run-tarot-reading SKILL.md skillA

run-tarot-reading from whoamimi/plugin-mimi is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add whoamimi/plugin-mimi/run-tarot-reading@git:20261019.c366762

Pins git:20261019.c366762 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
whoamimi/plugin-mimi
Path
plugins/craft-skills/skills/run-tarot-reading/SKILL.md
Versions recorded
2
Latest version
git:20261019.c366762, committed Oct 19, 2026
First version recorded
Oct 19, 2026
Size
4,887 bytes
Repository stars
3
License
none declared

Runs an interactive tarot reading in which the user picks their own cards from a shuffled 78-card deck, then gives a woven interpretation, for three-card spreads, single daily pulls, clarifiers and larger spreads. Use when the user mentions tarot, asks to draw or pull cards, or asks an open reflective question in a divination-flavoured way, even without saying "tarot". Examples include "read my cards", "do a daily pull", "give me a three-card spread about work" and…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Tarot card draw

A full 78-card Rider-Waite-Smith deck with a real shuffle, upright and reversed
orientations, and — the point of the whole thing — the querent choosing their own
cards from a face-down deck rather than watching you deal.

## Why the picking matters

Anyone can ask for three random cards. What makes a reading feel like a reading
is agency: the pause, the question held in mind, the finger landing on card 41
for no reason the querent can explain. Preserve that. Default to the pick flow
and only auto-draw when the querent asks you to just deal.

## Workflow

### 1. Set the question and the spread

Ask what is on their mind, or accept the question they already gave. Choose a
spread that fits it — see `references/spreads.md` for the catalog. Past /
Present / Future is the default, but Situation / Obstacle / Advice serves a
specific problem far better, and naming the choice makes the reading feel
tailored.

Keep this step to one or two sentences. Do not interrogate someone who just
wants cards.

### 2. Shuffle and present the face-down deck

```bash
python3 scripts/tarot.py shuffle --spread "Situation / Obstacle / Advice"
```
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_wcb7miqnsng7c6m7/322d32ce82d59230f668530a94a8eb2688cd4db0460bee98d4e63a4a8ccb2def.json

Then /plugin install run-tarot-reading@markdownregistry-wcb7miqnsng7c6m7 in Claude Code. It installs git:20261019.c366762, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add whoamimi/plugin-mimi/run-tarot-reading@sha256:322d32ce82d59230

The line at the top of this page pins the label git:20261019.c366762, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wcb7miqnsng7c6m7.svg)](https://markdownregistry.com/a/art_wcb7miqnsng7c6m7)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in whoamimi/plugin-mimi/run-tarot-reading since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of run-tarot-reading from somewhere else? Ask it: where did my run-tarot-reading come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, all committed on Oct 19, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261019.c366762 latest2026-10-19 c366762 4,887 BA view · diff
git:20261019.22a32e32026-10-19 22a32e3 4,921 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4887 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

whoamimi/plugin-mimi · 3 stars · license none declared · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_wcb7miqnsng7c6m7
GET https://markdownregistry.com/api/v1/resolve?ref=whoamimi/plugin-mimi/run-tarot-reading
GET https://markdownregistry.com/api/v1/blob/322d32ce82d59230f668530a94a8eb2688cd4db0460bee98d4e63a4a8ccb2def

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from whoamimi/plugin-mimi

plugin-mimi Plugin marketplace
whoamimi/plugin-mimi · .claude-plugin/marketplace.json · Mimi's personal Claude plugins: life admin, communication and writing, creative crafts, coding and security, and core…
v1.0.0 · audit A · 3 stars
backup-project SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/backup-project/SKILL.md · Briefs the user on CLI steps to back up a local project to GitHub, together with a checklist of their current local…
git:20261110.44b066c · audit F · 3 stars
depth-breakdown SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/depth-breakdown/SKILL.md · Breaks a project idea, or an existing list of steps, into nested subtasks to a chosen depth (1-5), drawn as a Mermaid…
git:20261019.c366762 · audit A · 3 stars
get-started SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/get-started/SKILL.md · Interactive, strictly local project-setup guide that scaffolds a new project inside the user's already-open, empty VS…
git:20261022.6b7da83 · audit B · 3 stars
git-repository-setup SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/git-repository-setup/SKILL.md · Sets up a project's git repository with best practices — a main default branch, .gitignore and .gitattributes…
git:20261110.2a36614 · audit A · 3 stars
mimi-cyber SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/mimi-cyber/SKILL.md · Keeps the user's cybersecurity and AI governance learning notes — news article summaries plus YAML catalogs of attack…
git:20261110.2a36614 · audit A · 3 stars
python-like-mimi SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/python-like-mimi/SKILL.md · Enforce functional-first, type-safe Python with Pydantic, dataclasses, enums, decorators, hooks, and lightweight…
git:20261110.44b066c · audit A · 3 stars
react-like-mimi SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/react-like-mimi/SKILL.md · Enforce functional-first, type-safe React Web development using TypeScript, Zod, hooks, composition, and modular…
git:20261110.44b066c · audit A · 3 stars
react-native-like-mimi SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/react-native-like-mimi/SKILL.md · Enforce functional-first, type-safe React Native and Expo development using TypeScript, Zod, hooks, composition…
git:20261110.44b066c · audit A · 3 stars
write-readme SKILL.md skill
whoamimi/plugin-mimi · plugins/code-skills/skills/write-readme/SKILL.md · Writes or updates a project's README.md to match a fixed template with badges, highlights, directory overview, system…
git:20261115.db8ba56 · audit A · 3 stars
create-brand-assets SKILL.md skill
whoamimi/plugin-mimi · plugins/craft-skills/skills/create-brand-assets/SKILL.md · Generates a matching brand kit (icons, banners, emoji, stickers, feature graphics, mascots) for an app, bot or project…
git:20261110.2a36614 · audit A · 3 stars
get-astro-today SKILL.md skill
whoamimi/plugin-mimi · plugins/craft-skills/skills/get-astro-today/SKILL.md · Reports today's influences from Vedic, Western and Lunar astrology for the user, each as a short table with one or two…
git:20261019.c366762 · audit A · 3 stars

Every file in whoamimi/plugin-mimi

Browse by kind, by grade A, or by owner.