Agent Skills
› anthropics/knowledge-work-plugins
› forecast
forecast
GitHub根据CRM数据或手动输入，生成加权销售预测，包含最佳/可能/最差情景、承诺与增量拆解及缺口分析。适用于季度预测会议、管线覆盖率检查及Deal优先级决策。
Trigger Scenarios
准备季度销售预测会议
评估管线对目标的缺口
决定哪些交易确认为承诺额
检查管线覆盖率
Install
npx skills add anthropics/knowledge-work-plugins --skill forecast -g -y
SKILL.md
Frontmatter
{
"name": "forecast",
"description": "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.",
"argument-hint": "<period>"
}
/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.
Version History
- 6f13415 Current 2026-07-05 18:34
