social-selling

31 stars 7 forks
28
B

Use when engaging prospects through LinkedIn, communities, and social channels to spark warm conversations and meetings.

Marketplace
Also in: javascript ci cd

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install gtmagents/gtm-agents/social-selling
skilz install gtmagents/gtm-agents/social-selling --agent opencode
skilz install gtmagents/gtm-agents/social-selling --agent codex
skilz install gtmagents/gtm-agents/social-selling --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/gtmagents/gtm-agents
2. Copy the agent skill directory:
cp -r gtm-agents/plugins/sales-prospecting/skills/social-selling ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Repository
gtm-agents
Stars
31
Forks
7
Type
Non-Technical
Meta-Domain
development
Primary Domain
github
Market Score
28

Agent Skill Grade

B
Score: 80/100 Click to see breakdown

Score Breakdown

Spec Compliance
12/15
PDA Architecture
22/30
Ease of Use
20/25
Writing Style
8/10
Utility
17/20
Modifiers: +1

Areas to Improve

  • Tips Section Belongs in References
  • Missing Navigation TOC
  • Workflow Lacks Numbered Steps

Recommendations

  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I've been reading through your social-selling skill and wondering how you're handling the balance between automation and authentic relationship-building—that's honestly where most tools fall apart. Your approach to this scored well (80/100), but I'm curious about a few edge cases in your implementation.

Links:

The TL;DR

You're at 80/100, solid B territory. This is based on Anthropic's skill evaluation framework across five pillars. Your Utility is really strong (17/20)—the engagement ladder and signal tracking are legitimately useful frameworks for SDRs. The weaker spot is Progressive Disclosure Architecture (22/30), which is mostly about token economy and navigation.

What's Working Well

  • Engagement ladder framework - The progression from monitoring → micro-engaging → direct outreach is solid tactical structure that actually maps to how social selling works in practice.
  • Signal tracking table - Mapping specific LinkedIn signals (job change, new role, content posted) to corresponding actions gives Claude something concrete to pattern-match on.
  • DM script examples - You've got working "Insight" and "Mutual Connection" scripts with clear input/output, which beats the hell out of abstract guidance.
  • Proper trigger phrases - Your description nails it with "engaging prospects," "LinkedIn," "social channels" as discoverability hooks.

The Big One: Tips Section Belongs in References

Here's what's eating your PDA score: that Tips section (lines 27-31) in SKILL.md is adding unnecessary bulk to your main file. Those five lines about engaging within 30 minutes and alternating public/private touches? They belong in engagement_playbook.md as a "Best Practices" section at the ...

Report Security Issue

Found a security vulnerability in this agent skill?