Sales Pipeline Review

Goal: Pull deal and meeting data from whatever CRM the user tracks their pipeline in, analyze it over a chosen period, and produce a report that answers the questions a founder, sales leader, or AE actually cares about.

Tool	Purpose	Required
Salesforce / HubSpot / Pipedrive / Close	Pull deal and pipeline data via API or CSV export	No (one required)
Supabase	Query deals or outreach tables directly	No (optional)
Google Sheets	Read pipeline data from a spreadsheet	No (optional)
Notion MCP	Query a Notion pipeline database	No (optional)

Trigger: Run on demand when the user asks for a pipeline review, deal review, 1:1 prep, board meeting prep, weekly sales review, or asks about meeting quality, conversion rates, or pipeline health. Also runs when an upstream workflow (Pipeline Ops, daily BDR rhythm) triggers an end-of-period review.

Setup

On first run, collect and store these preferences. Skip on subsequent runs. Data Source Config

Question	Options	Stored As
Where do you track your pipeline?	Salesforce / HubSpot / Pipedrive / Close / Supabase / Google Sheets / CSV / Notion / Other	`crm_tool`
How do we access it?	API / Export CSV / MCP tools / Direct query	`access_method`
What object represents a “deal” in your system?	Opportunity / Deal / Lead / Meeting / Custom	`deal_object`

Pipeline Stage Definitions

Question	Purpose	Stored As
What are your pipeline stages in order?	Map data to a standard funnel	`pipeline_stages`
Which stage means “qualified”?	Qualification rate calculation	`qualified_stage`
Which stage means “closed won”?	Win rate calculation	`won_stage`
Which stage means “closed lost”?	Loss analysis	`lost_stage`
What is your expected sales cycle length? (days)	Identify stuck deals	`expected_cycle_days`

Field Mapping Different CRMs use different field names. Map the user’s fields to standard analysis fields:

Standard Field	Purpose	Stored As	Examples
Deal name	Identification	`field_deal_name`	”Name”, “Deal Name”, “Opportunity Name”
Company	Account grouping	`field_company`	”Company”, “Account”, “Organization”
Stage	Funnel position	`field_stage`	”Stage”, “Pipeline Stage”, “Status”
Owner	Rep-level analysis	`field_owner`	”Owner”, “Assigned To”, “Rep”
Source	Channel attribution	`field_source`	”Lead Source”, “Source”, “Channel”
Created date	Period filtering	`field_created_date`	”Created Date”, “Created At”, “Date Added”
Close date	Velocity tracking	`field_close_date`	”Close Date”, “Expected Close”, “Closed At”
Amount	Revenue analysis	`field_amount`	”Amount”, “Deal Value”, “ARR”, “MRR”
Last activity date	Stale deal detection	`field_last_activity`	”Last Activity”, “Last Modified”, “Last Touched”
Loss reason	Loss analysis	`field_loss_reason`	”Loss Reason”, “Closed Lost Reason”

Minimum viable data: deal name + stage + created date. All other fields enrich but aren’t required. Benchmarks (Optional)

Question	Purpose	Stored As
Target meeting volume per week/month?	Compare actuals to goals	`target_meetings`
Target qualification rate?	Flag if below target	`target_qual_rate`
Target win rate?	Flag if below target	`target_win_rate`
Target pipeline value?	Revenue gap analysis	`target_pipeline_value`

Store config in: clients/<client-name>/config/pipeline-review.json or equivalent. Do not ask again in future runs.

Step 1: Pull Pipeline Data

Pull deal and meeting data from the configured CRM for the specified time period. Ask the user for the review period if not provided:

“What period should I analyze? Options: last 7 days, last 14 days, last 30 days, last 90 days, or a custom date range.”

Based on crm_tool and access_method, pull data as follows:

CRM	Access Method	How to Pull
Salesforce	API / CSV	SOQL query or user uploads CSV export
HubSpot	API / CSV	Deals API or user uploads CSV export
Pipedrive	API / CSV	Deals API or CSV export
Close	API / CSV	Leads/Opportunities API or CSV
Supabase	Direct query	Query deals/outreach_log tables
Google Sheets	Sheets API / CSV	Read sheet or user exports CSV
Notion	Notion MCP	Query database
CSV	File read	User provides file path

Pull two datasets:

Current period: All deals created or active within the specified date range
Comparison period: Same-length prior period (e.g., if reviewing last 2 weeks, also pull the 2 weeks before that)

Normalize all data into a standard structure regardless of source:

deals: [
  {
    id, name, company, stage, owner, source,
    created_date, close_date, last_activity_date,
    meeting_date, amount, qualification_status,
    loss_reason, days_in_current_stage, total_age_days
  }
]

Present a human checkpoint:

“Data Pulled Source: [CRM name] Current period: [start] to [end] — [N] deals Comparison period: [start] to [end] — [N] deals Fields available: [list] Fields missing: [list — analysis will adapt] Data looks correct? (Y/n)“

Step 2: Analyze Pipeline

Run all seven analyses on the current period data. Where comparison period exists, calculate period-over-period trends. Analysis 1 — Volume Metrics Calculate: total deals created, meetings booked, meetings held, no-show rate, weekly run rate, period-over-period change, vs. target_meetings. Analysis 2 — Qualification Breakdown Calculate: qualified deals, unqualified deals, pending qualification, qualification rate, top disqualification reasons, vs. prior period, vs. target_qual_rate. A deal is qualified if it reached or passed qualified_stage. A deal is unqualified if it was closed lost before reaching qualified_stage. Analysis 3 — Source Attribution Group by field_source: count deals, meetings, qualified deals, won deals. Calculate qualification rate and win rate per source. Flag if any single source drives more than 60% of pipeline. Analysis 4 — Stage Distribution and Velocity Group active deals by stage. Calculate deal count, revenue, weighted revenue, average days in stage, and stage-to-stage conversion rates. Use these stage probability defaults unless actual data is available:

Stage	Probability
Lead	5%
Meeting Booked	10%
Meeting Held	20%
Qualified	40%
Proposal Sent	60%
Negotiation	80%
Closed Won	100%
Closed Lost	0%

Analysis 5 — Stuck Deals and At-Risk Pipeline A deal is “stuck” if days_in_current_stage exceeds 2× the average for that stage, or exceeds expected_cycle_days total. Default stuck thresholds (use if stage-average data is insufficient):

Stage	Expected Max Days
Lead	3
Meeting Booked	7
Meeting Held	5
Qualified	10
Proposal Sent	14
Negotiation	14

Also flag: deals with no activity for more than 14 days; deals where total_age_days > 1.5× expected_cycle_days; any single deal > 30% of total pipeline value. Analysis 6 — Win/Loss Analysis Calculate: win rate overall, win rate by source, win rate by owner, average deal size (won), average days to close, top loss reasons, loss stage distribution. Analysis 7 — Forecast and Coverage Only run if target_pipeline_value or revenue targets are configured. Calculate: pipeline coverage ratio (weighted pipeline / remaining quota), commit forecast (Negotiation + Proposal stage deals), best case forecast (commit + Qualified deals × historical win rate), gap to target, required deals and meetings to close the gap. Coverage assessment:

Coverage	Assessment
3x+	Healthy
2–3x	Adequate
<2x	At risk
<1x	Critical

Step 3: Generate Report

Generate two formats from the analysis output. Executive Summary — one page, numbers and trends, what a founder reads in 60 seconds:

# Pipeline Review — [Period Type]: [Start Date] to [End Date]

## Snapshot

| Metric             | This Period | Prior Period | Change   |
| Meetings booked    | [N]         | [N]          | [+/-Z%]  |
| Meetings held      | [N]         | [N]          | [+/-Z%]  |
| Qualification rate | [X%]        | [Y%]         | [+/-Z pts] |
| Win rate           | [X%]        | [Y%]         | [+/-Z pts] |
| Pipeline value     | $[X]        | $[Y]         | [+/-Z%]  |
| Avg deal size      | $[X]        | $[Y]         | [+/-Z%]  |
| Avg days to close  | [X]         | [Y]          | [+/-Z]   |

## Red Flags
- [Metric trending down significantly]
- [Stuck deals above threshold]
- [Pipeline coverage below 2x]
- [Single source >60% of pipeline]
- [No-show rate above 20%]

## Green Lights
- [Metrics trending up]
- [Sources performing well]
- [Stages moving faster than expected]

## Top 3 Actions
1. [Most impactful action this week]
2. [Second most impactful]
3. [Third most impactful]

Detailed Diagnostic — full data tables, stage-by-stage breakdown, source analysis, stuck deal list, and specific recommendations. Sections: Volume, Qualification, Source Effectiveness, Stage Distribution and Velocity, Stuck Deals, Win/Loss Analysis, Forecast and Coverage (if targets set), Recommendations. Each recommendation must cite the specific data point that drives it. Apply this logic:

Pattern	Recommendation
Qualification rate <40%	Tighten ICP targeting — top DQ reason is [X]
No-show rate >20%	Implement confirmation reminders 24h and 1h before meetings
One source >60% of pipeline	Diversify — if this channel underperforms, pipeline collapses
High-quality source with low volume	Scale it — [source] has [X]% qual rate but only [Y]% of volume
Deals stuck in a specific stage	Unblock [stage] — [N] deals averaging [Y] days (2× normal)
Win rate declining	Win rate dropped from [X]% to [Y]% — top loss reason is now [Z]
Pipeline coverage <2x	Need [Z] more qualified deals — requires [W] meetings at current rates
Cycle lengthening	Bottleneck at [stage] — deals [X] days slower vs prior period

Present the executive summary first, then offer the detailed diagnostic:

“[Executive Summary rendered]
Full detailed diagnostic is also available. Actions from this review:

[High priority recommendation]

[High priority recommendation]

[Medium priority recommendation]

Stuck deals requiring immediate attention:
Deal Company Stage Days Stuck Action
Want to see the full diagnostic? Or take action on any of these recommendations?”

Save or share the report based on user preference:

Destination	How
Markdown file	Save to `clients/<client>/reports/pipeline-review-[date].md`
Google Sheets	Export data tables (metrics, deal list, source breakdown)
Notion	Push to a Notion database page via Notion MCP
Slack	Send executive summary to a specified channel
Email	Send via agentmail
Display only	Render inline (default)

Output Format

Pipeline Review — [Period Type]: [Start] to [End] Snapshot

Metric	This Period	Prior Period	Change
Meetings booked	[N]	[N]	[+/-Z%]
Meetings held	[N]	[N]	[+/-Z%]
Qualification rate	[X%]	[Y%]	[+/-Z pts]
Win rate	[X%]	[Y%]	[+/-Z pts]
Pipeline value	$[X]	$[Y]	[+/-Z%]
Avg deal size	$[X]	$[Y]	[+/-Z%]
Avg days to close	[X]	[Y]	[+/-Z]

Red Flags: [List or “None”] Green Lights: [List or “None”] Top 3 Actions:

[Action]
[Action]
[Action]

Stuck Deals

Deal	Company	Stage	Days Stuck	Owner	Action

Edge Cases

Missing amount field: Skip revenue metrics, weighted pipeline, and forecast. Volume and stage analysis still run.
Missing source field: Skip source attribution (Analysis 3). All other analyses still run.
Missing loss reason field: Skip loss reason breakdown. Win/loss rate still calculates.
Missing last activity date: Skip no-activity deal detection. Stuck deals are still detected via stage duration.
No comparison period data: Run single-period analysis only. Omit all period-over-period trend columns.
No targets configured: Skip forecast and coverage analysis (Analysis 7). Note in output that targets are not set.
Loss reasons mostly blank or “Other”: Flag data hygiene issue in recommendations. Note that loss analysis is unreliable until reps fill in reasons consistently.
CRM not connected or CSV not provided: Ask the user to either connect the CRM via MCP or upload a CSV export before proceeding.

Overview

Skill Library

Setup

Step 1: Pull Pipeline Data

Step 2: Analyze Pipeline

Step 3: Generate Report

Output Format

Edge Cases

Overview

Skill Library

Documentation Index

​Setup

​Step 1: Pull Pipeline Data

​Step 2: Analyze Pipeline

​Step 3: Generate Report

​Step 4: Export and Share

​Output Format

​Edge Cases

Setup

Step 1: Pull Pipeline Data

Step 2: Analyze Pipeline

Step 3: Generate Report

Step 4: Export and Share

Output Format

Edge Cases