Review your Salesforce pipeline by stage and forecast category every week

SKILL.md---
name: salesforce-pipeline-report
description: "Monday mornings: open Salesforce pipeline by stage and forecast category, the deals that moved or slipped last week, and the change in total. Use when the user asks for this, or when it runs on a schedule."
---

# Salesforce weekly pipeline report

Monday mornings: open Salesforce pipeline by stage and forecast category, the deals that moved or slipped last week, and the change in total.

A saved Salesforce pipeline report shows where things stand. The Monday question is different: what changed since last week, and which of those changes should worry anyone. This skill reads open opportunities grouped by stage and forecast category, then reads `OpportunityHistory` for the last seven days to find the deals that advanced, slipped a close date or dropped out of Commit.

It is written for sales managers who run a weekly pipeline call and would rather spend it on the deals than on rebuilding the stage by forecast category matrix in a spreadsheet.

## Two ways to get the data

Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used.

## Route A: API or MCP server

### What you need

- A Salesforce user who can see the whole team's opportunities and their OpportunityHistory.
- SOQL access: the `sf` CLI logged in once with `sf org login web`, a Salesforce connector, or an access token and instance URL in `SF_ACCESS_TOKEN` and `SF_INSTANCE_URL`.

If something is missing, say what and stop; do not invent numbers.

### Steps

1. **Total open pipeline** (Salesforce): Run `SELECT StageName, ForecastCategoryName, COUNT(Id) n, SUM(Amount) total FROM Opportunity WHERE IsClosed = false AND CloseDate = THIS_FISCAL_QUARTER GROUP BY StageName, ForecastCategoryName` with `sf data query --query "..." --json` or the REST `query` resource. Drop the `CloseDate` filter if the team reviews all open pipeline, not just this quarter.
2. **Read last week's changes** (Salesforce): `SELECT OpportunityId, Opportunity.Name, Opportunity.Owner.Name, StageName, ForecastCategory, Amount, CloseDate, CreatedDate FROM OpportunityHistory WHERE CreatedDate = LAST_N_DAYS:7 ORDER BY OpportunityId, CreatedDate`. Each row is the opportunity as it stood after a change; compare it with the row before (query older history for that opportunity when the window holds only one).
3. **Sort the movement**: Classify each change: stage forward or back (by `SortOrder` from `OpportunityStage`), forecast category into or out of Commit, close date pushed past the quarter end (a slip), amount changed by more than 10%, or Closed Lost.
4. **Write the report**: Total open pipeline and its change since last Monday, the stage by forecast category table with totals, up to 8 movers with owner and amount, and the slipped deals last.

## Route B: the browser

### What you need

- Signed in to Salesforce as a user with the Run Reports permission and visibility of the whole team's opportunities, such as a manager above them in the role hierarchy.

If something is missing, say what and stop; do not invent numbers.

### Steps

Start at https://login.salesforce.com/. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.

1. **Sign in to your org**: Salesforce has no shared report URL: after sign-in you land on your own My Domain (`https://<company>.lightning.force.com`). Open the **Reports** tab from the App Launcher.
2. **Build the stage by forecast category matrix**: Click **New Report**, report type **Opportunities**. Filters: **Show Me** All opportunities, **Close Date** **Current FQ**, **Opportunity Status** Open. Group rows by **Stage** and columns by **Forecast Category**, add **Amount** with **Sum**, then **Run**. The subtotals are the table; the grand total is open pipeline. Save it so next Monday is one click.
3. **Read last week's changes**: A second report with the **Opportunity History** report type, filtered on **Last Modified Date** **Last 7 days**, shows one row per change with **From Stage**, **To Stage**, Amount, Close Date and Forecast Category. Add Opportunity Owner and sort by Opportunity Name.
4. **Sort the movement**: Classify each row as a stage move forward or back (by the order of your sales process), Commit in or out, a close date pushed past quarter end (a slip), an amount change over 10%, or Closed Lost. Compare the total with the number you saved last Monday.
5. **Write the report**: Open pipeline and its change, the matrix with totals, up to 8 movers with owner and amount, the slipped deals last, and the two deals to raise first.

Note: Report previews show up to 2,000 rows; with more history rows, use **Export** with Details Only as CSV. The Opportunity History report type records stage, amount, probability, forecast category and close date changes, the same source as the API route. If the Opportunity Status filter is missing, add Closed equals False instead.

## The report

- **Open pipeline** for the quarter and the change since last Monday.
- **Stage by forecast category**: the amount in each cell, with row and column totals.
- **Movers**: stage moves, forecast category changes and Closed Lost deals, with owner and amount.
- **Slipped**: deals whose close date moved out of the quarter.
- The two deals to discuss first on the call.

## Post it to Briefkin

When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on.

```bash
[ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env
curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \
  -H "authorization: Bearer $BRIEFKIN_TOKEN" \
  -H "content-type: application/json" \
  -d @- <<'JSON'
{
  "v": 1,
  "event_id": "salesforce-pipeline-report/<date of this run, e.g. 2026-10-16>",
  "item_key": "salesforce-pipeline-report",
  "project": "Acme",
  "source": "Salesforce weekly pipeline report skill",
  "kind": "metric",
  "title": "Open pipeline $2.41M, down 3% on last week",
  "metric": {
    "label": "Open pipeline",
    "value": 2410000,
    "prefix": "$",
    "better": "higher",
    "period_start": "<start of the period, ISO 8601>",
    "period_end": "<end of the period, ISO 8601>"
  },
  "glance": {
    "type": "Grid",
    "props": {
      "columns": 3
    },
    "children": [
      {
        "type": "Stat",
        "props": {
          "label": "Commit",
          "value": "$740k",
          "tone": "ok"
        }
      },
      {
        "type": "Stat",
        "props": {
          "label": "Best case",
          "value": "$610k"
        }
      },
      {
        "type": "Stat",
        "props": {
          "label": "Pipeline",
          "value": "$1.06M"
        }
      }
    ]
  },
  "widget": [
    {
      "type": "Table",
      "props": {
        "columns": [
          "Stage",
          "Pipeline",
          "Best case",
          "Commit",
          "Total"
        ],
        "align": [
          "left",
          "right",
          "right",
          "right",
          "right"
        ],
        "rows": [
          [
            "Qualification",
            "$420k",
            "$0",
            "$0",
            "$420k"
          ],
          [
            "Needs Analysis",
            "$380k",
            "$90k",
            "$0",
            "$470k"
          ],
          [
            "Proposal/Price Quote",
            "$260k",
            "$330k",
            "$120k",
            "$710k"
          ],
          [
            "Negotiation/Review",
            "$0",
            "$190k",
            "$620k",
            "$810k"
          ],
          [
            "Total",
            "$1.06M",
            "$610k",
            "$740k",
            "$2.41M"
          ]
        ]
      }
    },
    {
      "type": "Table",
      "props": {
        "columns": [
          "Opportunity",
          "Owner",
          "Amount",
          "What changed"
        ],
        "align": [
          "left",
          "left",
          "right",
          "left"
        ],
        "rows": [
          [
            "Contoso EMEA rollout",
            "Lena",
            "$180k",
            "Proposal → Negotiation, now Commit"
          ],
          [
            "Northwind analytics add-on",
            "Priya",
            "$64k",
            "Needs Analysis → Proposal"
          ],
          [
            "Adatum platform",
            "Sam",
            "$120k",
            "Commit → Best case"
          ],
          [
            "Litware seats",
            "Theo",
            "$48k",
            "Closed Lost: budget frozen"
          ],
          [
            "Fabrikam renewal",
            "Marco",
            "$95k",
            "Close date Nov 28 → Jan 15 (slipped)"
          ]
        ]
      }
    },
    {
      "type": "Callout",
      "props": {
        "text": "$95k slipped out of the quarter: Fabrikam moved its close date to January.",
        "tone": "warn"
      }
    }
  ],
  "size": "md"
}
JSON
```

Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.

Set `period_start` and `period_end` to the window the number covers: the tile names it from them ("Last 7 days", "Today", "This month"). For a count right now (open items, a balance), send `"period_label": ""` so no period shows; for another name, send it as `period_label` (at most 24 characters).

## Run it on a schedule

Suggested: Mondays at 7:30 (`30 7 * * 1`). From cron, with the agent signed in on that machine:

```bash
30 7 * * 1 claude -p "Run the salesforce-pipeline-report skill"
# Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run
```

Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/salesforce-pipeline-report#schedule

Source: https://briefkin.dev/skills/salesforce-pipeline-report