LinkedIn Recruiter Agent
A sourcing assistant that stays inside a 30-credit month and does not score things a profile cannot evidence. Built around the two constraints recruiting AI usually ignores: a finite InMail allowance, and the requirement that a shortlist be defensible. Requirements are split into evidenceable and not, protected characteristics and their proxies are off limits, and the credit budget is part of the plan rather than an afterthought.
No email, no account, no cookie wall. Every file in it is also readable in full on this site.
The folder
linkedin-recruiter-agent/
├── README.md # setup, in order
├── CLAUDE.md
├── LINKEDIN-LIMITS.md
├── RECRUITER.md
├── RESEARCH.md
├── OUTREACH.md
├── BRAND-VOICE.md
├── AGENTS.md
└── PROMPTS/
├── talent-mapping.md
├── boolean-search-generator.md
├── candidate-research.md
├── recruiter-outreach.md
└── inmail-writer.mdTalent Map, worked
What this pack produces once the files above are filled in — the actual example from this prompt's own page.
Role: Senior Backend Engineer (Go), payments domain, London or remote UK.
Source archetypes — direct: payments startups, high confidence. Adjacent: banking-infrastructure vendors, medium confidence. Overlooked: internal payments teams at large retailers — same problem, a less fashionable employer, far less recruiter competition.
Pool assessment — normal difficulty in London; hard if the role is restricted to remote-UK-only candidates rather than remote-with-relocation.
What would make the hire easier — dropping "payments domain" from must-have to nice-to-have roughly triples the addressable pool, based on the requirements split above.
About twenty minutes, most of it writing down your ICP
- Download and unzip.
- Fill RECRUITER.md — the requirements split is the part worth doing carefully.
- Attach to a Claude or ChatGPT Project.
- Start with PROMPTS/talent-mapping.md, before you build a single search.
What you do with it once it is set up
- Map — Which companies produce this profile, and what the role is called inside each.
- Search — Boolean per archetype, within the result cap of your tier.
- Shortlist — Evidence per requirement. Unevidenced means unknown, not zero.
- Message — Company named, salary given where permitted, ask kept small.
- Hold — The "not looking" reply that keeps a candidate warm for six months.
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
RECRUITER.md
Sourcing and outreach that stays inside your InMail budget and does not infer things it should not.
- 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
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
AGENTS.md
Three narrow agents with defined handoffs instead of one conversation that drifts.
- Prompt
Talent Map
A named list of source companies, the titles the role is called at each, and the search strings that find them.
- Prompt
Boolean Search Generator
A copy-paste Boolean string built from real title variants, with the exclusions that remove the usual pollution.
- Prompt
Candidate Research & Shortlist
A ranked shortlist with evidence per requirement, the gaps named, and a screening question per candidate.
- Prompt
Recruiter Outreach
A subject line and message aimed at one candidate, with the details that decide whether a passive candidate replies included rather than withheld.
- Prompt
InMail Writer
A subject line and body written for a paid message, preceded by an honest verdict on whether to spend the credit at all.
Use it for your work and your clients' work
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.
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.
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.
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.
The reference behind this pack
Lite gives 30 InMail credits, Corporate 150 and no published price. The budget section of this pack is built on these figures.
For occasional hiring, Sales Navigator is often the cheaper tool. This compares them without a preferred answer.