leon-drq/qimen-dunjia-skill/qimen-dunjia-skill
Claude Code and agent skill by leon-drq/qimen-dunjia-skill
- community
Checking that the SKILL.md file is still in the repository.
Build and interpret a Qi Men Dun Jia chart for timing, direction, negotiation, travel, career moves, or a concrete complex decision. Use when the user mentions 奇门遁甲, 九宫, 八门, 九星, 八神, 择时, or 方位; do not use for a broad lifelong natal reading.
Install
npx vskill@latest install leon-drq/qimen-dunjia-skill/qimen-dunjia-skillSKILL.md
Qi Men Dun Jia
Use one chart to compare realistic actions, timing, and direction. Do not turn every symbol into a separate prediction.
Input gate
Collect one concrete question, the moment the question became active or the proposed action time, IANA time zone, place or longitude, topic category, and whether true solar time is expected. Record the chart method and rotating/flying plate convention when known. If the user supplies a chart, preserve it and skip recalculation.
Workflow
- Normalize the time to an ISO-8601 timestamp with offset. If using 6yao.ai, send
datetime,category,panType,trueSolarTime, andlongitudeto/api/qimen/calculate. - Verify the dun type, ju number, four pillars, chief star, chief door, and all nine palace fields before interpreting.
- Choose the useful deity/palace from the question. Read that palace together with the self palace, target palace, door, star, deity, stems, void, horse, and palace relations.
- Build two or three evidence chains. Mark clashes between signals instead of selecting only favorable ones.
- Compare available actions or time windows. Prefer reversible trials over a single fate-like command.
When direct HTTP access is needed, use scripts/sixyao_api.py qimen and follow references/6yao-api.md. Authentication must come from environment variables.
Output
Lead with a short decision summary. Then show input assumptions, chart facts, evidence for timing/direction, risks or contradictions, two action options, and a review condition. Use relative windows only when the chart supports them; do not invent an exact success date.
For suite use, follow references/evidence-contract.md and the high-stakes rules in references/safety-and-privacy.md.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingSKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/leon-drq/qimen-dunjia-skill/qimen-dunjia-skill)