1---2name: pipeline-report3description: >-4 Reports a B2B SaaS company's pipeline per channel by opportunity and buying group, not by lead, from a CRM export:5 opportunities, pipeline, win rate, days to close, contacts and roles per deal, cost per opportunity and pipeline6 against target, with new business and expansion kept apart. Flags where the data can't be trusted (missing source,7 duplicates, stage skips, date errors) and fails the report when those gaps could change which channel comes out on8 top. Use it for a monthly or quarterly channel review, before moving budget between channels, or before a board9 update. Not for checking tracking (use tracking-audit) or for scoring leads (use lead-scoring).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Reads a connected CRM read-only if the13 agent has one, otherwise CSV exports or pasted rows. Python 3 is optional, for the report and the trust checks.14metadata:15 author: SHAKEUP16 version: "1.0.0"17 stage: check18 plugin: markops19 homepage: https://www.shakeuphq.com/skills/pipeline-report20---21 22# Pipeline report23 24Shows which channels create pipeline, counted the way deals are bought, and says how far the figures can be trusted.25 26## Purpose27 28- One job: one pipeline report per channel for one period, with a trust check on the data behind it.29- Stage: check. It ends in a verdict on whether the report can carry a budget decision.30- Unit: the opportunity. It never counts leads as pipeline, never adds new business and expansion together, and never adds self-reported and software channels together.31- It never invents a win rate, deal size, cycle or benchmark. Every figure comes from the export or the profile, and a missing one is `not available`.32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| Monthly or quarterly channel review | this skill |38| Before moving budget between channels | this skill, after `tracking-audit` |39| A board or CFO asks for pipeline by channel | this skill |40| Platform figures and CRM figures disagree | `tracking-audit` |41| UTMs land in the wrong channel | `utm-check` |42| Deciding which leads sales calls first | `lead-scoring` |43 44## Inputs45 46| Input | Required | Ways to provide, in order | If missing |47| --- | --- | --- | --- |48| Opportunities: id, name, account, created date, close date, amount, stage, source, type; the period plus 2 earlier quarters | yes | a connected CRM, read-only; a CSV export; pasted rows | `BLOCKED`: ask for the export |49| Contacts linked to each opportunity: opportunity id, created date, source, role or title | no | the same CRM; a contacts export with the deal association | channel from the opportunity's source; buying group `not available` |50| Stage date fields on opportunities | no | the same export | stage skip check `not checked` |51| Spend per channel for the period | no | ad platform exports; `## Channels` monthly budgets | cost per opportunity `not available` |52| `self-reported-attribution` handoff | no | its handoff block; a self-reported column in the export | self-reported column `not available` |53| `utm-check` handoff | no | its handoff block | channels named as the CRM writes them |54| `tracking-audit` handoff | no | its handoff block | platform-sourced figures shown without a tracking grade |55 56## Profile read57 58From `company-profile.md`: `## Targets` (Pipeline target, Opportunity to closed-won rate, as targets to compare against, never to replace measured rates), `## Company` (Average deal size, Sales cycle, as stated values to compare with the measured ones), `## Buyers` (the buying group roles, to map titles to roles), `## Channels` (channel names and budgets), `## Accounts and data` (CRM), and every `## Learnings` entry for `pipeline-report`.59 60No profile: ask for the pipeline target for the period and the buying group roles, in one message; continue without them if the reader doesn't know. Say that `company-profile` saves this next time.61 62## Steps63 641. **Apply learnings.** A channel mapping or rule the reader accepted overrides the defaults. Name each one used.65 662. **Set the period.** Default: the last full quarter, counted by opportunity created date (pipeline created). Keep 2 earlier quarters in the export for the cycle and the comparison.67 683. **Give each opportunity 1 channel** (rule in `references/stage-model.md`): the earliest contact in its buying group created on or before the opportunity, else the opportunity's own source. Group source values with the `utm-check` scheme when its handoff exists, so the CRM and GA4 name channels alike.69 704. **Run the report and the trust checks.**71 72 ```73 python3 scripts/pipeline_report.py --opps opps.csv --contacts contacts.csv --start 2026-07-01 --end 2026-09-30 \74 --stage-cols "discovery_date,proposal_date" --target 1800000 --spend spend.csv75 ```76 77 Without Python, by hand: drop opportunities whose close date is before their created date (count them); list later copies of the same account with the same amount within 30 days, or the same name and account, and leave them out of totals; put missing sources (blank, unknown, not set, none, other, offline, import) in `unknown`; then per channel, sum opportunities and amounts, count won, lost and open, and take the median days from created to closed-won. Say which way you ran it.78 795. **Run the trust checks.**80 81 | Check | Fires when | Severity | Why |82 | --- | --- | --- | --- |83 | `headline_unsafe` | The `unknown` pipeline is at least the gap between the top 2 channels | critical | The unknown pipeline could belong to the runner-up, so the top channel isn't known |84 | `ranking_changed` | Removing duplicates changes the order of the top 5 channels | critical | The ranking depends on records counted twice |85 | `missing_source` | Any opportunity in `unknown` | warning | Shown as its own row, never spread across channels |86 | `duplicate` | Same account and amount within 30 days, or same name and account | warning | A re-entered deal is far more common than 2 equal deals in a month; the list is for review |87 | `date_error` | Close date before created date | warning | Left out of every figure |88 | `stage_skip` | A won opportunity has a later stage date with an earlier one missing | warning | Stage conversion for that channel is `not available` |89 | `zero_amount` | No amount | warning | Counted as an opportunity, adds nothing to pipeline |90 | `no_contacts` | No linked contact | warning | Buying group unknown for that deal |91 | `low_information` | Source is direct | warning | Kept as a channel; usually a missing tag, not a channel |92 | `win_rate_immature` | A channel has more open than closed opportunities | warning | Its win rate will move as deals close; shown, labelled |93 946. **Read the buying group.** Map each contact's role or title to the roles in `## Buyers`, `### Buying group` (match on the role's words; unmatched is `other`). Per channel: median contacts per opportunity and the share with 2 or more roles. Overall: win rate with 2 or more roles against 1 role or none, with the closed counts. Under 10 closed deals in either group, write the rate and say it is too few to compare.95 967. **Compare with the target and the timing** (`references/stage-model.md`): pipeline created against `Pipeline target`; opportunities needed at the measured median amount; and when this period's pipeline should close, from the measured median days to close. Where the profile's stated cycle or deal size differs from the measured one by a quarter or more, show both.97 988. **Grade each channel.**99 100 | Grade | Condition (first match wins) |101 | --- | --- |102 | `do not use` | Its rank could flip with the `unknown` pipeline, or half or more of its opportunities carry a flag |103 | `caution` | Any flag touches it, or its win rate is immature |104 | `trusted` | No flag touches it |105 1069. **Write the read.** 3 to 5 lines, each with its figure, its source and the channel's grade. Never recommend cutting or growing a channel graded `do not use`, and never when `headline_unsafe` fired.107 108## Check and verdict109 110| Verdict | Condition (first match wins) |111| --- | --- |112| `BLOCKED` | No opportunities in the period |113| `FAIL` | `headline_unsafe` or `ranking_changed` fired: the report can't carry a budget decision until the data is fixed |114| `PASS WITH NOTES` | Warnings only |115| `PASS` | No flags |116 117Named stop: `BLOCKED` asks for the opportunity export. No other stops: a FAIL still delivers the report, labelled, with the fix list.118 119## Learn120 121- The reader corrects a channel mapping ("Partner referral and Partner are one channel"): write a `fact`.122- The reader overrides a grade or a check: write a `proposal` with the reason.123- Each run's totals per channel (opportunities, pipeline, won): write a `fact` so the next run can show the trend.124 125Example: `- 2026-10-24 | pipeline-report | fact | Q3 new business: paid social 14 opps, 336,000; organic search 9 opps, 198,000; unknown 4 opps | Why: CRM export, 2026-10-01 | Status: noted`126 127## Output128 129```130Verdict: <PASS | PASS WITH NOTES | FAIL | BLOCKED> · Coverage: <complete | partial (what's missing)> · Report: <script | by hand>131Period: <dates> · Opportunities: <n> (<n> after duplicates, <n> date errors left out) · Channel rule: earliest contact <n>, opportunity source <n>132 133New business:134| Channel | Opps | Pipeline | Share | Won | Win rate (closed) | Median days to close | Contacts per opp | 2+ roles | Cost per opp | Self-reported | Grade |135(by pipeline; "unknown" as its own row)136 137Expansion: <same table, or "none in period">138Buying group: win rate with 2+ roles <r> (<n> closed) vs 1 role or none <r> (<n> closed)139Against target: <pipeline created> of <target> (<share>) · opportunities needed at the median amount: <n> · this period's pipeline closes around <date range>140Trust: <each fired check with its count and the records>141Read: <3 to 5 lines>142Learnings applied: <list, or none>143```144 145Then the handoff block.146 147## Hand off148 149```handoff150skill: pipeline-report151version: 1.0.0152verdict: PASS WITH NOTES153coverage: partial (no spend for organic channels)154for: <company> new business, 2026 Q3155outputs:156 pipeline_by_channel: {paid social: 336000, organic search: 198000, unknown: 72000}157 opportunities_by_channel: {paid social: 14, organic search: 9, unknown: 4}158 win_rate_measured: 0.24159 median_days_to_close: 71160 median_won_amount: 23000161 trusted_channels: [paid social]162next: [lead-scoring, lead-value-math]163open: [4 opportunities with no source]164```165 166`lead-scoring` reads the measured win rate and the won and lost deals. `lead-value-math` (paid media collection) reads `win_rate_measured`, `median_won_amount` and `median_days_to_close` instead of the profile's stated targets.167 168## Failure modes169 170| Problem | Do this |171| --- | --- |172| The export holds leads, not opportunities | Stop counting pipeline: ask for the opportunity export. Leads can't be pipeline |173| Amounts in several currencies | Report per currency, or convert only at a rate the reader gives, named |174| Most opportunities have no linked contacts | Use the opportunity source; buying group `not available`; recommend linking contacts at creation |175| A channel has 1 or 2 opportunities | Show the counts; no win rate comparison |176| The reader asks for "industry average" win rates | None in this skill; compare with their own earlier quarters |177| Sources are free text with many spellings | Group them with the `utm-check` scheme or ask the reader for the mapping; record it as a `fact` |178 179## Influenced by180 181- Winning by Design's bowtie model, the idea that the customer journey continues past the sale into expansion and renewal, measured with one data model on both sides: https://winningbydesign.com/press/winning-by-design-releases-updated-bowtie-model-and-benchmarks-to-provide-go-to-market-teams-with-a-standardized-customer-journey-and-data-model/182- SHAKEUP's pipeline target and pipeline timing calculators: the target worked back to opportunities from the company's own rates, and pipeline read 1 sales cycle ahead.