Get the FREE Ultimate OpenClaw Setup Guide →

testimonial-collector

Scanned
npx machina-cli add skill BrianRWagner/ai-marketing-claude-code-skills/testimonial-collector --openclaw
Files (1)
SKILL.md
6.6 KB

Testimonial Collector

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.

If the user wants to skip a field: note it and flag the quality impact in the output.


Phase 1: Situation Analysis

Before drafting anything, reason through:

  1. Client relationship stage: Was this a quick project or a deep engagement? Depth affects how much authentic language is available.
  2. Results clarity: Are the outcomes measurable (numbers, timelines, named outcomes) or soft (vibes, general satisfaction)?
  3. Format match: What placement does the user need this for? A homepage needs different length than a sales deck.
  4. Voice data: Does the user have existing communication from this client (emails, Slack, quotes) that can inform tone?

Output a brief situation summary:

"You have a [length] engagement with [client] in [industry], with [strong/weak] results data. I'll draft in [format] with [authentic/templated] voice. Main gap to address: [specific gap]."


Phase 2: Quality Scoring Framework

Score the raw testimonial content (or anticipated content) before drafting:

DimensionScore 1Score 3Score 5
SpecificityNo detailsVague referencesSpecific named result
Measurability"It was great""Noticeable improvement""40% increase in leads"
Authentic VoiceSounds like ad copySlightly stiltedReads exactly how a person talks
LengthToo short (no context)Decent but thinEnough for all 3 formats

Scoring rule:

  • 4+ on all 4 dimensions → ready to use
  • ≤2 on any dimension → apply iteration protocol before delivering

Phase 3: Draft Generation

The Ask Templates

Direct Ask:

Subject: Quick favor (30 seconds)

Hey [Name],

Loved working on [project] with you — especially seeing [specific result].

Would you be open to sharing a quick testimonial I could use on my site?

No pressure. If yes, I can either:
A) Send you 3 questions to answer
B) Write a draft for you to approve/edit

Whatever's easier.

Question Route:

3 quick questions:
1. What was the situation before we worked together?
2. What changed or improved?
3. Would you recommend this to others? Why?

Draft-on-Behalf Framework: Rules for writing in the client's voice:

  • Tone: Match their actual communication style (check emails/messages for vocabulary)
  • Structure: Situation Before → What Changed → Specific Result → Recommendation
  • Avoid: Superlatives without evidence ("amazing," "life-changing")
  • Avoid: Leading with praise — lead with the client's situation
  • Length: 50-75 words (short), 100-150 words (medium), 200+ (long/full)

Fill-in template:

"[Client situation in 1 sentence]. [What the engagement delivered — concrete]. 
[Specific result, ideally with a number]. [Recommendation statement in client's natural voice]."

Phase 4: Format Production

Short Format (2-liner)

"[One punchy outcome sentence — lead with the result]"
— [Name], [Title] at [Company]

Use for: Homepage, LinkedIn featured section, proposal proof points

Medium Format (2-3 sentences)

"[Problem or situation]. [What changed]. [Recommendation or result]."
— [Name], [Title] at [Company]

Use for: Services page, sales decks, email sequences

Long Format (Full narrative)

Structure:

  1. Context paragraph (2-3 sentences on the situation)
  2. Transformation paragraph (what happened during the engagement)
  3. Results paragraph (outcomes, numbers, named wins)
  4. Closing recommendation sentence

Use for: Case study pages, downloadable PDFs, high-trust sales assets


Phase 5: Self-Critique Pass (REQUIRED)

After generating all formats, evaluate:

Specificity check: Does the short version have at least one concrete outcome (not just "great results")? Voice check: Could the client have actually written this, or does it sound like a marketing headline? Placement check: Is the recommended format actually correct length for the stated use case? Ethics check: Does the draft contain any claims the client didn't make or numbers you added?

Flag any issues: "The short version lacks a specific metric — you'll need to get one number from the client before using this on a homepage."


Iteration Protocol

If the received testimonial scores ≤2 on any dimension, send this gentle follow-up:

"Thanks so much — this is great. One small ask: could you add one specific 
number or outcome? Even rough ('saved us about 5 hours a week') makes it 
much more compelling for other clients. Totally optional, but makes a real difference."

If a second request still yields nothing specific: use Tier 3 proxy language:

"noticeable improvement in [area]" or "process now runs without manual oversight"


Placement Recommendation

Always deliver a placement recommendation with the formatted testimonials:

FormatRecommended LocationsWhy
Short (2-liner)Homepage, proposals, LinkedInTrust at first glance
MediumServices page, email, sales decksOvercome late-stage objections
LongCase study page, PDF, portfolioDeep proof for serious buyers

Cross-reference: If this client has a strong story, suggest running case-study-builder to expand into a full case study.


Output Structure

## Testimonial: [Client Name] — [Date]

### Quality Assessment
- Specificity: [X/5]
- Measurability: [X/5]
- Authentic Voice: [X/5]
- Length: [X/5]
- **Total: [X/20] — [Ready to use / Needs iteration]**

### Short Format (2-liner)
"[Quote]"
— [Name], [Title], [Company]

### Medium Format
"[Quote]"
— [Name], [Title], [Company]

### Long Format
[Full narrative]

### Placement Recommendation
[Where to use each format]

### Next Step
[Iteration note OR cross-reference to case-study-builder]

Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com

Source

git clone https://github.com/BrianRWagner/ai-marketing-claude-code-skills/blob/main/testimonial-collector/SKILL.mdView on GitHub

Overview

The Testimonial Collector guides you to gather client details, score potential quotes, and draft polished testimonials for multiple formats. It emphasizes specificity, measurable results, and authentic voice to turn happy clients into credible social proof. The kit includes asks, questions, and draft frameworks to streamline the process.

How This Skill Works

It starts with Phase 1: Situation Analysis to collect client name, company, industry, project type, key results, and output format, plus urgency. Phase 2 applies a 4-dimension quality scoring framework (Specificity, Measurability, Authentic Voice, Length) to decide readiness. If needed, Phase 3 offers Direct Ask, Question Route, or Draft-on-Behalf methods, and Phase 4 formats produce Short, Medium, or Long testimonials.

When to Use It

  • To add credible social proof on a homepage or landing page
  • To collect structured feedback after a project for testimonials archive
  • To turn happy clients into public advocates for case studies or reviews
  • To request testimonials with a clear process and format
  • To draft client-ready quotes in the client’s own voice

Quick Start

  1. Step 1: Gather client name, company, industry, project type, key results, desired output, and urgency
  2. Step 2: Run Phase 2 quality scoring and flag any dimension ≤ 2 for iteration
  3. Step 3: Choose a template (Direct Ask, Question Route, or Draft-on-Behalf) and generate Short/Medium/Long formats

Best Practices

  • Always require a specific result before drafting
  • Clarify the output format and urgency at the start
  • Score using the 4-dimension framework and iterate if needed
  • Match tone and voice to the client; avoid hype without evidence
  • Capture client metadata (name, company, industry) to boost credibility

Example Use Cases

  • Homepage hero quote using a 40% leads increase with client attribution
  • Medium-length product page testimonial from a named client with before/after
  • Sales deck blurb featuring a quantified outcome and client role
  • LinkedIn feature quote endorsed by the client
  • Case-study intro sentence drafted via Draft-on-Behalf workflow

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers