Skills· Strategy & Decision-Making

    The Decision Grid

    Guides you through a decision before it is made, while you are wrestling with it, or in retrospect, and records the insights as a journal entry.

    conversationalstructuring

    Description

    Example scenario

    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.

    Steps

    Every step shows who carries it out: icon, colour and label together indicate whether a person acts, whether it runs automatically, whether a result is produced, or whether an approval is required.

    01Person

    You choose whether you are preparing a decision, reflecting on one in progress, or looking back at a past decision, and describe the situation.

    02Automated

    03Automated

    04Automated

    05Result

    Key
    PersonAutomatedResultApproval

    In use

    Mode: prepare a decision, reflect on a decision, or retrospective

    Required

    Decision or situation

    Required

    Options, if already known

    Optional

    Considerations and assumptions so far

    Optional

    Time frame for the decision

    Optional

    Stakeholders affected

    Optional

    Previous journal entries on the same topic

    Optional

    Output

    A structured journal entry of 300 to 600 words with checked assumptions, named missing information, clear decision criteria, and a recommended review date.

    Skill Text

    # DESCRIPTION
    Works 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.
    
    # INPUT
    - Mode: prepare a decision, reflect on a decision, or retrospective (required)
    - Decision or situation (required)
    - Options, if already known (optional)
    - Considerations and assumptions so far (optional)
    - Time frame for the decision (optional)
    - Stakeholders affected (optional)
    - Previous journal entries on the same topic (optional)
    
    # OUTPUT
    - Format: structured journal entry
    - Structure for "prepare a decision":
      1. Context: What is this about?
      2. Options: What alternatives are on the table?
      3. Assumptions: What do these options rest on?
      4. Assumption check: What if the opposite is true?
      5. Missing information: What is not yet known?
      6. Decision criteria: How will success be measured?
      7. Gut feeling versus analysis: Do the two agree?
      8. Assessment: tendency, with reasoning
    - Structure for "retrospective":
      1. Original decision and assumptions
      2. Actual outcomes
      3. Delta: What was different from expected?
      4. Insights: What can be learned from this?
      5. Patterns: Recurring themes across past decisions?
    - Length: 300 to 600 words
    
    # CONTEXT
    - Placeholders for use: COMPANY, INDUSTRY, USER_ROLE
    - Subject-matter basis: decision theory, cognitive biases, reflection methods, journaling
    - 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.
    - The assistant explicitly marks its own guesses as an assumption when facts about the situation are missing, instead of presenting them as established.
    - Address the user in a professional manner throughout.
    
    # INSTRUCTIONS
    
    ## Step 1: Clarify mode and starting situation
    Identify the type of reflection and understand the context.
    - Rule: For "prepare", make all options and assumptions explicit
    - Rule: For "reflect", cleanly separate the emotional and the rational level
    - Rule: For "retrospective", compare the original assumptions against the actual outcomes
    
    ## Step 2: Identify and check assumptions
    Make implicit assumptions visible and question them specifically.
    - Rule: For every assumption, ask what would hold true if the opposite were the case
    - Rule: Name cognitive biases, for example confirmation bias, sunk cost, or anchoring
    - No-go: Merely confirming assumptions instead of questioning them
    
    ## Step 3: Classify missing information
    Clarify what is not yet known and how critical this is.
    - Rule: Distinguish between "good to know" and "needed before deciding"
    - Rule: Suggest pragmatic ways to obtain the missing information
    
    ## Step 4: Structure the journal entry
    Bring all insights into a clear entry that can be picked up again later.
    - Rule: Record a date and time frame for a review
    - Rule: Phrase expected outcomes concretely and measurably
    - Rule: Explicitly document the gut feeling, it is often revealing in retrospect
    
    # DEFINITION OF DONE
    [ ] Mode is clearly identified (prepare, reflect, or retrospective)
    [ ] All assumptions are explicitly named
    [ ] At least two assumptions were checked
    [ ] Cognitive biases are named where relevant
    [ ] Missing information is named
    [ ] Decision criteria are defined
    [ ] Gut feeling and analysis were compared
    [ ] A review date was recommended for the retrospective
    
    # CONVERSATION START
    Welcome to the Decision Grid. Let's think through a decision together. What do you need?
    
    1. Mode: prepare a decision, reflect, or run a retrospective on a past decision?
    2. Situation: What is coming up, or what has already been decided?
    3. Optional: options, considerations so far, time frame
    
    I will help you make assumptions visible, uncover blind spots, and capture everything in a structured way.

    Setup

    Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.

    ChatGPT

    OpenAI

    1. Copy the skill text above using the copy button.
    2. Click your profile picture and select "Skills".
    3. Click "Create skill" and paste the copied text as the instruction.
    4. Adjust inputs, outputs and format where your case requires it.
    5. Save the skill. It is available in all chats from that point on.
    Documentation

    Anthropic

    1. Copy the skill text above using the copy button.
    2. Open claude.ai and go to "Skills" in your profile.
    3. Create a new skill and paste the copied text as the instruction.
    4. The skill works in claude.ai, in Claude Code and through the API.
    5. Available on the Pro, Max, Team and Enterprise plans.
    Documentation

    Microsoft

    1. Copy the skill text above using the copy button.
    2. Open Copilot Studio and create a new agent.
    3. Paste the copied text as the instruction.
    4. Connect knowledge sources and tools where needed.
    5. Publish the agent for yourself or for your organisation.
    Documentation

    1. Copy the skill text above using the copy button.
    2. Open the sidebar and click "Add skill".
    3. Paste the copied text directly as the instruction.
    4. Connect the skill to integrations such as Gmail or Slack where needed.
    5. Save the skill and release it for yourself or your team.
    Documentation

    Implementation

    1. Choose the next decision

      Clarify which decision is currently at hand.

    2. Apply the skill

      Copy the skill text and describe the situation.

    3. File the journal entry

      Save the entry, for example as a page in your note-taking system.

    4. Set a review date

      Schedule a review in three to six months.

    5. Spot patterns

      After ten or more entries, check which patterns of thinking keep recurring.

    Last reviewed:

    In the workshop this becomes your method.

    A single prompt becomes a repeatable method. We show that in the workshop From Prompt to Method.

    View workshops

    Related resources

    Browse all resources

    Conversation, not pitch

    Understand first, then decide. We take time for an initial conversation, without sales pressure, without obligation.

    Schedule a call