Widget v1.0.0
Reading + Divination + Love
Save this plugin to Following and return to review observed changes. Follow up to 10 plugins free.
From the marketplace listing
Draw tarot cards, see what they mean, and talk about your reading with ChatGPT. This tarot app lets you pick cards, build a tarot spread, and get a clear AI tarot reading in one place. You can draw one card, three cards, or more. Then you can ask questions about the cards you picked. ChatGPT can help explain the symbols, themes, and ideas in your reading using simple words. It is made for people who want an easy, interactive tarot reading. You do not need to know tarot. You do not need to remember card meanings. Just draw your cards and start talking. Use the app for a daily tarot card, a three card tarot spread, a love tarot reading, a career tarot reading, a relationship reading, or a reading about a choice you need to make. You can also use it for quiet self-reflection, journaling, or to think about a question in a new way. The main difference is that the reading does not stop after the cards are shown. You can keep the chat going. Ask things like: “What does this card mean for me?” “Why did these two cards come up together?” “What is the main theme in this spread?” “What should I think about next?” “Can you explain this in a simpler way?” “What does this card mean for love, work, or friendship?” You can ask follow-up questions for as long as you want. This makes the app feel more like an interactive tarot reader than a fixed card generator. The app is simple to use. First, think of a question or topic. Next, draw your tarot cards. Then look at the cards in your spread. After that, ask ChatGPT to help you explore what they may mean. You can focus on one card, compare several cards, or talk about the whole reading. You can also use the app when you do not have a question. Draw a card for the day and ask what idea it may point to. Draw three cards and use them as past, present, and future. Or draw cards just to learn the tarot deck and practice reading card meanings. This can help new tarot users learn as they go. Instead of looking up every card on a different page, you can ask about the card right inside the chat. You can ask about a symbol, a suit, a number, a person in the picture, or the way two cards work together. More experienced tarot users can use it too. You can draw your own spread, test a new tarot question, compare possible meanings, or use ChatGPT as a thinking partner while you read the cards yourself. The app is built for conversation. Tarot cards can have more than one meaning, and the meaning can change with the question, the spread, and the other cards around it. That is why follow-up questions can be useful. You can give more context, change the focus, or ask for another way to read the same spread. You can use the app for many common tarot topics, including love, dating, friendship, work, money, goals, choices, change, confidence, creativity, and personal growth. You can also use it for simple prompts such as “What should I pay attention to today?” or “What can I learn from this situation?” The app does not tell you what will happen for sure. Tarot is best used as a tool for reflection, ideas, and conversation. The cards can help you notice thoughts, feelings, fears, hopes, and choices. You are still the person who decides what to do. There is no need to treat a reading as a rule. If a card feels useful, explore it. If it does not fit, ask another question, look at it in a different way, or leave it. This tarot app brings together a virtual tarot deck, AI tarot interpretation, and ChatGPT conversation. You can draw tarot cards online, explore tarot card meanings, try different tarot spreads, and ask follow-up questions without leaving the chat. If you are looking for an AI tarot reading, a ChatGPT tarot app, a tarot card picker, a three card tarot reading, a daily tarot card, or a simple way to learn tarot, this app gives you a place to draw, read, ask, and think. Pick a card. See what comes up. Ask what it could mean. Keep the conversation going.
Language: English · Automatically detected from descriptions.
Oct 27, 2026 · 1 saved observations
Metadata · Oct 27, 2026 · 01:01 UTC · Compared with Oct 24, 2026 · 13:48 UTC
Package or technical metadata updated
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Oct 24, 2026 · 13:48 UTC
Not present
Oct 27, 2026 · 01:01 UTC
false
From the developer’s listing and package; capabilities are not independently tested. Package observed Nov 3, 2026.
Review scenarios; not an exhaustive list.
This plugin does not sell products or process payments.
Terms may have changed since this observation.
List available resources then invoke `offer-cards` to set up a one-card reflection.
From the developer.
--- name: creative-block-breakthrough description: Use a Tarot app spread to overcome a fiction-writing block, then turn the completed cards into three story directions and a short writing exercise. Use when the user asks for tarot-inspired help with a stuck scene, character motive, plot conflict, or turning point. Do not use for ordinary life readings, predictions, or image generation. --- # Creative Block Breakthrough ## Inputs Use the story premise, the specific writing block, and any tone, genre, or continuity constraints already supplied. Ask one concise question if the bottleneck is unclear. Work with the available story context without requiring a full manuscript. ## Workflow 1. Restate the writing problem in one sentence. Identify any established story facts that proposed directions must preserve. Frame the cards as creative prompts that the writer may adapt or reject. 2. Reuse a completed spread if the user explicitly wants story ideas from it. Otherwise, call `offer-cards` with a trimmed, non-empty `instruction` of at most 240 characters connecting the draw to the writing problem, and these ordered `roles`: - `The central tension` - `An overlooked motive` - `A possible turning point` Keep each role within 64 characters and any optional `reason` within 500 characters. Do not request specific cards, reversals, or extra tool arguments. 3. Tell the user to draw all three cards and select **Interpret these cards**, then yield. Resume only when the completed spread and interpretation request are available. Do not invent a draw or operate the widget. 4. Read the actual role/card pairs from model-visible `modelContent` or the widget's follow-up message. Confirm that the spread is complete and keep the supplied roles when reusing a spread. Treat all app cards as upright and keep the remaining shuffled cards private. 5. Address each card in its role through general symbolic associations, then connect the spread to the writing problem. Do not claim to see artwork from card names alone or describe card meanings as text supplied by the app. 6. Generate three distinct story directions grounded in the premise. For each, name the card/role connection and describe a concrete character choice, conflict, or scene change. Mark new story material as a proposal and flag any direction that intentionally challenges an established fact. 7. Give one 10–15 minute writing exercise with a concrete starting task and stopping point. Let the writer choose a direction; do not require another draw to resolve which idea is best. ## Deliverable Provide a brief card-to-story mapping, three numbered story directions, and one short writing exercise. Keep the output focused on the stated block instead of expanding into an unsolicited outline or full scene. ## Boundaries - Use only actual completed spreads. If setup data is all that is available, wait for the user to draw and request interpretation. - Treat the output as fictional possibilities. Do not infer hidden truths about the author, real people, or future events from the cards. - Preserve the writer's supplied constraints and creative agency. Do not present a card as evidence that a story choice is correct. - If the tool or selected cards are unavailable, request the missing context without pretending that a Tarot app session occurred.
Referenced files: 1 — file references are metadata, not package contents.
--- name: decision-reflection description: Guide a reflective comparison of two options through a Tarot app spread, then turn the completed cards into a comparison and a reversible next step. Use when the user asks to think through a choice or compare paths using tarot. Do not use for a routine reading alone, certain predictions, or medical, legal, or financial recommendations. --- # Decision Reflection ## Inputs Use the situation, two options, relevant values, and practical constraints already supplied in the conversation. Ask one concise question when essential context is missing. If there are more than two options, ask which pair to compare before opening a spread. ## Workflow 1. Summarize the choice and identify what the user wants to understand. Keep reported facts and uncertainties separate. Frame the cards as prompts for reflection and keep the decision with the user. 2. Reuse a completed spread if the user explicitly wants to apply it to this choice. Otherwise, call `offer-cards` with a trimmed, non-empty `instruction` of at most 240 characters that briefly describes the choice, and these ordered `roles`: - `What matters most` - `Option A lens` - `Option B lens` - `An overlooked concern` - `A useful next step` Identify Option A and Option B in the conversation. Keep each role within 64 characters and any optional `reason` within 500 characters. Do not add arguments for card identities, orientation, or randomness. 3. After opening the table, tell the user to draw every card and select **Interpret these cards**, then yield. The tool response contains setup data, not drawn cards. Resume when the completed spread and the user's interpretation request arrive; do not choose cards or operate the widget. 4. Read the actual instruction, roles, and selected cards from model-visible `modelContent` or the widget's follow-up message. Verify that every role has a selected card before interpreting. Preserve each role/card pairing and treat every card as upright. Do not access or infer the private deck order. 5. Address each position briefly, then compare the two options using the user's stated values and constraints. Label symbolic themes as possible perspectives. Do not turn a favorable card into evidence that an option will succeed, or invent facts about either option. 6. Suggest one small, reversible step that gathers information or tests an assumption. Tie it to an unresolved question and give the user a simple way to reflect afterward. ## Deliverable Produce a concise position-by-position reading, followed by a two-row table with the option, known practical considerations, symbolic reflection, and one question to investigate. End with the proposed next step and one reflection question. Retain the original roles when reusing an earlier spread. ## Boundaries - Interpret only actual, completed spreads; never fill missing positions or replace an existing spread without the user's request. - Use neutral symbolic guidance. Do not claim certainty, predict outcomes, or infer another person's private thoughts. - Keep medical, legal, and financial topics to values clarification and questions to discuss with an appropriate professional. Do not recommend a consequential action on the basis of cards. - If the tool or completed spread is unavailable, explain what is missing and request the needed context without fabricating a draw.
Referenced files: 1 — file references are metadata, not package contents.
--- name: reading-action-plan description: Turn a completed Tarot app reading into one to three manageable actions and a check-in question. Use when the user asks what to do with a reading, how to apply its themes, or how to make a practical plan from their drawn cards. Do not use for opening a routine spread, predicting outcomes, creating reminders, or medical, legal, or financial recommendations. --- # Reading Action Plan ## Inputs Use the completed spread, any interpretation already in the conversation, the user's priorities, and their available time or energy. Accept the current model-visible spread or an earlier reading the user supplies. Ask only for missing context that would materially change the plan. ## Workflow 1. Establish which reading the user wants to apply. Read the instruction, ordered roles, and selected card names from `modelContent`, the widget's follow-up message, or the user's supplied reading. Keep every role/card pairing intact and treat app cards as upright. Verify that every role has a card before deriving a plan from the spread. 2. If the spread is still being drawn, ask the user to finish and select **Interpret these cards**, then yield. If no reading is available, request it. Do not call `offer-cards` merely to replace missing context or produce an action plan from an existing reading. 3. Reuse the existing interpretation when available. If the user requests a plan from a completed spread without an interpretation, briefly address each position and synthesize it first. Treat widget status `submitted` as confirmation that the follow-up was sent, not evidence that a reading was generated or stored. 4. Identify the themes most relevant to the user's stated priorities. Use tentative language and distinguish symbolic suggestions from facts the user has reported. Invite the user to reject themes that do not fit. 5. Convert those themes into one to three small actions within the user's control. Make each action observable, feasible, and tied to a named card and role. Use the supplied time horizon; otherwise propose a modest plan for the coming week without implying the user has agreed to it. 6. End with one check-in question that helps the user assess usefulness or adjust the plan. Describe timing as a suggestion; do not claim to create a reminder, task, calendar event, or saved journal entry. ## Deliverable Give a short statement of the relevant themes and a compact table with: - Action - Card/role and the possible connection - Suggested timing or effort - A clear completion signal Finish with one check-in question. Keep the plan short enough to act on and avoid repeating a full reading that is already present. ## Boundaries - Use only the completed spread and information supplied in the conversation. Do not access the private shuffled remainder or invent cards, priorities, past actions, or outcomes. - Keep the reading reflective and symbolic. Do not present an action as required by the cards or as a guarantee of success. - For medical, legal, or financial topics, keep actions to reflection and gathering questions for an appropriate professional; do not derive advice or consequential decisions from tarot. - Deliver the plan in chat. Do not imply the app persists the interpretation, tracks progress, or schedules the check-in.
Referenced files: 1 — file references are metadata, not package contents.
--- name: reading-check-in description: Revisit an earlier Tarot app reading and intended actions using the user's reported experience, then identify lessons and a next step. Use when the user asks to check in on, review, or follow up on a previous reading supplied in the conversation. Open a fresh spread only when requested. Do not claim access to a reading archive, automatic reminders, or proof of predictions. --- # Reading Check-In ## Inputs Use the earlier reading or journal entry available in the conversation or supplied by the user: its question, any role/card pairs, interpretation, and intended actions. Use the user's account of what they tried and what changed. Ask one concise question to obtain essential missing context. ## Workflow 1. Identify the earlier reading being revisited. Ask which one when several are plausible. Do not treat the current widget state as a history archive or silently substitute it for the earlier session. If no earlier reading is available, request the reading or a summary before comparing sessions. 2. Reconstruct a short account of the original intention and proposed action from the available material. Preserve any supplied role/card pairs. If only a summary is available, label it as such and do not invent missing cards, positions, dates, or interpretations. 3. Ask what the user tried, what they noticed, and what still matters unless they have already explained it. Treat not taking an action as useful context. Separate reported events from the earlier symbolic interpretation; do not rewrite the reading to fit events or score its predictive accuracy. 4. Identify one useful lesson and a modest next step based on the user's experience and current priorities. Keep the action within the user's control and describe uncertainty plainly. 5. If the user explicitly requests a fresh spread, first summarize the check-in so far, then call `offer-cards` with a trimmed, non-empty `instruction` of at most 240 characters and these ordered `roles`: - `What has changed` - `What still needs attention` - `A useful next step` Keep roles within 64 characters and any optional `reason` within 500 characters. Do not add arguments for card selection or reversals. Tell the user to draw every card and select **Interpret these cards**, then yield until the completed spread and interpretation request arrive. 6. If a fresh spread was requested and completed, read its actual instruction, roles, and selected cards from model-visible `modelContent` or the widget's follow-up message. Verify that all roles have cards, treat app cards as upright, and interpret each position before synthesizing. Keep the earlier and fresh spreads distinct; compare only what their questions and roles support. Do not interpret a change of cards as evidence that fate changed. ## Deliverable Produce a compact comparison of the original intention, the action tried, the user-reported result, and the lesson learned. End with one practical next step and one reflection question. Include a fresh reading only after the user requests and completes it. Deliver the check-in in chat without implying that it has been saved or scheduled. ## Boundaries - Use conversation context and the user's supplied history; do not claim to retrieve prior sessions, track progress automatically, or inspect the private shuffled remainder. - Treat `submitted` as a sent follow-up status, not proof of a stored interpretation or a completed action. - Keep tarot as neutral symbolic reflection. Do not claim certainty, validate predictions, or infer another person's private thoughts. - Keep medical, legal, and financial matters to reflection and questions for an appropriate professional; do not recommend consequential actions based on cards.
Referenced files: 1 — file references are metadata, not package contents.
First version!
Declared in the saved package. Remote tools may change independently.
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Nov 3, 2026.
plugin_asdk_app_6ac8a6faf25c81919fe5efc5d9c36c71
Download plugin data (JSON)