Pipeline review Claude skill

Use this weekly or before a forecast call. It turns a pipeline export into an honest forecast and a short list of actions that move the number.

Inputs

• Pipeline export: deal, owner, stage, amount, close date, created date, last activity, next step, contacts.
• Quota or target for the period and what has closed so far.
• Historical stage conversion rates if available.

The play

1. Check coverage

Open pipeline due this period ÷ remaining target. Healthy coverage depends on win rate; at a 25% win rate, 3-4x is typical. Read references/pipeline-health.md for the health checks, thresholds and the risk scoring table.

2. Run the health checks

• Aging: deals in a stage longer than 1.5x the average for that stage.
• Slips: close date moved 2+ times.
• No next step: no future activity scheduled.
• Stale: no activity in 14+ days.
• Single-threaded: one contact engaged.
• Close date in the past.
• Stage mismatch: proposal stage without an economic buyer met.

3. Score deal risk

Each failing check adds risk points. High-risk deals in commit move to best case or out, with the reason.

4. Build the forecast

Weighted forecast = commit + (best case × historical conversion).

5. Choose the actions

Three to five actions that change the quarter: a deal that needs an executive call, a stalled proposal, a missing champion, pipeline generation if coverage is short.

Output format

Target: X | Closed: X | Gap: X | Coverage: Nx (healthy / thin)
Forecast: Commit X | Best case X | Upside X | Weighted X
Risks: <deal - risk score - failing checks - recommendation>
Actions this week: <action - owner - expected impact>
Pipeline hygiene: N deals with past close dates, N without next steps

What good looks like

• Every deal moved out of commit has a stated reason.
• The forecast says what would need to be true for best case to land.
• Actions are specific, owned and dated.
• The common mistake is reviewing deals by amount only; a small deal with a signed order form matters more for the forecast than a big deal with no economic buyer.

Rules

• MUST base risk on evidence (activity, dates, contacts), not on rep confidence.
• MUST flag past-due close dates and missing next steps.
• NEVER change records in the CRM without approval; propose updates instead.

Example prompts

• "Here’s our pipeline export. Prep me for Monday’s forecast call."
• "Which of my 30 open deals are most at risk this quarter?"
• "We need $400k more this quarter. Is the pipeline enough, and what should we do?"

Coverage targets by win rate

Coverage counts only deals with close dates inside the period and stages past discovery.

Risk scoring

Risk: 0-2 low, 3-5 medium, 6+ high.

Stage conversion sanity check

If the team’s commit category historically closes below 80%, the commit rules are too loose.

Weekly review flow (30 minutes)

1. Numbers: target, closed, gap, coverage (5 min).
2. Commit deals: confirm each with evidence (10 min).
3. Best-case deals: what moves them to commit (10 min).
4. Hygiene and pipeline creation: past dates, missing next steps, new pipeline needed (5 min).