Revenue Operations
Pipeline coverage, forecast accuracy, and revenue analytics.
$skillfish add ~skills/revenue-operations Real Conversations
See how the Revenue Operations skill responds to actual requests. These are representative examples of what your AI agent will produce.
Our pipeline coverage ratio dropped from 3.8x to 2.4x in 6 weeks. We're trying to hit $4.5M ARR by Q4. The sales team says they're working hard but something is clearly broken. How do I figure out what's actually happening?
A 37% drop in pipeline coverage in 6 weeks is a systemic signal — not a hard work problem. Here's how to diagnose it.
Pipeline Coverage Decomposition:
Coverage = (Total qualified pipeline value) / (Revenue target)
It can drop because:
- New pipeline generation slowed — top-of-funnel problem (marketing, SDR, or outbound)
- Existing pipeline stalled — deal velocity slowed (longer cycles, more objections)
- Pipeline was cleaned — someone disqualified deals that were previously inflated
- Target went up — denominator increased without pipeline keeping pace
Diagnostic Queries to Run in Your CRM (today):
| Question | What It Reveals |
|---|---|
| New opps created last 4 weeks vs. same period last quarter | Top-of-funnel trend |
| Average days in each stage — is one stage slower? | Where deals are stalling |
| Deals moved to closed-lost in last 6 weeks — any pattern? | Win rate shift |
| Who created the most pipeline 6 weeks ago vs. today? | Rep-level vs. systematic issue |
Most Common Root Causes:
- A top SDR/AE left or changed role (check headcount changes 8-10 weeks ago)
- Marketing campaign ended or channel dried up
- One or two large deals that were inflating coverage closed or fell out
- ICP change or price increase hit conversion rates
Forecast Implication: At 2.4x coverage with a 25-30% win rate, you're looking at a potential ARR shortfall of $300-500K. Do you want to model the scenarios?
What does the stage-by-stage breakdown look like — where is pipeline accumulating?
Get Started
How to install and use this skill in your preferred environment.
Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.
Models & Context
Which AI models and context windows work best with this skill.
Recommended Models
Larger models produce more detailed, production-ready outputs.
Context Window
This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.
All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.
Pro tips for best results
Be specific
Include numbers — users, budget, RPS — so the skill can size the architecture.
Share constraints
Compliance needs, team size, and existing stack all improve the output.
Iterate
Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.
Combine skills
Pair with companion skills below for end-to-end coverage.
Good to Know
Advanced guide and reference material for Revenue Operations. Background, edge cases, and patterns worth understanding.
Contents
Pipeline Health Metrics
Coverage ratio: Total qualified pipeline value ÷ revenue target for the period. A 3x ratio is the standard baseline; early-stage companies with less forecast visibility should target 4–5x. Below 2.5x with less than 90 days to close is a red flag requiring immediate top-of-funnel action.
Stage conversion rates: Track conversion at each stage (e.g., Discovery → Demo → Evaluation → Commit). A sudden drop at one stage usually points to a specific problem: demo quality, pricing objection, or competitive loss pattern.
Pipeline velocity formula:
Velocity = (# Qualified Deals × Win Rate × Average ACV) ÷ Average Sales Cycle (days)
This tells you how many dollars of ARR flow through your pipeline per day. Use it to model the impact of improving any single variable — a 10% improvement in win rate is often worth more than doubling deal volume.
RevOps Stack Decision Matrix
| Category | Options | Key Differentiator | Choose When |
|---|---|---|---|
| CRM | Salesforce | Customization, enterprise integration depth, AppExchange | >50 reps or complex sales process |
| CRM | HubSpot | Faster setup, built-in marketing, lower admin overhead | <50 reps, marketing and sales under one roof |
| Sequencing | Outreach | Advanced analytics, enterprise workflow control | Large SDR team, complex sequences |
| Sequencing | Salesloft | Better UX, Rhythm AI prioritization | Mid-market, AE-driven outreach |
| Enrichment | Apollo | Prospecting + enrichment in one tool, lower cost | Budget-constrained, SMB ICP |
| Enrichment | Clay | Waterfall enrichment, custom workflows via Claygent | High-volume outbound, technical RevOps team |
| Enrichment | ZoomInfo | Data breadth and accuracy at enterprise scale | Enterprise ABM, intent data needed |
| BI | Looker | LookML modeling layer, governed metrics | Data team exists, complex data warehouse |
| BI | Tableau | Powerful visualization, broad adoption | Analyst-heavy org, existing Salesforce stack |
| BI | Metabase | Fast setup, SQL-friendly, low cost | Startup, data-literate ops team |
Forecast Methodology Comparison
| Method | How It Works | Best For | Accuracy Risk |
|---|---|---|---|
| Commit / Best Case / Pipeline | Reps manually categorize deals by confidence tier | Early-stage, small sales teams | Rep optimism bias; "best case" becomes "commit" over time |
| Weighted Pipeline | Multiply deal value by stage-based probability | Mid-market, established stage probabilities | Stage weights go stale; doesn't account for deal age |
| AI-based (Clari, Gong) | Historical patterns + rep behavior signals | Scale-stage, enough historical data | Requires 12+ months of clean CRM data to be reliable |
Most companies should use weighted pipeline as their baseline and overlay commit tiers for board-level communication. AI forecasting earns its cost at Series B+ when data volume makes the signal meaningful.
Common Salesforce Automation Recipes
Lead routing by territory/account size: Use assignment rules or a tool like LeanData or Chili Piper. Route by account firmographics (employee count, revenue) pulled from enrichment. Always define a "catch-all" rule so no lead goes unassigned.
Opportunity stage-change triggers: When a deal moves to Evaluation, auto-create a task for the AE to schedule a technical validation call and notify the SE. When a deal moves to Commit, trigger an auto-notification to the VP of Sales and update the forecast roll-up.
Stale deal alerts: A Process Builder or Flow that fires when Last Activity Date on an Opportunity is >14 days and Stage is not Closed. Creates a follow-up task and optionally flags in a Slack channel. Critical for catching deals that silently die.
Renewal opportunity creation: When a subscription record hits 90 days before Contract End Date, auto-create a linked Renewal Opportunity with ACV = current contract value and set Owner = CSM. Prevents renewals from falling through the cracks.
Attribution Model Trade-offs
| Model | Logic | Misleads You When |
|---|---|---|
| First-touch | 100% credit to the first touchpoint | Sales cycle is long; first touch happened 18 months ago on a cold email |
| Last-touch | 100% credit to the touchpoint before conversion | Ignores all awareness and nurture activity; over-credits BDR cold outbound |
| Linear | Equal credit across all touchpoints | Treats a webinar view the same as a product demo request |
| Time-decay | More credit to recent touchpoints | Penalizes top-of-funnel programs that run long before conversion |
| Data-driven | ML assigns credit based on observed patterns | Requires high deal volume (500+ conversions) to produce reliable weights |
For most B2B companies at <$20M ARR, multi-touch linear is the most defensible starting point. The goal is directional insight, not accounting precision.
Ready to try Revenue Operations?
Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.
$skillfish add ~skills/revenue-operations