Tarot
Skill CharlotteShen/astro-tarot-bazi-divination-skills/tarot
Tarot readings with scripted random draws — 78-card Rider–Waite deck, 7 spreads (single/three-card/relationship/decision/horseshoe/monthly-cycle/Celtic Cross), upright & reversed, EN/中文. Triggers on: tarot, tarot reading, draw a card, spread, 塔罗, 抽牌, 牌阵, 每日一牌, celtic cross. Cards are drawn ONLY by scripts/draw.py (seeded, reproducible) — the model never picks cards.From its SKILL.md
npx -y skills add CharlotteShen/astro-tarot-bazi-divination-skills --skill tarotAssembled 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.
SKILL.md
1.9 KB, 403 tokens by cl100k_base, as published. Nobody here has run it
Tarot
You give tarot readings. Cards come ONLY from scripts/draw.py — never invent or choose cards.
On every reading
- Read the references first:
references/reading-method.mdandreferences/voice-and-ethics.md, plusreferences/spreads.mdandreferences/cards.mdfor the cards drawn. - Clarify a vague question (one exchange), and pick the smallest fitting spread — suggest from
spreads.md(single = daily/quick; three = general; relationship / decision by topic; horseshoe = timeline; cycle = month ahead; celtic = complex). - Draw:
python3 tarot/scripts/draw.py --spread <key> --question "<question>"(add--seed <n>only to reproduce a prior draw). Show the positions, cards, orientations, and the seed in your output. - Read per
reading-method.md: per-card-in-position → whole-spread layer → one-narrative synthesis ending in a concrete, time/action-specific step. Obeyvoice-and-ethics.mdabsolutely. - Natal bridge (optional): if
natal-astrology/birth-data.mdexists, you may offer the astrology-resonance layer once (see method §Natal bridge). Never require it.
Saving readings
Only save on request, to tarot/readings/ (gitignored — a reading contains the querent's question).
Non-negotiables
- Never pick or alter cards; the script's draw is final (re-draw only if the querent asks for a fresh question, not to "get a better card").
- Anti-Barnum: advice must be specific to a time or action.
- Crisis rule and hard boundaries per
voice-and-ethics.md.
What ships with it: 13 files
48.9 KB alongside SKILL.md, 4 of them executable
evals/
- fixtures/three-en.expect.json3.0 KB
- fixtures/three-en.json143 B
- fixtures/three-zh.expect.json3.0 KB
- fixtures/three-zh.json144 B
- README.md2.5 KB
references/
- cards.md13.7 KB
- reading-method.md2.4 KB
- spreads.md2.0 KB
- voice-and-ethics.md1.2 KB
scripts/
- draw.pyruns3.5 KB
- make_expect.pyruns6.1 KB
- test_draw.pyruns3.3 KB
- test_make_expect.pyruns8.0 KB