Agent skill
forecast
Generate a weighted sales forecast with best/likely/worst scenarios, commit vs. upside breakdown, and gap analysis. Use when preparing a quarterly forecast call, assessing gap-to-quota from a pipeline CSV, deciding which deals to commit vs. call upside, or checking pipeline coverage against your number.
Install this agent skill to your Project
npx add-skill https://github.com/anthropics/knowledge-work-plugins/tree/main/sales/skills/forecast
SKILL.md
/forecast
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Generate a weighted sales forecast with risk analysis and commit recommendations.
Usage
/forecast [period]
Generate a forecast for: $ARGUMENTS
If a file is referenced: @$1
How It Works
┌─────────────────────────────────────────────────────────────────┐
│ FORECAST │
├─────────────────────────────────────────────────────────────────┤
│ STANDALONE (always works) │
│ ✓ Upload CSV export from your CRM │
│ ✓ Or paste/describe your pipeline deals │
│ ✓ Set your quota and timeline │
│ ✓ Get weighted forecast with stage probabilities │
│ ✓ Risk-adjusted projections (best/likely/worst case) │
│ ✓ Commit vs. upside breakdown │
│ ✓ Gap analysis and recommendations │
├─────────────────────────────────────────────────────────────────┤
│ SUPERCHARGED (when you connect your tools) │
│ + CRM: Pull pipeline automatically, real-time data │
│ + Historical win rates by stage, segment, deal size │
│ + Activity signals for risk scoring │
│ + Automatic refresh and tracking over time │
└─────────────────────────────────────────────────────────────────┘
What I Need From You
Step 1: Your Pipeline Data
Option A: Upload a CSV Export your pipeline from your CRM (e.g. Salesforce, HubSpot). I need at minimum:
- Deal/Opportunity name
- Amount
- Stage
- Close date
Helpful if you have:
- Owner (if team forecast)
- Last activity date
- Created date
- Account name
Option B: Paste your deals
Acme Corp - $50K - Negotiation - closes Jan 31
TechStart - $25K - Demo scheduled - closes Feb 15
BigCo - $100K - Discovery - closes Mar 30
Option C: Describe your territory "I have 8 deals in pipeline totaling $400K. Two are in negotiation ($120K), three in evaluation ($180K), three in discovery ($100K)."
Step 2: Your Targets
- Quota: What's your number? (e.g., "$500K this quarter")
- Timeline: When does the period end? (e.g., "Q1 ends March 31")
- Already closed: How much have you already booked this period?
Output
# Sales Forecast: [Period]
**Generated:** [Date]
**Data Source:** [CSV upload / Manual input / CRM]
---
## Summary
| Metric | Value |
|--------|-------|
| **Quota** | $[X] |
| **Closed to Date** | $[X] ([X]% of quota) |
| **Open Pipeline** | $[X] |
| **Weighted Forecast** | $[X] |
| **Gap to Quota** | $[X] |
| **Coverage Ratio** | [X]x |
---
## Forecast Scenarios
| Scenario | Amount | % of Quota | Assumptions |
|----------|--------|------------|-------------|
| **Best Case** | $[X] | [X]% | All deals close as expected |
| **Likely Case** | $[X] | [X]% | Stage-weighted probabilities |
| **Worst Case** | $[X] | [X]% | Only commit deals close |
---
## Pipeline by Stage
| Stage | # Deals | Total Value | Probability | Weighted Value |
|-------|---------|-------------|-------------|----------------|
| Negotiation | [X] | $[X] | 80% | $[X] |
| Proposal | [X] | $[X] | 60% | $[X] |
| Evaluation | [X] | $[X] | 40% | $[X] |
| Discovery | [X] | $[X] | 20% | $[X] |
| **Total** | [X] | $[X] | — | $[X] |
---
## Commit vs. Upside
### Commit (High Confidence)
Deals you'd stake your forecast on:
| Deal | Amount | Stage | Close Date | Why Commit |
|------|--------|-------|------------|------------|
| [Deal] | $[X] | [Stage] | [Date] | [Reason] |
**Total Commit:** $[X]
### Upside (Lower Confidence)
Deals that could close but have risk:
| Deal | Amount | Stage | Close Date | Risk Factor |
|------|--------|-------|------------|-------------|
| [Deal] | $[X] | [Stage] | [Date] | [Risk] |
**Total Upside:** $[X]
---
## Risk Flags
| Deal | Amount | Risk | Recommendation |
|------|--------|------|----------------|
| [Deal] | $[X] | Close date passed | Update close date or move to lost |
| [Deal] | $[X] | No activity in 14+ days | Re-engage or downgrade stage |
| [Deal] | $[X] | Close date this week, still in discovery | Unlikely to close — push out |
---
## Gap Analysis
**To hit quota, you need:** $[X] more
**Options to close the gap:**
1. **Accelerate [Deal]** — Currently [stage], worth $[X]. If you can close by [date], you're at [X]% of quota.
2. **Revive [Stalled Deal]** — Last active [date]. Worth $[X]. Reach out to [contact].
3. **New pipeline needed** — You need $[X] in new opportunities at [X]x coverage to be safe.
---
## Recommendations
1. [ ] [Specific action for highest-impact deal]
2. [ ] [Action for at-risk deal]
3. [ ] [Pipeline generation recommendation if gap exists]
Stage Probabilities (Default)
If you don't provide custom probabilities, I'll use:
| Stage | Default Probability |
|---|---|
| Closed Won | 100% |
| Negotiation / Contract | 80% |
| Proposal / Quote | 60% |
| Evaluation / Demo | 40% |
| Discovery / Qualification | 20% |
| Prospecting / Lead | 10% |
Tell me if your stages or probabilities are different.
If CRM Connected
- I'll pull your pipeline automatically
- Use your actual historical win rates
- Factor in activity recency for risk scoring
- Track forecast changes over time
- Compare to previous forecasts
Tips
- Be honest about commit — Only commit deals you'd bet on. Upside is for everything else.
- Update close dates — Stale close dates kill forecast accuracy. Push out deals that won't close in time.
- Coverage matters — 3x pipeline coverage is healthy. Below 2x is risky.
- Activity = signal — Deals with no recent activity are at higher risk than stage suggests.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
anthropics/knowledge-work-plugins
view-pdf
Interactive PDF viewer. Use when the user wants to open, show, or view a PDF and collaborate on it visually — annotate, highlight, stamp, fill form fields, place signature/initials, or review markup together. Not for summarization or text extraction (use native Read instead).
anthropics/knowledge-work-plugins
signature-request
Prepare and route a document for e-signature — run a pre-signature checklist, configure signing order, and send for execution. Use when a contract is finalized and ready to sign, when verifying entity names, exhibits, and signature blocks before sending, or when setting up an envelope with sequential or parallel signers.
anthropics/knowledge-work-plugins
brief
Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.
anthropics/knowledge-work-plugins
legal-risk-assessment
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.
anthropics/knowledge-work-plugins
triage-nda
Rapidly triage an incoming NDA and classify it as GREEN (standard approval), YELLOW (counsel review), or RED (full legal review). Use when a new NDA arrives from sales or business development, when screening for embedded non-solicits, non-competes, or missing carveouts, or when deciding whether an NDA can be signed under standard delegation.
anthropics/knowledge-work-plugins
compliance-check
Run a compliance check on a proposed action, product feature, or business initiative, surfacing applicable regulations, required approvals, and risk areas. Use when launching a feature that touches personal data, when marketing or product proposes something with regulatory implications, or when you need to know which approvals and jurisdictional requirements apply before proceeding.
Didn't find tool you were looking for?