Pipeline read you can trust
Assess every account against defined criteria rather than optimistic self-reporting.
— Sales & Growth
Deal win-likelihood scorer
Upload one CRM export with a row per opportunity and a column recording the result (e.g. 'Outcome' = Won/Lost, blank for open deals).
- Sales & Growth
- Traceable reasoning
- Runs anywhere
1–2 weeks → ~15 minutes
For a full population, not a sample
No coding required
- Input
- CRM exports, deal notes or call records
- Output
- A scored view of each account with reasons shown
- Runs in
- Skillsize · ChatGPT · Claude · Copilot
- Export
- SKILL.md · MCP
- Time saved
- ~1–2 weeks per run
— USE CASES
What people use Deal win-likelihood scorer for
Patterns across the whole book
See what repeats across the pipeline in scope instead of the loudest recent deal.
Action, not just insight
Each finding lands with a recommended next move and the evidence behind it.
What it works from
- CRM exports, deal notes or call records
- Your qualification criteria, ICP or scoring rules
What you get back
- A scored view of each account with reasons shown
- A prioritised action list for the team
— HOW IT BEHAVES
How Deal win-likelihood scorer produces its result
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Every row of the pipeline in scope
Each row of your export is processed on the same basis, so no account is skipped however long the table is.
Composed as work product
Findings on the pipeline in scope are written up as a document that reads like professional output, with each claim tied back to a account.
Roll-up alongside account-level detail
Detail rows are summarised into the grouped view of the pipeline in scope without losing the underlying accounts.
Why this is expensive by hand
Reading the pipeline in scope usually depends on what reps put in the CRM and what a leader remembers from calls. In practice it shows up as pipeline read you can trust: assess every account against defined criteria rather than optimistic self-reporting. The value sits in the rigour, not the typing — yet the rigour is exactly what gets traded away when there is only 1–2 weeks of capacity for it.
How this Skill produces it
Skillsize turns that work into a Skill: you supply the material, and what comes back is a scored view of each account with reasons shown, with a prioritised action list for the team. The judgement is built in — how items are broken up, what standard they are held to, and where the run stops for a human review. In effect, 1–2 weeks of senior time compresses into ~15 minutes — and the output is comparable across clients, quarters and colleagues instead of shaped by whoever ran it.
Who it's for
- Revenue and commercial leaders
- Sales operations and enablement teams
- Customer success and account management leads
- Consultants advising on go-to-market
Run it in Skillsize — or export it anywhere
Deal win-likelihood scorer exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
ChatGPTClaudeCopilotAI Products (MCP)
More Sales & Growth Skills
Browse the full library →Sales & Growth
Upsell propensity map
Upload a purchase-history export with a row per account and a column recording whether they expanded (e.g. 'Expanded' = Yes/No).
Sales & Growth
Campaign response predictor
Upload a campaign export with a row per contact, lead or send, and a column recording the result (e.g. 'Converted' = Yes/No).
Sales & Growth
Customer churn & renewal risk
Upload one account export with a row per customer and a column recording what happened at renewal (e.g. 'Renewal outcome' = Renewed/Churned, blank for accounts not yet up).