Testimonial Collector

brianrwagner/ai-marketing-claude-code-skills

Turns testimonials from "hey can you write something nice" into actual sales assets with numbers and specificity. The quality scoring framework is the real value here: it won't let you ship vague praise, and it includes iteration scripts to push clients for concrete metrics when they give you generic feedback. Three modes scale from a single outreach script to a full VA-ready collection system with multi-channel campaigns. The voice matching guidance is practical, pulling from actual client emails instead of writing ad copy. If you've ever gotten back "it was great!" and didn't know how to salvage it, the iteration protocol handles that exact scenario.

skills.sh installs: 402
GitHub stars: 455
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add brianrwagner/ai-marketing-claude-code-skills --skill testimonial-collector --agent claude-code

Installs into .claude/skills of the current project.

Files

Testimonial Collector

Mode

Detect from context or ask: "One script, full system, or full system with campaign?"

Mode	What you get	Best for
`quick`	1 outreach script + 1 format template	Asking one client, right now
`standard`	Full collection system: timing, scripts, formatting, display guidance	Building repeatable social proof
`deep`	Full system + multi-channel strategy + case study pipeline	Sales enablement, proposal library

Default: standard — use quick if they have one client in mind. Use deep if they want a system they can hand to a VA.

Context Loading Gates

Before proceeding, gather:

Client name, company, and industry
Project type and specific deliverables
Key results — push for at least one number ("even a rough estimate")
Desired output format (short quote / medium paragraph / full narrative)
Urgency (this week vs. building a library)

If results are vague (e.g., "things improved"), stop and ask: "Can you name one specific number — even a rough estimate? That's what makes a testimonial credible and usable." Do not draft until you have this.

SKILL.md on GitHub