Skip to main content
11 files · 8 prompts · v1.0

LinkedIn Sales Agent

A working agent folder — root instruction, seven context files and the prompts — that you fill in once and use for a year. The full outbound stack as a folder. Drop it into a Claude Project, a Cursor workspace or a Claude Code repo, fill in the angle-bracket placeholders in ICP.md and PRODUCT.md, and every subsequent request inherits who you sell to, what you may claim, how you write and what LinkedIn actually permits.

No email, no account, no cookie wall. Every file in it is also readable in full on this site.

What you get

The folder

linkedin-sales-agent/
├── README.md   # setup, in order
├── CLAUDE.md
├── LINKEDIN-LIMITS.md
├── ICP.md
├── PERSONAS.md
├── PRODUCT.md
├── COMPANY.md
├── OUTREACH.md
├── BRAND-VOICE.md
├── OBJECTIONS.md
├── RESEARCH.md
├── SALES-NAVIGATOR.md
└── PROMPTS/
    ├── icp-builder.md
    ├── sales-navigator-search-builder.md
    ├── lead-qualification.md
    ├── prospect-research.md
    ├── cold-outreach-personalizer.md
    ├── connection-request.md
    ├── follow-up-sequence.md
    └── reply-handler.md
Version 1.0 — updated 18 September 2026For SDR, Account executive, FounderSet up once, then every session starts with the context already loaded
One prompt from inside the folder

ICP Builder, worked

What this pack produces once the files above are filled in — the actual example from this prompt's own page.

Setup

About twenty minutes, most of it writing down your ICP

  1. Download and unzip.
  2. Fill ICP.md, PRODUCT.md and BRAND-VOICE.md — about twenty minutes.
  3. Attach the folder to a Claude Project, a ChatGPT Project, or drop it in a Cursor workspace.
  4. Run PROMPTS/sales-navigator-search-builder.md as the first real task.
The loop it is built around

What you do with it once it is set up

  1. ICPBuild it from closed deals, or fill ICP.md by hand. Everything downstream reads it.
  2. SearchTurn the ICP into Sales Navigator filters and Boolean, tier-aware.
  3. QualifyScore the export down to what a week of invitations can actually cover.
  4. ResearchOne brief per surviving prospect, with the evidence line drawn explicitly.
  5. MessageFirst touch built on a stated hypothesis, at the right length.
  6. Follow upThree to four touches inside the platform ceilings, with a stop rule.
  7. ReplyClassify what came back and answer it — or close the thread cleanly.
  8. LearnAdd the week’s objections to OBJECTIONS.md. The folder gets better; the prompts do not change.
Read before you download

Every file, in full, on this site

Nothing in the pack is hidden behind the download. If you would rather take three files than fifteen, take three.

  • Context file

    CLAUDE.md

    An agent that reads the right files in the right order and knows what it is not allowed to do.

  • Context file

    LINKEDIN-LIMITS.md

    Your assistant stops proposing 300 connection requests a week, because it now knows the ceiling is about 100.

  • Context file

    ICP.md

    Every prompt you run afterwards knows who you sell to, in terms LinkedIn can filter on.

  • Context file

    PERSONAS.md

    Messages that speak to what the reader is measured on rather than to a job title.

  • Context file

    PRODUCT.md

    Messages stop describing features and start describing what changes for the person receiving them.

  • Context file

    COMPANY.md

    The assistant stops describing your company the way its training data describes companies in your category.

  • Context file

    OUTREACH.md

    Every message an assistant writes comes out at the right length, in the right shape, with the openers you hate already banned.

  • Context file

    BRAND-VOICE.md

    Drafts arrive in your voice on the first attempt instead of after four rounds of "less corporate".

  • Context file

    OBJECTIONS.md

    The assistant answers the objection you actually get, in the way that has worked, instead of improvising.

  • Context file

    RESEARCH.md

    Research that is consistent between people and between runs, with the evidence line drawn in the same place every time.

  • Context file

    SALES-NAVIGATOR.md

    Search instructions that reference filters your tier actually has.

  • Prompt

    ICP Builder

    An ICP written in the vocabulary LinkedIn search understands, derived from deals you actually closed rather than from who you wish would buy.

  • Prompt

    Sales Navigator Search Builder

    A filter-by-filter Sales Navigator search you can build in about three minutes, plus the Boolean strings for the fields that accept them.

  • Prompt

    Lead List Qualifier

    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.

  • Prompt

    LinkedIn Prospect Research

    A one-page research brief on a single prospect that ends in a usable opening line, and that separates what it read from what it inferred.

  • Prompt

    LinkedIn Outreach Personalizer

    A first message and its follow-up, built from a stated hypothesis, with every claim traceable to something you actually gave it.

  • Prompt

    Connection Request Generator

    Three connection requests under 300 characters, each with one specific reference, plus a recommendation on whether to send a note at all.

  • Prompt

    Follow-up Sequence Builder

    A three-to-four touch sequence with dates, channels, a stop rule, and a capacity check against what your plan can actually send.

  • Prompt

    Reply & Objection Handler

    A read of what the reply actually means and three responses at different levels of directness, including the one that ends it politely.

Licence, in plain words

Use it for your work and your clients' work

You may

Use every prompt, file and pack for your own company or for clients you are paid by, commercially, modified as much as you like. Put them in your Claude Project, your ChatGPT Project, your Cursor workspace or your agent repo. Share a filled-in copy with your team.

You must

Keep the attribution line at the bottom of any file you redistribute unchanged, and credit Linkediz with a link wherever you republish a resource in full.

You may not

Repackage the library or a pack as your own product, paid or free, or scrape the section to rebuild it elsewhere. The downloads exist so you do not have to.

No warranty

These are writing and research aids. They do not know your customers, they can be wrong, and an assistant will state a fabricated fact as confidently as a true one. Read what comes out before you send it to a person.

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.

Questions

About this pack

Do I need Claude Code for this?

No. It works as a Claude Project, a ChatGPT Project or a Gemini Gem — anywhere you can attach files to a standing instruction. Claude Code and Cursor read CLAUDE.md automatically, which is convenient rather than necessary.

How long does setup actually take?

Twenty minutes if you know your ICP, an hour if you do not — and in that case most of the hour is the ICP prompt, which is work you needed to do anyway.

Where the constraints come from

The reference behind this pack

The limits this pack enforces

LINKEDIN-LIMITS.md is generated from this page. Reading it once tells you what the agent is refusing to do and why.

Which tier your searches need

The search builder marks Advanced-only filters. This page prices the difference.