
Sales Forecast Workbook
Builds an Excel sales forecast with trend, seasonality, bands, scenarios and sensitivity.
- Repository
- genspark-ai/genoffice
- Stars
- 11,537
- Licence
- Apache-2.0
- Files
- 1 file
What it does
When installed, the agent turns your historical sales numbers into a forecast for future periods. It splits the history into trend and seasonal patterns, then delivers an Excel workbook with history, assumptions, a forecast chart, optimistic/base/pessimistic scenarios, a sensitivity table and a notes sheet explaining the method and limits. The forecast is built with spreadsheet formulas so changing the history or assumptions updates the results.
Great for
- Sales or finance staff who want a first-pass forecast in Excel with transparent formulas
- Small businesses with at least two years of monthly sales data planning next year
- Analysts who want a documented method, assumptions and limitations rather than a black-box number
Skip it if
- Very short or noisy histories: with less than two full seasonal cycles the skill only does a trend forecast, and the results are weak evidence
- Setting sales targets or commitments: the skill itself states a forecast is not a target and its bands are statistical intervals, not guarantees
Try asking
- “Forecast next year from these two years of monthly sales”
- “Give this forecast optimistic, base and pessimistic scenarios”
- “Show how sensitive the full-year total is to growth rate and seasonal strength”
- “Identify promotion spikes or stock-outs in my monthly data and compare results with and without them”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
sales-forecast.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip sales-forecast.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip sales-forecast.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide at least 24 months of monthly data (or equivalent) so seasonal factors are meaningful; state product or region splits if relevant
- Tell the agent about known future events such as price changes or promotions, and their expected impact source, so they are recorded as assumptions
- Review the Assumptions and Notes sheets before using any figure, and refresh the forecast as new actuals arrive
What's inside
- SKILL.md
Redistributed unmodified from genspark-ai/genoffice under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.