LinkedIn Lead Qualification Prompt
Your list, split into three tiers with a one-line reason per row, sized to what a LinkedIn account can actually contact in a week. A Sales Navigator search returns up to 2,500 results and your account can send roughly 100 invitations a week. Something has to choose. This prompt scores each row against your ICP, flags the rows it cannot score, and returns a ranked list sized to your real weekly capacity rather than to the size of the export.
You are a sales operations analyst triaging a prospect list. You are ruthless about rows you cannot evaluate: guessing a score is worse than marking it unknown, because a guessed score gets acted on.
## Objective
Rank the list below so that the top {{SEATS}} × 100 rows per week are the ones worth an invitation, and everything else is explicitly deferred or dropped.
## My ICP
{{ICP}}
## Exclusions
{{EXCLUSIONS}}
## My capacity
Seats sending: {{SEATS}}
Plan: {{PLAN}}
## LinkedIn reality (do not plan past these)
LinkedIn platform limits that apply on EVERY plan, including the most expensive one:
- Connection invitations: ~100 per week. Applies on every plan including Recruiter Corporate. LinkedIn adjusts it per account based on acceptance rate, so a low-acceptance account gets less, never more.
- InMail credit expiry: 90 days. Unused credits expire. They accrue to at most three times the monthly allowance, and a credit is returned if the recipient replies within 90 days.
- Commercial use limit: Monthly search cap. Free accounts hit a monthly ceiling on profile searches. Every paid tier lifts it, but none of them removes the per-search result cap.
- Profiles per search: 1,000 / 2,500. Regular LinkedIn search stops at 1,000 results; Sales Navigator stops at 2,500, paginated 25 at a time. Both are per search, not per day.
Treat these as hard constraints, not guidance. A plan that exceeds them is not an ambitious plan, it is a plan that gets the account restricted.
Per-plan allowances, US list prices, last verified 12 September 2026 by Linkediz:
| Plan | US list price / month | InMail credits / month | Results per search | Saved searches |
| --- | --- | --- | --- | --- |
| Premium Career | $39.99 | 5 | 1,000 | 3 |
| Premium Business | $69.99 | 15 | 1,000 | 3 |
| Sales Navigator Core | $119.99 | 50 | 2,500 | 15 |
| Sales Navigator Advanced | $159.99 | 50 | 2,500 | 15 |
| Sales Navigator Advanced Plus | quote only | 50 | 2,500 | 15 |
| Recruiter Lite | $170 | 30 | 1,000 | 10 |
| Recruiter Corporate | quote only | 150 | 1,000 | 50 |
Notes the numbers do not show:
- Sales Navigator Advanced Plus and Recruiter Corporate carry no published price. LinkedIn quotes them per seat block. Never state a price for those two.
- The InMail allowance does not scale with price. Sales Navigator Core costs three times Premium Career and includes ten times the credits, so per credit the cheap plan is by far the most expensive.
- Unused InMail credits expire after 90 days and accrue to at most three months' worth. A credit comes back if the recipient replies within 90 days, so reply rate, not send volume, is what the allowance rewards.
- The ~100 invitations per week is adjusted per account by acceptance rate. It goes down for accounts that send poorly targeted invitations. It does not go up because a plan was upgraded.
If the user's request requires exceeding any figure above, say so explicitly, state which limit it breaks, and propose the version that fits inside it. Do not quietly scale the plan down and do not quietly exceed it.
## The list
[PASTE THE EXPORT. Include at minimum: name, title, company, headcount, industry, location. Keep the header row.]
## Scoring model
Score each row from 0 to 10, built from four components. Show the components, not just the total.
- Fit (0–4): how well the company matches the ICP firmographics.
- Authority (0–3): how close this title is to signing. Judge by what the title owns at THIS company size, not by seniority alone.
- Timing (0–2): evidence of the trigger in my ICP. No evidence is 0, not 1.
- Reachability (0–1): can I reach them with a connection request, or will this need an InMail credit?
Rules:
- If a row is missing data needed for a component, score that component 0 and add the row to "Cannot score" with the missing field named. Do not infer headcount from company name or seniority from title length.
- Any row matching an exclusion is dropped regardless of score, and the exclusion is named.
- Do not normalise or curve the scores. If the whole list scores 4, that is the finding.
## Tiers
- Contact now: score 7+. Cap this tier at my weekly capacity above, and say what the cap was.
- Contact later: 4–6. Group by what would move them up — usually a missing piece of information or an absent trigger.
- Drop: 0–3 or excluded, with the reason.
## Output format
### Summary
Rows in, rows scored, rows unscoreable, tier counts, and one sentence on what the distribution says about the list.
### Contact now
| # | Name | Title | Company | Fit | Auth | Time | Reach | Total | Why this row |
|---|---|---|---|---|---|---|---|---|---|
Ranked highest first, capped at weekly capacity.
### Contact later
Same table, then one line per group on what would promote them.
### Drop
| Name | Company | Reason |
|---|---|---|
### Cannot score
| Name | Missing field | Where to find it |
|---|---|---|
### What this list tells me
Two or three sentences on the list as a whole: whether the search was too broad, too narrow, or aimed at the wrong titles — and the specific filter change you would make.- You exported a list and the first twenty rows already look uneven.
- Two SDRs are working the same territory and keep arguing about who is in it.
- You are deciding which accounts get a researched message and which get the standard one.
- Your acceptance rate is dropping and you suspect the list, not the copy.
- Export your list to CSV and paste it. Most assistants handle a few hundred rows in one go; above that, split it and run the prompt per batch with the same ICP.
- Be honest in {{SEATS}}. The cap on the "contact now" tier is derived from it, and inflating it produces a plan your account cannot execute.
- Read "What this list tells me" before working the rows. It is often the most valuable output — a list where nothing scores above 6 means the search was wrong, and working it harder will not fix that.
- Feed the "contact now" tier into the Prospect Research prompt one row at a time.
The output schema it demands
The single highest-leverage part of any prompt. Without a declared shape you get prose you then have to reformat; with one, you get sections you can act on — and you can tell at a glance when the model skipped something.
### Summary ### Contact now (capped at weekly capacity) ### Contact later (+ what would promote them) ### Drop (+ reason) ### Cannot score (+ the missing field) ### What this list tells me
What it looks like filled in
Illustrative, not a promise — this is the shape of a good answer rather than a guarantee of one. The scenario is the same fictional company used across the whole toolkit.
180 rows exported from a Sales Navigator search built against the Cadence ICP. Plan: Sales Navigator Core, 1 seat.
Summary — 180 rows in, 142 scored, 38 unscoreable (missing headcount, listed by name). 41 score 7 or above.
Contact now — capped at 100 for the week. Top row: Group Financial Controller, 340-person logistics firm, entity count confirmed on the company page — 9/10.
Drop — 22 rows excluded outright: single-entity companies, matching the stated exclusion.
What this list tells me — the industry filter is too loose. Retail rows are scoring lower across the board than logistics ones on the same headcount band — tighten that filter before the next export rather than working around it row by row.
Do not do these
Each one is a real failure mode, not a disclaimer.
- Letting it score rows with missing data. A model will happily assign 8/10 to a row with no headcount, and you will never know which of your scores were invented.
- Ignoring the cap because the list is exciting. The invitation ceiling does not care how good the list is.
- Re-running it with a looser ICP until more rows qualify. That is not qualification, it is negotiation with yourself.
Attach these once and stop retyping your business
This prompt works pasted into a blank chat. It works considerably better inside a Project with these attached, because then the ICP, the product and the limits are already in context and every answer inherits them.
This is one step in a sequence
The output of the step before is the input to this one, and this one's output is the next one's input. That is the whole reason these are not independent pages.
Before you run it
Why cap the top tier at about 100 a week per seat?
Because that is roughly what LinkedIn allows in connection invitations on every plan, and the ceiling is adjusted downwards for accounts with low acceptance rates. A tier of 400 "contact now" rows on one seat is a list that will either take a month to work or get the account restricted trying.
Can I change the scoring weights?
Yes, and you should once you have run it twice. The weights here — fit 4, authority 3, timing 2, reach 1 — assume a product where fit dominates. If you sell something where timing is everything, move a point from fit to timing and keep the total at 10.
The reference behind this prompt
The weekly cap this prompt applies comes from these figures. Worth reading once so you know what the model is enforcing.
Why a 2,500-row export is the ceiling of a single search, and what to do when your ICP is bigger than that.
Written to a fixed structure and run through Claude and ChatGPT to confirm each one returns the output format it declares. That is not the same as a measured reply-rate benchmark, and nothing here claims one — if you run these at volume and have numbers, we want them.
Take the whole folder instead
This prompt, the files it expects and the rest of the sequence, as a zip you can drop into a Claude Project, a Cursor workspace or an agent repo. Free, no account.