Chenggu
Yuan (元) — a unified destiny-reading skill for Codex, Claude Code, and Agent Skills runtimes. One input surface, six methods (BaZi / Cheng Gu / Numerology / Western / Vedic / Zi Wei), production-grade output.
npx -y skills add shizhilya/yuan --skill chengguAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Structured Chinese Chenggu (“bone weight”) fortune analysis for 称骨算命 / 袁天罡称骨 tasks. Use when the user wants a deterministic lookup + structured output pipeline from birth datetime or normalized lunar components.
SKILL.md
3.8 KB, ~1.3k tokens by cl100k_base, as published. Nobody here has run it
Goal
你要把“称骨算命”执行成一个 可计算、可结构化、可扩展 的民俗规则流程,而不是自由发挥的玄学散文。
Core contract
- 先标准化输入:优先接受
lunar_components;若只有birth_datetime且是公历,先做可靠的农历转换。 - 再查表:严格从 JSON 查
year/month/day/hour四项权重。 - 只做整数运算:内部统一使用“钱”。
- 精确匹配:
total_qian必须一一对应verse_profiles的唯一档位。 - 结构化输出:必须同时给出机器可读 JSON 与中文展示层。
- 不臆测:不会转换就明确限制,不要猜农历日期,不要自造权重。
Scope
仅在以下场景使用:
- 称骨算命 / 袁天罡称骨 / 骨重 / 几两几钱 / 四两几钱
- 希望把歌诀拆成事业、财运、婚姻等结构化结果
- 需要把民俗规则做成可编排的 agent / skill / rule-engine
不要用于:
- 八字、紫微、星座、塔罗等非称骨体系
- 缺少可靠农历转换能力却仍要求你硬算公历结果
- 任何需要科学、医学、法律、投资保证的场景
Resources
references/chenggu_skill_spec.json: 完整规则总表(可直接被工具读取)references/lookup_tables.json: 年/月/日/时权重查表references/verse_profiles.json: 51 档歌诀与结构化标签references/skill_contract.json: 输入、派生特征、规则、决策流references/implementation_notes.md: 边界规则、转换要求、限制说明assets/output-template.json: 中文展示模板assets/input.schema.json/assets/output.schema.json: 机器可读 schemareferences/examples.md: 参考输入输出
Execution flow
- 读取输入。
- 若存在
lunar_components,直接使用:year_ganzhimonthdayhour_branchis_leap_month
- 若仅有
birth_datetime:- 先识别
calendar_type - 若为
gregorian,调用宿主环境中可靠的农历转换能力 - 若为
lunar,提取农历年月日时
- 先识别
- 应用边界规则:
- 夜子时 23:00~23:59 视为次日
- 闰月 1
15 按本月,1630 按下月
- 查
lookup_tables.json:year_weight_qian_by_ganzhimonth_weight_qianday_weight_qianhour_weight_qian
- 计算:
total_qian = year + month + day + hourtotal_display = verse_profiles[total_qian].total_displaygrade = verse_profiles[total_qian].grade
- 读取
verse_profiles.json中对应档位:verse_canonicalstructured.trajectory_tagsstructured.career_levelstructured.wealth_levelstructured.marriage_levelstructured.scores
- 生成输出:
- 顶层 JSON 遵循
assets/output.schema.json - 同时填充
display_zh,键名与assets/output-template.json一致
- 顶层 JSON 遵循
- 给出简短说明:
- 说明这是民俗解释,不是科学结论
- 点明不确定性来源:版本差异、农历转换、歌诀解释主观性
Output requirements
- 必须先输出一个完整 JSON 对象。
- JSON 至少包括:
skill_nameapi_nameinput_normalizedweightstotal_weightgradeverse_canonicalanalysisadvicedisplay_zhlimitations
display_zh内必须包含:骨重明细总骨重等级原始歌诀结构化分析建议
Style
- 默认跟随用户语言;中文用户优先中文。
- 结果要简洁、可审计、便于程序后处理。
- 不要把歌诀扩写成冗长散文;重点是结构化与可复核。
What ships with it: 11 files
86.7 KB alongside SKILL.md
agents/
- openai.yaml287 B
assets/
- input.schema.json2.0 KB
- output.schema.json3.4 KB
- output-template.json240 B
references/
- chenggu_skill_spec.json40.2 KB
- examples.md6.9 KB
- implementation_notes.md1.5 KB
- lookup_tables.json1.8 KB
- skill_contract.json1.4 KB
- verse_profiles.json28.3 KB
- AGENTS.md629 B