Skip to content

hoavdc/CodexKit / skills/codexkit-sales-forecast-analyzer

codexkit-sales-forecast-analyzer

Unverified

Analyze sales pipeline, historical revenue, conversion rates, and assumptions to produce forecast scenarios. Use for sales reviews, RevOps planning, and founder revenue forecasting.

Sales Forecast Analyzer

When to Use

  • Forecasting revenue from historical sales or active pipeline.
  • Preparing weekly, monthly, or quarterly sales reviews.
  • Comparing committed, best-case, and upside scenarios.
  • Explaining forecast movement to founders, finance, RevOps, or sales leadership.

Procedure

Step 1 - Normalize Inputs

Separate actuals, pipeline, assumptions, and qualitative signals. Do not mix closed revenue with open pipeline.

Step 2 - Segment The Pipeline

Group opportunities by stage, close date, owner, segment, product, and confidence where available.

Step 3 - Apply Forecast Logic

Choose the simplest defensible method:

  • historical trend for stable recurring sales
  • stage-weighted pipeline for active opportunities
  • rep commit for manager-reviewed forecast
  • scenario range when inputs are uncertain

Step 4 - Explain Drivers

Identify the movement drivers:

  • new pipeline
  • slipped deals
  • closed-won / closed-lost
  • expansion / contraction
  • conversion rate change
  • average deal size change

Step 5 - Produce Scenarios

Provide Base, Upside, and Downside scenarios with assumptions and confidence. Flag data quality gaps.

Inputs

InputRequiredFormat
Historical salesRecommendedPeriod, revenue, bookings, units
PipelineRecommendedDeal, amount, stage, probability, close date
Sales cycle assumptionsOptionalWin rate, stage duration, seasonality
Forecast horizonYesMonth, quarter, year
Business contextOptionalPromotions, market changes, hiring, capacity

Output

## Sales Forecast - [Period]

### Executive Summary
[Forecast number, confidence, main movement drivers]

### Scenario Forecast
| Scenario | Forecast | Assumptions | Confidence |
|----------|----------|-------------|------------|

### Pipeline Movement
| Driver | Impact | Notes |
|--------|--------|-------|

### Risks And Watch Items
- [Risk] - [mitigation]

### Data Quality Notes
- [Missing fields, stale opportunities, probability caveats]

Quality Criteria

  • Forecast method is stated and fits the available data.
  • Actuals, pipeline, and assumptions are clearly separated.
  • Scenario assumptions are visible and testable.
  • Data quality gaps are not hidden.
  • Recommendations are operational, not just numerical.

Verification (4C)

CheckQuestion
CorrectnessAre formulas, stage weights, win rates, dates, and totals calculated consistently?
CompletenessAre actuals, open pipeline, assumptions, scenarios, and risks all covered?
Context-fitDoes the method match the sales motion, cycle length, and data maturity?
ConsequenceWhat decision could be distorted if this forecast is overconfident?

Edge Cases

  • Sparse history - Use scenario ranges and clearly mark confidence as low.
  • Stale pipeline - Flag opportunities with old next steps or close dates before including them.
  • Enterprise deal concentration - Show forecast with and without the largest deals.
  • Seasonal business - Avoid straight-line forecasts unless seasonality is explicitly addressed.

Examples

Prompt: "Use this opportunity export to forecast Q3 bookings. Show commit, base, and upside scenarios and explain slipped-deal risk."

Good pattern: "Base forecast is $1.2M because 64% of weighted pipeline is in late-stage deals with close dates before quarter end. Confidence is medium because 3 of 8 largest deals have stale next steps."

Definition of Done

  • Forecast number and range are defensible from inputs.
  • Assumptions are explicit.
  • Risks and confidence are visible.
  • A sales leader can act on next steps.

Changelog

  • v1.0.0 - Initial release
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 318kUpdated Claude CodeCodexUnverifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 117kUpdated Claude CodeCodexUnverifiedInstall