data-sourcing

31 stars 7 forks
28
A

Optimize provider selection, routing, and credit usage across 150+ enrichment sources for company/contact intelligence.

Marketplace

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/data-sourcing
skilz install gtmagents/gtm-agents/data-sourcing --agent opencode
skilz install gtmagents/gtm-agents/data-sourcing --agent codex
skilz install gtmagents/gtm-agents/data-sourcing --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/data-enrichment-master/skills/data-sourcing ~/.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
Technical
Meta-Domain
cloud infrastructure
Primary Domain
terraform
Market Score
28

Agent Skill Grade

A
Score: 93/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
28/30
Ease of Use
23/25
Writing Style
9/10
Utility
19/20
Modifiers: +3

Areas to Improve

  • Description needs trigger phrases
  • Missing TOC for long file
  • Redundant waterfall examples

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 looking at how you structured the data sourcing patterns here—the layered approach to handling heterogeneous data sources is pretty clean, and it shows solid thinking about extensibility. Curious whether you're planning to add validation layers between the source connectors and the consumers, or if that's intentionally left to downstream code?

Links:

The TL;DR

You're at 93/100, solidly in A territory. This evaluation is based on Anthropic's Claude Skills best practices rubric. Your strongest area is Utility (19/20)—the waterfall routing and credit optimization frameworks are genuinely useful. Weakest spot is Spec Compliance (11/15), mainly because your description lacks trigger phrases that help users discover the skill.

What's Working Well

  • Utility is chef's kiss – The provider selection matrix, cost-tier strategies, and credit optimization approach solve a real problem for teams dealing with 150+ enrichment sources. This isn't theoretical—it has clear ROI.
  • Solid PDA structure – You've nailed the layered approach: SKILL.md is comprehensive, provider_cheat_sheet.md and cost_calculator.py are exactly one level deep for reference. References land perfectly.
  • Discoverability is tight – Your "When to Use" section has excellent trigger terms (provider selection, waterfall, credit audit, enrichment design). Developers will find this when they need it.
  • Consistency throughout – Terminology stays uniform (waterfall, enrichment, provider, credits, cache). No semantic drift.

The Big One: Missing Trigger Phrases in Description

Your frontmatter description is specific but doesn't include trigger phrases that help discoverability:

Current:

description: Opti...

Report Security Issue

Found a security vulnerability in this agent skill?