agentleFS
surfmind-spacesurfmind-space/awesome-surfmind/skills/linkedin-outreach/SKILL.md

linkedin-outreach

Skill8 starsChanged 5 months agoMITView on GitHub

Drafts short LinkedIn connection or outreach messages for recruiters, hiring managers, peers, and interviewers using the visible job or company context. Use when the user wants to write a LinkedIn message, connect with a recruiter, or reach out to someone about a job opportunity.

7 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use cold-email.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ukunal91appSkill

    cold-email

    Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails, prospecting emails, cold email campaigns, sales development emails, or SDR emails. Also use when the user mentions "cold outreach," "prospecting email," "outbound email," "email to leads," "reach out to prospects," "sales email," "follow-up email sequence," "nobody's replying to my emails," or "how do I write a cold email." Covers subject lines, opening lines, body copy, CTAs, personalization, and multi-touch follow-up sequences. For warm/lifecycle email sequences, see email-sequence. For sales collateral beyond emails, see sales-enablement.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the message under 300 characters unless the user asks for a longer note, and include one alternate version with a different angle when …

    line 22

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Linkedin Outreach

Draft a short career outreach message from the selected text, visible page, job description, company page, person profile, or user request, and present it in chat for copy-paste. Work only from the user's supplied background, target role, proof points, and relationship to the recipient — use a concrete proof point only if they gave it to you, never invent numbers or qualifications. Avoid generic enthusiasm, phone numbers, and pressure; never lead with "please refer me" to a peer. Adapted from santifer/career-ops contacto mode.

  1. Identify the contact type — recruiter (talent acquisition, sourcer, HR), hiring manager (leads or owns the team), peer (similar role, collaborator, possible referral path), or interviewer (already scheduled or named in the process). If it's unclear, draft by likely type and say what would improve personalization.
  2. Build the message on the three-sentence framework for that contact type:
    • Recruiter: Fit (the direct match — role, relevant experience, location, or availability), Proof (data that answers a screening question before they ask it), CTA (offer to share the CV if it aligns).
    • Hiring manager: Hook (a specific challenge their team faces, drawn from the posting, blog, or news), Proof (the user's strongest relevant quantified achievement), CTA (ask how the team is approaching that challenge).
    • Peer: Interest (a genuine reference to their work — a post, talk, or project), Connection (something the user is doing in the same space, not a job pitch), CTA (invite their take on a shared topic). Don't ask for a job or referral; it happens naturally if the conversation flows.
    • Interviewer: Research (a reference to their work or trajectory), Context (a light tie to the user's experience), CTA (look forward to the scheduled conversation). Keep it light, never eager.
  3. Keep the message under 300 characters unless the user asks for a longer note, and include one alternate version with a different angle when the context supports it.

Return Contact type, Primary message, Alternative, and Why this works. If the visible page doesn't show enough detail, keep the message honest and ask for the missing detail that would make it stronger.

Example

Context (a recruiter's profile + the user's note):

Sarah Lin, Senior Recruiter at Northwind, posted a Backend Engineer role (Go, distributed systems, remote US). My note: 6 yrs backend, built a payments service handling 2k req/s in Go, open to remote.

Output:

Contact type: Recruiter

Primary message: Hi Sarah — saw the Backend Engineer opening at Northwind. I've spent 6 years in Go backend, most recently building a payments service handling 2k req/s. Remote works well for me. Happy to send my CV if it looks like a fit.

Alternative: Hi Sarah — the Northwind Backend Engineer role caught my eye. Distributed systems in Go is exactly my lane (payments service at 2k req/s). Open to remote — would love to learn more.

Why this works: Leads with the direct fit and a concrete throughput number that pre-answers a screening question, then a low-pressure CTA. Both stay under 300 characters.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.