Perform structured Ziwei Dou Shu (紫微斗数 / Zi Wei Dou Shu) system design, chart interpretation, and implementation planning. Use when the user asks to build a Ziwei skill or engine, define palaces/stars/four-transformations/limits, interpret an existing chart JSON/table, or produce deterministic-vs-heuristic output. Do not use for birth-data-only personal readings unless verified chart facts or a deterministic chart engine are available.
npx skills add https://github.com/shizhilya/yuan --skill ziwei-analysis
这是一个给 AI 代理使用的 紫微斗数 Skill。目标不是“神秘发挥”,而是把紫微斗数任务拆成确定性的排盘层与经验性的解读层,并用结构化输出保证可复核、可集成、可版本化。
design:构建/评审 Skill、Prompt、接口、JSON schema、规则引擎、代码架构。interpret_chart:用户已经提供命盘事实(JSON、表格、转写后的截图信息),基于事实解释。chart_from_birth:用户只提供出生资料;仅在你能访问可信、确定、可复现的排盘规则或外部排盘引擎时执行。design 模式,输出实现方案;或下列因素可能影响排盘,必须在结果里显式列出:
calendar_type:公历 / 农历 / 自动判断gendertimezonelate_zi_hour_rule:晚子时算次日还是当日school_variant:四化表/流派差异use_true_solar_time当用户出现以下需求时使用本 Skill:
优先接受如下结构;如果用户只给自然语言,也要先转换成这个结构:
{
"task_mode": "auto",
"birth_datetime": "",
"gender": "unknown",
"calendar_type": "solar",
"timezone": "Asia/Shanghai",
"latitude": null,
"longitude": null,
"use_true_solar_time": false,
"late_zi_hour_rule": "cross_day",
"school_variant": "traditional_fullbook_v1",
"chart_facts": null,
"question_focus": [],
"output_locale": "zh-CN"
}
assets/input-schema.jsonassets/chart-facts-schema.jsondesigninterpret_chartchart_from_birth如果环境支持运行 Python,可先执行:
python scripts/request_guard.py <request.json>
该脚本会告诉你:
task_mode按以下顺序输出事实层:
10. 三方四正 / 对宫关系
11. 大限
12. 流年(如用户指定年份)
基于事实层,按主题聚合:
如环境支持,生成结果后执行:
python scripts/validate_output.py <output.json>
如果校验器发现你把“经验推断”写成了“排盘事实”,或漏掉了歧义/置信度提示,应先修正再交付。
默认产出如下 JSON;必要时可加字段,但不要删掉核心结构:
{
"meta": {
"version": "1.0.0",
"task_mode": "",
"school_variant": "",
"deterministic_part": true,
"interpretive_part": true,
"ambiguity_warnings": [],
"confidence_notes": []
},
"命宫": {
"排盘事实": {
"宫位": "",
"主星": [],
"辅星": [],
"四化": [],
"三方四正": []
},
"经验解读": {
"关键词": [],
"优势": [],
"风险": [],
"建议": [],
"confidence": 0.0
}
},
"事业宫": {
"来源宫位": "官禄宫",
"排盘事实": {},
"经验解读": {}
},
"财帛宫": {
"排盘事实": {},
"经验解读": {}
},
"婚姻": {
"来源宫位": ["夫妻宫", "福德宫", "命宫", "迁移宫"],
"排盘事实": {},
"经验解读": {}
},
"综合分析": {
"命盘主轴": [],
"大限趋势": [],
"流年提示": [],
"关键机会": [],
"关键风险": [],
"行动建议": []
}
}
更详细模板见:assets/output-template.json
当任务是“做系统”而不是“算命盘”时,请优先输出以下内容:
input_schemaderived_featuresdeterministic_rulesinterpretive_rulesdecision_flowoutput_templateambiguity_policytest_casesversioning_strategy推荐把系统拆成三层:
chart_engine:只负责确定性排盘interpretation_engine:只负责经验解读renderer:把结构化结果转成 JSON / Markdown / API Responsereferences/DOMAIN_MODEL.mdreferences/WORKFLOW.mdreferences/LIMITS_AND_GUARDRAILS.mdREADME.mdexamples/Expert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests organizational design and headcount planning for a startup.
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.
Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progress or updates, (3) Generate weekly/daily reports from Jira, (4) Publish status summaries to Confluence, or (5) Analyze project blockers and completion. Queries Jira issues, categorizes by status/priority, and creates formatted reports for delivery managers and executives.
Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.
Google Workflow: Today's meetings + open tasks as a standup summary.
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.
Take shizhilya/ziwei-analysis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.