to every session and 1,358 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mingyu, differing in 0 lines, and is treated as a copy.

Claude Code ai-agent astrology bazi codex skill

mingyu

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

命语

First Moves

Deterministic Chart Workflow

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

yueyuan

ziwei-analysis

yuan

vedic-analysis

numerology-analysis

astrology-analysis