Bazi Engine generates traceable Four Pillars charts and grounded traditional Chinese astrology reports from verified birth data.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install bazi-engine
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install bazi-engine using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Bazi Engine is an AI agent skill for Four Pillars of Destiny (Bazi) analysis. It guides users through collecting their name, solar or lunar birth date, birth time, gender, and birthplace, then uses deterministic code and reference tables to calculate the year, month, day, and hour pillars, Ten Gods, hidden stems, Five Elements, luck cycles, annual cycles, and related chart data.
Unlike free-form fortune text generation, the skill requires chart calculations to be performed by code rather than LLM intuition. Its interpretations are tied to classical Chinese texts and matched rule records, with citations for key judgments, neutral language, beginner-friendly explanations, and an explicit reminder that Bazi is for cultural learning and self-exploration—not professional medical, financial, relationship, or life-planning advice. Among Openclaw Skills, it is especially valuable for transparent, reproducible, and visualized traditional-culture analysis.
Bazi Engine is distributed as a skill project with its knowledge base, browser UI, deterministic chart engine, rule database, and validation utilities. No external service is required for the offline chart interface.
kb/, ui/, and tools/.ui/index.html is not already present:python tools/build_ui.py
ui/index.html directly in a browser to validate chart calculation and report rendering. The UI embeds the Jie Qi data and the production rule library.present_files to preview the generated HTML report in an embedded browser when supported.node tools/test_ui.js
node tools/test_eval_state.js
kb/04-rules-db/rules.json, regenerate the UI, and rerun distribution, conflict, duplication, and end-to-end checks:python tools/gen_rules.py
python tools/build_ui.py
node tools/audit_hit_distribution.js
node tools/check_dup_hits.js
node tools/check_conflicts.js
node tools/verify_ux_e2e.js
The skill metadata specifies version 1.2.1, MIT licensing, and compatibility with WorkBuddy, QClaw, and ima. Treat health, finance, and relationship outputs as cultural reference material and defer consequential decisions to qualified professionals.
| Path | Purpose |
|---|---|
ui/index.html |
Single-file offline interface containing deterministic charting, embedded Jie Qi data, visualizations, and rule rendering. |
kb/01-basics/ |
Foundational tables and concepts: Gan-Zhi, Five Elements, Ten Gods, hidden stems, Shichen, Na Yin, and Shen Sha. |
kb/02-rules/ |
Calculation and interpretation rules for Da Yun, classical methods, remedies, marriage, workflow, examples, and optional Bazi-MBTI references. |
kb/03-classics/ |
Classical source material including seasonal adjustment, Zi Ping methods, chart structures, and stem-branch principles. |
kb/04-rules-db/rules.json |
Production rule records; the documented library contains 504 rules with suggestion coverage and categories for annual, monthly, daily, marriage, family, and thematic interpretations. |
kb/04-rules-db/rules-template.json |
Schema and examples for adding new rule records. |
kb/05-reference/ |
Visualization specifications and prompt references. |
tools/ |
Build, generation, regression, audit, monitoring, and end-to-end validation scripts. |
suggestion guidance. Matching is performed by the matchRules condition engine.Rules should be tested for missing fields, overly broad conditions, duplicate conditions, contradictory matches, invalid Ten Gods keys, and incorrect negation semantics before being injected into the UI.
matchRules, including positive combinations and explicit negation conditions.Loading
Turn prompts and existing media into production-ready AI videos through a streamlined command-line workflow.

Create production-ready Seedance 2.0 videos from prompts and reference media with automated uploads, pricing checks, task tracking, and downloads.

Generate controlled Seedance 2.5 videos by defining the opening and closing frames, then automate media upload, task tracking, and result downloads.

An automated Openclaw Skills report generator that aggregates task outcomes into daily tenant reports, fairness metrics, and 30-day welcome-back summaries.

Generate and revise a fact-checked, channel-ready image suite for one SKU while preserving product identity, claims, and visual consistency.

Generate reviewable apparel-on-model product images while preserving authorized adult identity, body proportions, garment details, layering, and ecommerce composition.








































