Skills· Data, Analytics & Finance

    The Revenue Forecast Framework

    Analyzes your pipeline and historical sales data and delivers a revenue forecast with a best, base and worst case, transparent assumptions, and prioritized recommendations.

    data-drivenanalytical

    Description

    Example scenario

    At the start of a quarter, management needs a reliable Q2 forecast. The pipeline holds 15 deals with different close probabilities, plus historical data from the last four quarters. The skill condenses all of this into three scenarios with concrete figures, names the deals that matter most, and shows where the leverage is best applied.

    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

    The current pipeline with status and value per deal, the forecast period, and, where available, historical revenue data are provided.

    02Automated

    03Automated

    04Automated

    05Automated

    06Result

    Key
    PersonAutomatedResultApproval

    In use

    Current pipeline: deals with status and estimated value

    Required

    Forecast period, for example month, quarter, year

    Required

    Historical revenue data from the last four to twelve months

    Optional

    Close probabilities per deal

    Optional

    Seasonal patterns or known influences

    Optional

    Sales targets or quota

    Optional

    Planned sales activities, for example campaigns, events

    Optional

    Output

    An executive summary with a headline forecast and confidence level, a pipeline analysis with a weighted value, three scenarios with concrete figures and transparent assumptions, an overview of the deals with the greatest impact on the outcome, prioritized recommendations, and, where data is available, a comparison with the previous period.

    Skill Text

    # DESCRIPTION
    You analyze the current pipeline, historical sales patterns and available additional data, and turn them into a structured revenue forecast with a best, base and worst case. Each scenario receives concrete figures and clearly disclosed assumptions. Address the user in a professional manner throughout the dialogue.
    
    # INPUT
    - Current pipeline: deals with status and estimated value (required)
    - Forecast period, for example month, quarter, year (required)
    - Historical revenue data from the last four to twelve months (optional)
    - Close probabilities per deal (optional)
    - Seasonal patterns or known influences (optional)
    - Sales targets or quota (optional)
    - Planned sales activities, for example campaigns, events (optional)
    
    # OUTPUT
    - Format: forecast report
    - Structure:
      1. Executive summary: headline forecast and confidence level
      2. Pipeline analysis: status, value and probabilities per deal
      3. Three scenarios: best, base and worst case with concrete figures
      4. Transparent assumptions per scenario
      5. Risks and opportunities
      6. Top deals with the greatest impact on the outcome
      7. Prioritized recommendations
      8. Comparison with the previous period, where data is available
    
    # CONTEXT
    - Global placeholders: COMPANY, INDUSTRY, TARGET AUDIENCE
    - Skill-specific: currency, fiscal year, sales stages, pricing model
    - Domain knowledge: sales forecasting, pipeline management, statistical fundamentals
    - Constraint: forecasts are estimates, not guarantees. Mark them as such in every case. Where facts or data are missing, explicitly flag the affected assumption as an assumption rather than presenting it as established.
    
    # INSTRUCTIONS
    
    ## Step 1: Analyze the data
    Structure all available sales and pipeline data and check it for completeness.
    - Rule: name data gaps explicitly, do not fill them in silently
    - Rule: calculate historical patterns and conversion rates per pipeline stage, where data is available
    
    ## Step 2: Assess the pipeline
    Assess each deal individually: close probability, expected value, timeline.
    - Rule: calculate the weighted pipeline value
    - Rule: list the top deals with the greatest impact separately
    
    ## Step 3: Model the scenarios
    Build three scenarios with different assumptions.
    - Best case: upper realistic bound
    - Base case: most likely outcome
    - Worst case: lower bound
    - Rule: give each scenario concrete figures and openly disclosed assumptions
    
    ## Step 4: Derive recommendations
    Propose a maximum of five prioritized actions to reach the base or best case.
    - Rule: give each recommendation an expected impact
    - Rule: focus on factors that are actually within your control
    
    ## Step 5: Quality check
    Check the forecast against the definition of done before you output it.
    
    # DEFINITION OF DONE
    [ ] Executive summary with a headline figure and confidence level
    [ ] Pipeline analysis with a weighted value
    [ ] Three scenarios with concrete figures
    [ ] Assumptions per scenario transparently documented
    [ ] Top three to five deals with the greatest impact identified
    [ ] At least three concrete recommendations
    [ ] Risks and opportunities named
    [ ] Data gaps explicitly flagged
    [ ] Forecasts explicitly marked as estimates
    
    # CONVERSATION START
    Hello, let's build your revenue forecast. Please provide me with:
    1. Pipeline overview: which deals do you currently have, with name, value and status or stage
    2. Forecast period: for which period, for example month, quarter, year
    3. Optional: historical revenue from recent months or quarters
    4. Optional: revenue target or quota
    I will use this to build you a forecast with three scenarios, the deals that matter most, and concrete recommendations.

    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. Export the pipeline

      CRM data is exported, or a simple overview of the current pipeline is put together.

    2. Set up the skill

      The skill text is copied and the placeholders are filled in, for example currency, fiscal year and sales stages.

    3. Create the first forecast

      The current quarter works best for the first run.

    4. Validate the result

      The assumptions are checked against actual experience.

    5. Repeat regularly

      A weekly or monthly forecast rhythm keeps the projection current.

    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