
AI Divination Skills
io.github.sapuyou45-bit由 GitHub 帳號 sapuyou45-bit 發布v0.7.1更新於 Oct 24, 2026
Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.
概覽
本機 MCP 伺服器,執行經過稽核的塔羅、易經、小六壬與八字起卦腳本,讓助理解讀結果而非自行編造。
- 可以做什麼
- 依牌組、牌陣與逆位選項抽取塔羅牌
- 以銅錢或蓍草法起易經卦,給出本卦與變卦
- 依數字或公曆時間回退方式起小六壬課
- 依公曆出生時間排出八字(四柱)盤
- 取得解讀範本,以及帶方法中繼資料、可供稽核的 JSON 輸出
- 適用情境
- 適合希望助理針對決策、創作瓶頸或專案重新檢視給出象徵性、反思性解讀,且要求結果由腳本產生而非模型編造的情境。也適合用種子做可重現的示範。
- 執行需求
- 以本機 stdio 程序執行;README 要求安裝 oraclebone Python 套件(Python 3,無其他執行期相依套件),並在主機設定中註冊 ai-divination-mcp 指令。八字技能需要選用的 lunar-python 附加套件。未宣告帳號、金鑰或標頭。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 AI Divination Skills,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Oraclebone
The bone cracks. The model reads.
Three thousand years ago, Shang kings carved their divinations into bone — the first auditable record of an oracle at work. Oraclebone brings the same discipline to AI agents: audited scripts produce the draw, the hexagram, the pillars; the model only interprets what it is given. It never invents the result.
[tests] [release] [PyPI] [PyPI Downloads] [Latest release] [License: MIT] [Python] [GitHub Discussions]
🔮 Open-source divination toolkit for AI agents, formerly known as ai-divination-skills (renamed in v8.0.0 — the old PyPI package is frozen; install oraclebone instead).
oraclebone is a practical skill collection for tarot, I Ching, Xiao Liu Ren, and future symbolic systems. It is built for agent workflows that need auditable randomness, clear method boundaries, and reusable interpretation templates.
This project treats divination as symbolic reasoning and reflection, not deterministic prediction.
⚡ One-line Install for AI Agents
Paste this into your AI agent:
Or install directly for Claude-style local skills:
The default target is ~/.claude/skills. Set AI_SKILLS_DIR for another agent skill directory.
✨ Overview
Most AI divination prompts let the model invent the result. This repo separates the two jobs:
- A local script produces the card draw, hexagram, or Xiao Liu Ren position.
- The AI agent interprets that generated result with clear safety boundaries.
That makes readings easier to test, reproduce, audit, and reuse across agents.
🧭 Methodological Rigor
The core rule is simple: scripts or user-provided physical casts generate the divination result; AI interprets that result and does not generate the divination result.
This is not scientific proof of divination efficacy. It is a stricter workflow for symbolic reasoning:
- real readings use system randomness by default
- seeded mode is only for tests and reproducible demos
- traditional methods and limitations are documented per skill
- JSON outputs include enough metadata to audit the method
- approximate modes emit warnings instead of pretending to be traditional
🌐 Multilingual Docs
The GitHub Pages site ships a six-language switcher — 简体中文, English, 日本語, Português, 한국어, Español. It follows your browser language by default and remembers your manual choice.
Local preview:
Published site:
🧩 Included Skills
🚀 Quick Start
Install from PyPI:
Or from a checkout:
Use editable mode while developing:
Use one command for every system:
Ask for an agent interpretation template:
Use the Python API directly:
You can still run the underlying scripts directly:
Use a seed for reproducible demos:
All scripts output JSON.
📦 Install as Agent Skills
For AI-agent-guided setup, use the remote install runbook:
For direct shell install:
The installer copies tarot, iching, and xiaoliuren into ~/.claude/skills by default. To target another agent, set AI_SKILLS_DIR before running it.
Manual install is just copying the folders you want into your agent's skill directory:
Each skill is self-contained:
Install individual folders, not the entire repository, when you only want one skill.
Each skill script also works in single-folder mode. If the Python package is installed, the script delegates to the package runtime. If only the skill folder is copied, it falls back to the bundled standalone script in that skill.
Per-host adapters
Every skill ships four adapter files in skills/<skill>/agents/:
All four adapters route through the same audited ai-divination <skill> CLI, so the agent host never invents the result.
🧠 Use it from Claude Desktop / Codex / any MCP host
oraclebone ships a built-in MCP server (ai-divination-mcp). Any
Model Context Protocol host — Claude Desktop, Codex,
Continue, Cursor — can mount it with a single config line, and the model gets five tools:
tarot_draw, iching_cast, xiaoliuren_cast, bazi_cast, and interpretation_template.
The model never invents the draw; the server runs the audited scripts locally.
Claude Desktop
Install the package once:
Then edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or
%APPDATA%\Claude\claude_desktop_config.json (Windows):
Restart Claude Desktop. Ask "draw three tarot cards for my decision" — Claude will call
tarot_draw and interpret the JSON output.
Codex / Continue / Cursor
Any MCP-aware host follows the same pattern. The server speaks JSON-RPC 2.0 over stdio with no third-party dependencies.
Per-client setup guides
Copy-paste JSON configs and example prompts for each host:
🤖 Agent Behavior
Each skill instructs the agent to:
- generate or accept a concrete draw/cast result
- read concise reference material only when needed
- interpret with the shared response contract
- avoid certainty, fatalism, and professional advice
Shared guidance lives in:
shared/methodology.mdshared/interpretation-protocol.mdshared/response-contract.mdshared/randomness-protocol.mdshared/safety-policy.mdshared/interpretation-style.md
🧪 Examples
examples/tarot-decision.mdexamples/iching-strategy.mdexamples/xiaoliuren-daily.md
🛡️ Safety Boundaries
These skills are not for medical, legal, financial, or crisis guidance.
Good readings should:
- frame the result as symbolic reflection
- connect claims to the generated result
- preserve user agency
- offer small, reversible next steps
- state uncertainty clearly
See ETHICS.md for the full project stance.
🛠️ Development
No runtime dependencies are required beyond Python 3.
Run tests:
Current coverage checks:
- unified CLI routing
- package-only CLI execution
- importable Python APIs
- single-folder skill execution
- skill metadata and asset contracts
- interpretation protocol templates
- tarot spread output
- I Ching cast structure and manual lines
- Xiao Liu Ren number and time fallback behavior
💬 Community
- Releases: https://github.com/sapuyou45-bit/oraclebone/releases
- Roadmap:
ROADMAP.md - Discussions: https://github.com/sapuyou45-bit/oraclebone/discussions
- Issues: pick a
good first issueor propose anew-skill - Security: see
SECURITY.mdfor private vulnerability reporting
🗺️ Roadmap
Near-term:
- Add a published package workflow.
- Expand automated skill validation in CI.
- Add richer reference material for each MVP skill.
- Add more example readings.
- Add more agent integration examples.
Later:
meihualiuyaorunesnumerologyastrology
📄 License
MIT
來源:README.md,提交 a9a8ab7
工具
0版本歷史
1- v0.7.1最新Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分