social-selling

social-selling is a skill for Claude Code from Doris-Labs/sales-skills. It costs 74 tokens per session (1,571 once invoked), scanned A, original, MIT.

A guide for starting conversations with potential customers on LinkedIn by using their profile, posts, career history, and shared connections as context before making an offer.

In plain words
What is it for?
Use it to research a prospect, plan profile engagement, write a connection note, and create a personalized first-message sequence.
Why use it?
It helps avoid generic connection requests and sales messages that prospects ignore. The approach provides a reason for each interaction and builds familiarity first.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-skills plugin — 30 skills shipped together

Good fit Use it to research a prospect, plan profile engagement, write a connection note, and create a personalized first-message sequence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/social-selling
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Doris-Labs/sales-skills --skill social-selling
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for social-selling

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/social-selling/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/social-selling)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/social-selling"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/social-selling/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for social-selling

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/social-selling"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/social-selling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01571
Opus 5 $0.00037 $0.00785
Sonnet 5 $0.00015 $0.00314
Haiku 4.5 $0.00007 $0.00157

Measured 12d ago against content hash f35f9bd55b83, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

social-selling scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/social-selling/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Selling

Purpose

Turn a cold LinkedIn profile into a warm conversation: engage with the prospect's world first, send a connection note they accept, and open with a first message that references something real — not a templated pitch they've seen a hundred times.

Inputs

  • The prospect (LinkedIn URL, name + company, or profile text)
  • Why you're reaching out (the trigger: their post, a role change, a mutual, an account play)
  • The account context (existing deal, prior touchpoints, who else you know there)

Method

1. Profile-led engagement — warm before you pitch

Never let the connection request be the first time they've heard your name. Read the profile for hooks and engage on their terms first:

  • Recent activity — posts, comments, reposts in the last 2–4 weeks. This is the highest-signal hook; it's what they care about right now.
  • Role + tenure — new in role (<6 months) = openness to change; long tenure = owns the status quo.
  • Career path / shared ground — past companies, schools, regions, mutual connections.
  • About section + featured — the problems they self-identify with, in their words.

Warm-before-pitch rule: earn one to three touchpoints (a thoughtful comment, a relevant reaction) before the connection request. The request then lands as "the person who said that smart thing," not a stranger.

2. Content-comment cadence — engage before reaching out

Run this over 5–10 business days, not all at once:

Day Action
1 Follow (not connect). Like 1 recent post.
2–3 Leave one substantive comment on a recent post — add a point, don't praise.
4–5 React to a second post; reply if they answer your comment.
6 Send the connection request with a note (formula below).
8–10 If accepted and quiet, send first message. If ignored, keep commenting; retry the request in 3–4 weeks.

Comment quality bar: a good comment teaches, disagrees respectfully, or adds a concrete example. "Great post!" is invisible. "We saw the opposite with X — curious if Y was a factor for you?" gets a profile click.

Read the full file on GitHub · 131 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 131 lines · 74 tokens per session scan A f35f9bd55b83

Subscribe to this mod's changes

social-selling is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,571 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.