Most decisions get made faster than the underlying assumptions get checked. The Decision Grid starts exactly there: it works as a structured reflection partner, whether you have a decision still ahead of you, are in the middle of weighing it up, or want to evaluate a decision you have already made in retrospect.
\nThe result is a journal entry with a clear structure: context, options, assumptions and their counter check, missing information, decision criteria, and a comparison between gut feeling and analysis. In a retrospective, it additionally compares what actually happened against what was expected and what this means for future decisions. Across multiple entries, this builds a personal decision archive that reveals recurring thinking patterns.
\nThe skill does not make a decision for you, and it replaces neither a second opinion in conversation nor solid market data. It offers structured reflection, and its value depends on how openly you let your own assumptions be examined. For legal or medical questions, it consistently points to the relevant professional advice.
\n" }, { "id": "skill-text", "title": "Skill Text", "html": "Copy the prompt below in full into your AI tool. As a file: entscheidungs-raster.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Describe mode and situation", "beschreibung": "You choose whether you are preparing a decision, reflecting on one in progress, or looking back at a past decision, and describe the situation.", "rolle": "mensch" }, { "nr": 2, "titel": "Challenge assumptions", "beschreibung": "The skill surfaces implicit assumptions and names cognitive biases that could be distorting the assessment.", "rolle": "automatisch" }, { "nr": 3, "titel": "Assess missing information", "beschreibung": "It separates what is merely good to know from what genuinely needs to be resolved before deciding.", "rolle": "automatisch" }, { "nr": 4, "titel": "Structure the journal entry", "beschreibung": "Insights, the comparison between gut feeling and analysis, and a review date are brought into a fixed structure.", "rolle": "automatisch" }, { "nr": 5, "titel": "Finished journal entry", "beschreibung": "A structured reflection with a review date is ready and can be picked up again later.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Choose the next decision", "text": "Clarify which decision is currently at hand." }, { "titel": "Apply the skill", "text": "Copy the skill text and describe the situation." }, { "titel": "File the journal entry", "text": "Save the entry, for example as a page in your note-taking system." }, { "titel": "Set a review date", "text": "Schedule a review in three to six months." }, { "titel": "Spot patterns", "text": "After ten or more entries, check which patterns of thinking keep recurring." } ], "zutaten": [ "Mode", "Situation" ], "beispielSzenario": "A founder is weighing whether to enter a new market or deepen the existing product. She describes the situation to the skill, along with her options and the assumptions behind her current leaning. The Decision Grid walks her through the reflection: what assumptions sit behind each option, what would hold true if the opposite were the case, and what information is still missing. The result is a journal entry with a review date six months out, at which point she can check whether her assessment held up.", "eingaben": [ { "feld": "Mode: prepare a decision, reflect on a decision, or retrospective", "pflicht": true }, { "feld": "Decision or situation", "pflicht": true }, { "feld": "Options, if already known", "pflicht": false }, { "feld": "Considerations and assumptions so far", "pflicht": false }, { "feld": "Time frame for the decision", "pflicht": false }, { "feld": "Stakeholders affected", "pflicht": false }, { "feld": "Previous journal entries on the same topic", "pflicht": false } ], "ausgabe": "A structured journal entry of 300 to 600 words with checked assumptions, named missing information, clear decision criteria, and a recommended review date.", "prompt": "# DESCRIPTION\nWorks as a structured reflection partner through decisions. Makes assumptions visible, uncovers blind spots, and records insights as a decision journal entry so they remain usable for later situations.\n\n# INPUT\n- Mode: prepare a decision, reflect on a decision, or retrospective (required)\n- Decision or situation (required)\n- Options, if already known (optional)\n- Considerations and assumptions so far (optional)\n- Time frame for the decision (optional)\n- Stakeholders affected (optional)\n- Previous journal entries on the same topic (optional)\n\n# OUTPUT\n- Format: structured journal entry\n- Structure for \"prepare a decision\":\n 1. Context: What is this about?\n 2. Options: What alternatives are on the table?\n 3. Assumptions: What do these options rest on?\n 4. Assumption check: What if the opposite is true?\n 5. Missing information: What is not yet known?\n 6. Decision criteria: How will success be measured?\n 7. Gut feeling versus analysis: Do the two agree?\n 8. Assessment: tendency, with reasoning\n- Structure for \"retrospective\":\n 1. Original decision and assumptions\n 2. Actual outcomes\n 3. Delta: What was different from expected?\n 4. Insights: What can be learned from this?\n 5. Patterns: Recurring themes across past decisions?\n- Length: 300 to 600 words\n\n# CONTEXT\n- Placeholders for use: COMPANY, INDUSTRY, USER_ROLE\n- Subject-matter basis: decision theory, cognitive biases, reflection methods, journaling\n- Important constraint: The assistant does not make the decision for anyone, it offers structured reflection only. For legal or medical topics, it points to the relevant professional advice.\n- The assistant explicitly marks its own guesses as an assumption when facts about the situation are missing, instead of presenting them as established.\n- Address the user in a professional manner throughout.\n\n# INSTRUCTIONS\n\n## Step 1: Clarify mode and starting situation\nIdentify the type of reflection and understand the context.\n- Rule: For \"prepare\", make all options and assumptions explicit\n- Rule: For \"reflect\", cleanly separate the emotional and the rational level\n- Rule: For \"retrospective\", compare the original assumptions against the actual outcomes\n\n## Step 2: Identify and check assumptions\nMake implicit assumptions visible and question them specifically.\n- Rule: For every assumption, ask what would hold true if the opposite were the case\n- Rule: Name cognitive biases, for example confirmation bias, sunk cost, or anchoring\n- No-go: Merely confirming assumptions instead of questioning them\n\n## Step 3: Classify missing information\nClarify what is not yet known and how critical this is.\n- Rule: Distinguish between \"good to know\" and \"needed before deciding\"\n- Rule: Suggest pragmatic ways to obtain the missing information\n\n## Step 4: Structure the journal entry\nBring all insights into a clear entry that can be picked up again later.\n- Rule: Record a date and time frame for a review\n- Rule: Phrase expected outcomes concretely and measurably\n- Rule: Explicitly document the gut feeling, it is often revealing in retrospect\n\n# DEFINITION OF DONE\n[ ] Mode is clearly identified (prepare, reflect, or retrospective)\n[ ] All assumptions are explicitly named\n[ ] At least two assumptions were checked\n[ ] Cognitive biases are named where relevant\n[ ] Missing information is named\n[ ] Decision criteria are defined\n[ ] Gut feeling and analysis were compared\n[ ] A review date was recommended for the retrospective\n\n# CONVERSATION START\nWelcome to the Decision Grid. Let's think through a decision together. What do you need?\n\n1. Mode: prepare a decision, reflect, or run a retrospective on a past decision?\n2. Situation: What is coming up, or what has already been decided?\n3. Optional: options, considerations so far, time frame\n\nI will help you make assumptions visible, uncover blind spots, and capture everything in a structured way.", "einrichtung": { "intro": "Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.", "plattformen": [ { "plattform": "ChatGPT", "anbieter": "OpenAI", "schritte": [ "Copy the skill text above using the copy button.", "Click your profile picture and select \"Skills\".", "Click \"Create skill\" and paste the copied text as the instruction.", "Adjust inputs, outputs and format where your case requires it.", "Save the skill. It is available in all chats from that point on." ], "doku": { "label": { "de": "OpenAI Dokumentation: Skills in ChatGPT", "en": "OpenAI documentation: Skills in ChatGPT" }, "url": "https://help.openai.com/de-de/articles/20001066-skills-in-chatgpt" } }, { "plattform": "Claude", "anbieter": "Anthropic", "schritte": [ "Copy the skill text above using the copy button.", "Open claude.ai and go to \"Skills\" in your profile.", "Create a new skill and paste the copied text as the instruction.", "The skill works in claude.ai, in Claude Code and through the API.", "Available on the Pro, Max, Team and Enterprise plans." ], "doku": { "label": { "de": "Anthropic Dokumentation: Benutzerdefinierte Skills erstellen", "en": "Anthropic documentation: Creating custom skills" }, "url": "https://support.claude.com/de/articles/12512198-benutzerdefinierte-skills-erstellen" } }, { "plattform": "Copilot Studio", "anbieter": "Microsoft", "schritte": [ "Copy the skill text above using the copy button.", "Open Copilot Studio and create a new agent.", "Paste the copied text as the instruction.", "Connect knowledge sources and tools where needed.", "Publish the agent for yourself or for your organisation." ], "doku": { "label": { "de": "Microsoft Dokumentation: Einen Agent erstellen und bereitstellen", "en": "Microsoft documentation: Create and deploy an agent" }, "url": "https://learn.microsoft.com/de-de/microsoft-copilot-studio/fundamentals-get-started" } }, { "plattform": "Langdock", "anbieter": null, "schritte": [ "Copy the skill text above using the copy button.", "Open the sidebar and click \"Add skill\".", "Paste the copied text directly as the instruction.", "Connect the skill to integrations such as Gmail or Slack where needed.", "Save the skill and release it for yourself or your team." ], "doku": { "label": { "de": "Langdock Dokumentation: Skills", "en": "Langdock documentation: Skills" }, "url": "https://docs.langdock.com/de/product/chat/skills" } } ] }, "itemIcon": "table-2", "recommended": [ { "slug": "debatten-drehbuch", "category": "skill", "name": "The Debate Playbook", "teaser": "Has three AI experts with opposing convictions debate each other in a structured format and derives a resilient synthesis for strategic decisions with no clearly right answer.", "domaene": "Strategie & Entscheidung", "itemIcon": "speech" }, { "slug": "domino-raster", "category": "skill", "name": "The Domino Grid", "teaser": "The Domino Grid traces a planned action across five levels of consequences to reveal where the real strategic opportunity actually lies.", "domaene": "Strategie & Entscheidung", "itemIcon": "waypoints" }, { "slug": "entscheidungs-dossier", "category": "skill", "name": "The Decision Dossier", "teaser": "The Decision Dossier turns a decision question, options and context into a structured decision template with a weighted scoring matrix, pros and cons, a risk assessment and a substantiated recommendation.", "domaene": "Strategie & Entscheidung", "itemIcon": "scale" }, { "slug": "muster-dossier", "category": "skill", "name": "The Pattern Dossier", "teaser": "Collects a series of decisions, projects, or content and exposes the overarching pattern behind them, including the actual unconscious strategy, real selection criteria, and blind spots.", "domaene": "Strategie & Entscheidung", "itemIcon": "grid-2x2" }, { "slug": "rueckpfad-manoever", "category": "skill", "name": "The Backcasting Maneuver", "teaser": "Describe your ideal end state and let the AI work backward step by step to today, surfacing the path a forward plan would miss.", "domaene": "Strategie & Entscheidung", "itemIcon": "corner-up-left" }, { "slug": "business-case-dokumentierer", "category": "assistent", "name": "The Business Case Documenter", "teaser": "Turns a project idea, an investment or an initiative into the form decision makers actually read: benefits, costs, risks and a clear recommendation, cleanly structured and free of jargon.", "domaene": "Strategie & Entscheidung", "itemIcon": "trending-up" }, { "slug": "gegenargument-sparringspartner", "category": "assistent", "name": "The Counterargument Sparring Partner", "teaser": "Tests a thesis or decision by formulating well-founded counterarguments and systematically questioning assumptions, evidence and logic.", "domaene": "Strategie & Entscheidung", "itemIcon": "shield-half" }, { "slug": "wettbewerbskraefte-pruefer", "category": "assistent", "name": "The Five Forces Analyzer", "teaser": "Analyzes an industry systematically using Michael Porter's five competitive forces and derives a well founded assessment of market attractiveness.", "domaene": "Strategie & Entscheidung", "itemIcon": "swords" }, { "slug": "grill-me", "category": "tool", "name": "grill-me", "teaser": "grill-me is an external skill repository by Matt Pocock that clarifies plans and designs through persistent questioning, branch by branch, before any code is written.", "domaene": "Strategie & Entscheidung" }, { "slug": "feedback-route", "category": "workflow", "name": "The Feedback Route", "teaser": "A daily automated report that sorts incoming customer feedback by sentiment and topic and immediately flags critical cases to the team.", "domaene": "Kundensupport & Service", "itemIcon": "message-square-quote" } ] }