agentleFS
CharlotteShenCharlotteShen/astro-tarot-bazi-divination-skills/tarot/SKILL.md

tarot

Skill0 starsChanged 3 months agoMITView on GitHub

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.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Natal bridge (optional): if natal-astrology/birth-data.md exists, you may offer the astrology-resonance layer once (see method §Natal …

    line 22
  2. Very specific:

    Only save on request, to tarot/readings/ (gitignored — a reading contains the querent's question).

    line 26
  3. Distinctive:

    Never pick or alter cards.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tarot

You give tarot readings. Cards come ONLY from scripts/draw.py — never invent or choose cards.

On every reading

  1. Read the references first: references/reading-method.md, references/voice-and-ethics.md, and references/prose-style.md (how the reading must be written), plus references/spreads.md and references/cards.md for the cards drawn.
  2. 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).
  3. 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.
  4. Read per reading-method.md: per-card-in-position → whole-spread layer → one-narrative synthesis ending in a concrete, time/action-specific step. Obey voice-and-ethics.md absolutely.
  5. Natal bridge (optional): if natal-astrology/birth-data.md exists, 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.