Bazi calendar research

Skill ProfesseurHaipeng/bazi-calendar-research-skill/skills/bazi-calendar-research

Research BaZi and Chinese calendrical notation as convention-dependent time labeling, with transparent sexagenary-cycle calculations, solar-term boundaries, source provenance, and uncertainty. Use when Codex is asked about 八字、四柱、天干地支、节气、真太阳时 or Chinese calendar algorithms.From its SKILL.md

Install

npx -y skills add ProfesseurHaipeng/bazi-calendar-research-skill --skill bazi-calendar-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, 666 tokens by cl100k_base, as published. Nobody here has run it

BaZi and Calendar Research

Treat BaZi as a historical interpretive system built on calendrical labels. The calendar arithmetic can be reproduced; claims that a chart causes personality, health, wealth, compatibility, or destiny are not established scientific conclusions.

Runtime: Python 3.10+

The bundled helper requires Python 3.10+ and only the Python standard library. It is deterministic and does not make network requests.

Workflow

Preserve raw civil time, UTC offset, location, and precision. Never replace an unknown birth time with noon without labeling it.
Choose and record the convention: year boundary (立春 or lunar New Year), month boundary (solar terms or lunar months), day boundary (midnight or 子初), and true-solar-time adjustment.
Compute only the fields supported by verified inputs. Use scripts/sexagenary.py for transparent year/month labels and scripts/day_cycle.py only with a named anchor. Do not pretend to calculate a complete chart without an ephemeris and boundary decision.
Read calculation-logic.md before deriving pillars. It makes the dependency order and unresolved fields explicit.
Separate the resulting labels from later school interpretations. Read classical-corpus.md; cite the school, commentator, date, and alternative reading.
Report sensitivity: which pillars change under another boundary convention, and which observations remain unchanged.
Convert reflection into observable questions and actions. Do not issue professional, medical, financial, legal, or irreversible life advice.

Output contract

Return: inputs, conventions, computed_labels, unknowns, textual_sources, school_readings, alternative_reading, and reflection_questions. Never return a single “fate score.”

Bundled tools and data

Run python3 scripts/sexagenary.py --year 2024 --solar-month-index 1 only after a verified boundary has selected the Gregorian year and solar-month index.
Run python3 scripts/day_cycle.py --anchor-date YYYY-MM-DD --anchor-index 0 --target-date YYYY-MM-DD only with a named, independently checked calendar anchor.
Run python3 scripts/relationship_graph.py --day-stem 甲 --target-stems 乙,丙,丁 for a reproducible stem relationship graph. It returns labels, not a personal reading.
Run python3 scripts/source_lookup.py --source hko-24-solar-terms to obtain local source metadata without fetching the network.
Read data/solar-terms.json for angular term definitions and data/stems-branches.json for the declared relationship graph. Neither is a timestamp ephemeris or a complete chart engine.

Read learning-path.md, calculation-logic.md, relationship-logic.md, knowledge-model.md, conventions.md, and sources.md before calculating or interpreting.

What ships with it: 19 files

30.5 KB alongside SKILL.md, 6 of them executable

agents/

openai.yaml344 B

data/

references/