Xuanxue Database

引导用户通过对话从零搭建个人玄学数据库——「命盘与结论库 / 应事与回测库 / 方法与资料库」三库体系，支持 Notion 一键建库与本地 Markdown 双模式，覆盖八字命理、六爻占卜、紫微斗数。当用户提到想搭建或整理命理资料库、记录命例/卦例、建立应事回测体系、验证断语准确率、系统化管理玄学学习笔记，或说「搭建玄学数据库」「整理我的命例」「怎么记录卦例」「想系统地学命理/追踪应验」时，使用本 skill——即使用户没有明确说出「数据库」三个字。

5 starsDatabases

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add yanouyuan-bit/xuanxue-database-skill --skill xuanxue-database

Manual install

git clone --depth 1 https://github.com/yanouyuan-bit/xuanxue-database-skill.git /tmp/xuanxue-database-skill
mkdir -p ~/.claude/skills
cp -r /tmp/xuanxue-database-skill/. ~/.claude/skills/xuanxue-database

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 玄学数据库搭建助手

通过多轮对话，引导用户搭建一套属于自己的玄学研究数据库。这不是普通的笔记模板，而是一套**可回测的研究体系**：

```
方法与资料库 ──提供判断依据──► 命盘与结论库 ──产出可证伪断语──► 应事与回测库
      ▲                                                        │
      └────────────── 回测结果反哺方法可靠度评级 ◄──────────────┘
```

三库分工：

| 库 | 存什么 | 核心价值 |
|---|---|---|
| 🎴 命盘与结论库 | 命例（八字/紫微盘）+ 对每个命例的结构化分析与结论 | 积累「样本」 |
| 📋 应事与回测库 | 事前断语、实际应事、事后复盘（含六爻卦例） | 让断语接受现实检验 |
| 📚 方法与资料库 | 判断规则、口诀心法、经典资料，附可靠度评级 | 沉淀「哪些方法真的有用」 |

这套体系的灵魂是**回测闭环**：每条断语写下时就要可证伪，应事后复盘评级，评级结果回头修正方法库中对应方法的可靠度。向用户传达这一点，比建好表格本身更重要。

## 工作流程总览

按以下五个阶段推进。每个阶段开始前，先读对应的参考文件。

| 阶段 | 做什么 | 参考文件 |
|---|---|---|
| 0. 访谈 | 了解用户的术数体系、现有资料、部署偏好 | `references/interview-guide.md` |
| 1. 选择部署模式 | Notion 或本地 Markdown | 本文件「部署模式」一节 |
| 2. 搭建三库 | 按 schema 建库/建目录 | `references/schemas.md` + 对应部署文件 |
| 3. 首条数据录入 | 引导用户录入第一个命例/卦例 | `references/interview-guide.md` 阶段 3 |
| 4. 建立回测习惯 | 讲解回测方法论，约定复盘节奏 | `references/backtest-guide.md` |

不要一口气跑完全部阶段。每个阶段结束时向用户确认，再进入下一阶段。用户中途想跳步（比如「先把库建起来再说」）就顺着来，但阶段 4 的回测理念务必在结束前讲到——没有回测闭环，这套系统就退化成普通笔记。

## 访谈原则

- **一次只问一到两个问题**，绝不发问卷式的长列表。这是对话式引导，不是填表。
- 先问体系（八字 / 六爻 / 紫微，可多选），因为它决定建哪些字段变体。
- 问用户现在有没有已积累的资料（微信收藏、散落笔记、旧 Excel），有的话在阶段 3 引导迁移一两条作为首批数据。
- 具体话术和分支见 `references/interview-guide.md`。

## 隐私守则（重要）

玄学数据天然涉及敏感个人信息。在整个引导过程中主动执行以下守则，并向用户解释原因：

1. **匿名编号代替真名**。命例命名用「命例·日主」或「朋友A·乙木」这类标签，不写真实姓名。出生年月日时 + 姓名足以唯一定位一个人。
2. **出生信息降敏**。四柱干支本身已足够分析使用；精确的公历生日、出生地建议只在用户明确愿意时录入，并提示：Notion 数据在云端，本地模式数据在自己硬盘。
3. **他人命盘需谨慎**。录入朋友、家人、粉丝的命盘时，提醒用户：这些是别人的隐私，若日后公开分享库内容（截图、开源模板），务必先脱敏。

Read the full skill on GitHub

Details

Skill name: xuanxue-database
Repository: yanouyuan-bit/xuanxue-database-skill
License: MIT
Repo updated: 18 July 2026

FAQ

What does the Xuanxue Database skill do?

How do I install the Xuanxue Database skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add yanouyuan-bit/xuanxue-database-skill --skill xuanxue-database. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Xuanxue Database popular?

It lives in yanouyuan-bit/xuanxue-database-skill, which has 5 GitHub stars and 0 forks.

Related skills

Analyzing Database Indexes

jeremylongshore/claude-code-plugins-plus-skills

This skill uses the database-index-advisor plugin to analyze query patterns and recommend optimal database indexes. It identifies missing indexes to improve query performance and unused indexes that can be removed to save storage and improve write performance. Use this skill when the user asks to "analyze database indexes", "optimize slow queries", "find missing indexes", "remove unused indexes", or requests help with "database index optimization". The plugin analyzes database workloads, detects potential indexing issues, and provides actionable recommendations for indexing strategies.

Databases

Time Ledger

cruisekkk/time-ledger

Natural-language time tracking — the user says what they did in plain language, you parse it into Activity + Minutes + Date and write it to their Notion database; anything uncertain you mark To-confirm and BATCH-ASK rather than fabricate. Use when the user reports time spent (e.g. "read papers for two hours", "hit the gym for an hour", "coded all morning"), says log it / log my time / tidy up my time ledger / time ledger, or asks where their time went.

Databases

Analyzing Query Performance

jeremylongshore/claude-code-plugins-plus-skills

This skill enables Claude to analyze and optimize database query performance. It activates when the user discusses query performance issues, provides an EXPLAIN plan, or asks for optimization recommendations. The skill leverages the query-performance-analyzer plugin to interpret EXPLAIN plans, identify performance bottlenecks (e.g., slow queries, missing indexes), and suggest specific optimization strategies. It is useful for improving database query execution speed and resource utilization.

Databases

DBT Semantic Layer Developer

keithbinkly/dbt-semantic-layer

Provides expert-level assistance with dbt Semantic Layer, MetricFlow, semantic models, metrics, dimensions, entities, measures, and BI tool integrations. Use this skill when building semantic models, creating metrics (simple, ratio, cumulative, derived, conversion), debugging validation errors, or integrating with BI tools. Extracted from official dbt documentation and optimized for data practitioners.

Databases

Archiving Databases

jeremylongshore/claude-code-plugins-plus-skills

This skill automates database archival processes. It helps reduce primary database size by moving historical records to archive tables or cold storage solutions like S3, Azure Blob, or GCS. The plugin supports PostgreSQL and MySQL, implementing automated retention policies, compression, compliance tracking, and zero-downtime migration. Use this when the user mentions "database archival", "archive old database records", "retention policies", "cold storage", or "reduce database size." It is particularly useful for handling requests related to data lifecycle management and compliance requirements

Databases

Gospec

singchia/gospec

Go 后端 SDLC 全流程中文规范。覆盖 Bounded Context 切分、Kratos 风格分层（cmd/server/service/biz/data/model）、API 设计、数据模型（MySQL / Redis / ClickHouse / InfluxDB）、测试、CI/CD、日志指标追踪 SLO、认证密钥安全、部署与事故、数据库 migration、PRD/RFC/ADR/HLD 文档。框架中性——Web 框架可选 Kratos / gin / Hertz / chi / echo，规范只约束分层和依赖方向。写或审查 Go 代码时按需加载。Go backend SDLC spec — framework-neutral, load on demand for coding/design/testing/ops/docs.

Databases

Browse the most popular Claude skills, all databases skills, or write your own with the skills generator.