Prd V10 Testimonial Collector logo

Prd V10 Testimonial Collector

Community
mattgierhart
prd-v10-testimonial-collector

Systematically harvest short testimonials from customers via NPS, milestones, post-purchase, and email during PRD v1.0 Market Adoption. Triggers on requests to collect testimonials, set up social proof harvest, gather customer quotes, or when user asks "how do we get testimonials?", "social proof harvest", "NPS responses", "testimonial wall", "customer quotes", "post-purchase survey", "milestone follow-up". Outputs CFD-TST-* testimonial entries and GTM-TST-* placement assets.

Overview

Publishermattgierhart
RepositoryPRD-driven-context-engineering
Skill nameprd-v10-testimonial-collector
Stars
179
Forks
11
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mattgierhart on GitHub. Read the source before you install it.

Installation

Install the Prd V10 Testimonial Collector AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git /tmp/PRD-driven-context-engineering
mkdir -p .claude/skills
cp -r /tmp/PRD-driven-context-engineering/plugins/prd-ce/skills/prd-v10-testimonial-collector .claude/skills/prd-v10-testimonial-collector
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prd V10 Testimonial Collector in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prd V10 Testimonial Collector on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prd V10 Testimonial Collector is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Testimonial Collector

Position in workflow: v1.0 Case Study Builder → v1.0 Testimonial Collector → GTM channels (placement)

Execution Mode

Default is standard. See .claude/rules/08-skill-execution-modes.md for selection logic.

ModeWhat this skill produces
quickOne trigger (e.g., NPS promoters) + collection email + 5–10 testimonials processed
standard3 triggers (NPS, milestone, post-purchase) + processing workflow + consent management + per-placement formatting
deep5+ triggers + automated harvest + sentiment-segmentation + per-segment placement targeting + measurement loop

What This Does

Systematically harvests short-form testimonials — 1–3 sentence quotes with name + role + logo — and processes them into placement-ready assets. Testimonials are the lower-effort complement to case studies: they don't carry a full story but they multiply social proof on landing pages, pricing pages, ad creative, and outreach.

This skill solves the "we have happy customers but no quotes" problem — most teams have plenty of positive feedback in support tickets, NPS responses, and renewal calls, but never capture it as marketing-ready assets. The fix is a system, not heroic effort.

How It Works

  1. Identify collection triggers — Each trigger is an event that suggests the customer is in a moment to share positive feedback:
    • NPS Promoter response (score 9–10) — Lowest-friction; they already wrote feedback
    • Activation milestone (Day 30 / Day 90 active) — They've seen value by now
    • Post-purchase / post-upgrade — Decision fresh in mind
    • Renewal — Strong signal of ongoing value
    • Support resolution (positive) — Acute "you saved my day" moment
    • Referral from customer — They already advocated
  2. Build per-trigger collection mechanism:
    • NPS Promoter → automated email asking permission to use response + adding 1-question follow-up
    • Milestone → in-app prompt or email with one-line ask
    • Post-purchase → email 7 days after purchase
    • Renewal → CSM-led ask during renewal call
    • Support → followup in support thread after positive resolution
  3. Process incoming testimonials — Each goes through:
    • Consent confirmation (scope: name? role? logo? use anywhere?)
    • Light edit for clarity (their voice; don't rewrite)
    • Tag by segment fit (in-beachhead / adjacent / off-segment)
    • Tag by outcome theme (speed / cost / activation / quality / etc.)
  4. Place in marketing surfaces — Per testimonial:
    • Pricing page (logo + quote)
    • Landing page hero (1 prominent quote)
    • Feature pages (segment-relevant quotes)
    • Ad creative (testimonial-style ads)
    • Email signatures / sales decks
    • Investor decks
  5. Measure placement performance [standard+] — Some testimonials convert; some don't. Track per-placement conversion to identify which quotes earn their spot.

Example

B2B SaaS, 3 collection triggers active.

Trigger 1: NPS Promoter (9–10). NPS run quarterly. Promoters get followup email:

Thanks for the 10! Your response — "Cut our reporting time in half" — would be a powerful testimonial for our pricing page. May we use it with your name and role? Reply YES and we'll send back the version we'd publish for your approval.

Auto-fires when NPS response submitted with score ≥ 9.

Trigger 2: Day-30 active milestone. In-app prompt at first login after Day 30 active:

You've been active for a month! In one sentence, what's working best? → [text box] → [Submit + permission checkbox]

Trigger 3: Post-purchase (Day 7). Email 7 days after first paid charge:

Quick favor — what convinced you to upgrade? Your answer might appear (with your permission) on our pricing page.

Processing: Inbound testimonials enter a triage doc. Per testimonial:

  • Consent confirmed (scope: name / role / logo / anywhere)
  • Light edit (clarity only — kept their voice)
  • Segment tag (in-beachhead: yes/no)
  • Theme tag (speed / cost / activation / quality)
  • Placement decision (pricing / landing / feature page / ad / multi)

Placement: Pricing page logo wall expanded with 6 new testimonials in the beachhead segment. A/B test the hero-section quote on landing pages.

What You Get Back

  • CFD-TST-* entries — One per testimonial; the durable record with consent, source, segment, theme
  • GTM-TST-* entries — Per-placement formatting (the placed quote with surrounding context)
  • Consent records — Customer-by-customer scope and version history
  • Placement-performance log — Per-quote conversion rate (which testimonials earn their spot)

When to Use It

TriggerMode
First testimonial harvest system (none in place)standard
Quarterly NPS run + harvestquick
Pricing page redesign needs more social proofstandard
Landing page A/B test needs quote variantsquick
Pre-investor / pre-Series A push for logo + quote densitydeep
New segment expansion (need segment-specific testimonials)deep

Consumes

  • CFD-* customer feedback (all sources, especially v0.9 feedback loop) — Raw inbound testimonial material
  • NPS / CSAT data (from v0.9 Feedback Loop Setup) — Promoter responses are the highest-yield source
  • ADO-REF-* candidates — Reference accounts already in cultivation are testimonial-eligible
  • PER-* personas + ADO-BEACHHEAD-* — Segment tagging
  • BR-POS-* — Tone constraints; testimonials shouldn't contradict positioning

Produces

  • CFD-TST-* entries in SoT/SoT.customer_feedback.md
  • GTM-TST-* entries (with Type=Testimonial-Placement) per placement
  • Consent records — Append-only log with scope and version
  • Placement-performance metrics — Per-quote A/B data feeding back into selection

Output Template

CFD-TST-XXX: Testimonial — [Customer name]
Type: Testimonial
Date received: YYYY-MM-DD
Source trigger: [NPS-promoter | Day-30-milestone | Post-purchase | Renewal | Support | Referral]
Customer: [Name, Role, Company, Logo]

Verbatim text:
  "[The actual quote, lightly edited for clarity only]"

Original text (for audit):
  "[The raw response]"

Tags:
  Segment fit: [In-beachhead | Adjacent | Off-segment]
  Theme: [Speed | Cost | Activation | Quality | Reliability | Specific-use-case]
  Length: [Words / chars]

Consent:
  Scope: [Name? Role? Logo? Use-anywhere?]
  Approved by: [Customer name]
  Approved date: YYYY-MM-DD
  Approved version: vX

Placement eligibility:
  - Pricing page logo wall: [Yes/No]
  - Landing page hero: [Yes/No]
  - Feature page (which): [Yes/No]
  - Ad creative: [Yes/No]
  - Sales deck: [Yes/No]
  - Investor deck: [Yes/No]

Linked IDs: PER-XXX (segment), ADO-REF-YYY (if cultivated), CFD-ZZZ (interview source if applicable)
GTM-TST-XXX: Testimonial Placement — [Quote summary]
Type: Testimonial-Placement
Source: CFD-TST-AAA
Placement: [URL or surface, e.g., "/pricing — hero zone"]
Format: [Quote + Name + Role + Logo | Quote + Logo only | Quote in card]

Surrounding context:
  [What this testimonial sits next to — headline, CTA, product feature]

A/B test (if active):
  Variant A: [This testimonial]
  Variant B: [Alternative]
  Metric: [Click-through, signup-rate, etc.]
  Started: YYYY-MM-DD

Performance (if measured):
  [Per-quote conversion data]

Linked IDs: CFD-TST-AAA (source), GTM-YYY (page channel), KPI-ZZZ (placement metric)

Anti-Patterns

PatternSignalFix
Heroic one-time harvest"We collected 20 testimonials in a sprint, then stopped"Triggers run continuously; harvest is a system, not a project
No consent recordPublishing without explicit approvalConsent record per testimonial, scope-explicit
Marketing rewrite"I love [product]" rewritten from "It's pretty useful"Light edits for clarity only; their voice
No segment taggingAll testimonials placed everywhereSegment-relevant placement converts better; tag and target
Stale wallsPricing page testimonials from 2 years agoRefresh quarterly; rotate underperformers
No placement measurementAll testimonials treated as equally goodSome quotes convert 3× others; measure and prune
Anonymous testimonials"VP at major fintech" with no name/logoPragmatists discount anonymous; named + logo or skip
Off-segment testimonials during chasm crossingVisionary-startup quotes on a page targeting enterprise pragmatistsIn-segment placements only during chasm crossing

Quality Gates

Before placing testimonials:

  • Consent on record (scope explicit)
  • Customer name + role + logo (or rationale for less)
  • Segment tag applied
  • Theme tag applied
  • Light edit only (their voice preserved)
  • Placement matches segment fit (in-beachhead testimonials for pragmatist surfaces)
  • BR-POS-* constraints honored (no contradiction with positioning)
  • Refresh cadence committed (quarterly minimum)

Downstream Connections

ConsumerWhat it usesExample
Launch Channels (ORB)Testimonials are Owned-channel content + Borrowed-channel ad creativePricing-page testimonials = Owned; testimonial-style ads = Paid-Borrowed
Alternatives Pages"Pick us if..." sections feature segment-relevant testimonialsMigration-from-X testimonial anchors the alt page
Case Study BuilderStrong testimonials surface case-study candidatesRepeat testimonialer with strong outcome → case study
Cold Outreach (Tiered)Testimonials cited in Touch 2/3 of sequencesTier 2 email includes in-segment testimonial
Feedback Loop SetupTestimonial sources tie back to feedback channelsNPS promoters feed both feedback and testimonial flow
Investor / Sales decksLogo wall + theme-curated testimonials"Customers in segment X say..."

Detailed References

  • BrianRWagner's testimonial-collector skill (ai-marketing-claude-code-skills)
  • Sean D'Souza, The Brain Audit (using testimonials to overcome buying objections)
  • Joanna Wiebe, Copy Hackers — testimonial-driven landing pages
  • (No bundled references/ — testimonials are the artifact)

Frequently asked questions

What does the Prd V10 Testimonial Collector AI skill do?

Systematically harvest short testimonials from customers via NPS, milestones, post-purchase, and email during PRD v1.0 Market Adoption. Triggers on requests to collect testimonials, set up social proof harvest, gather customer quotes, or when user asks "how do we get testimonials?", "social proof harvest", "NPS responses", "testimonial wall", "customer quotes", "post-purchase survey", "milestone follow-up". Outputs CFD-TST-* testimonial entries and GTM-TST-* placement assets.

Why use Prd V10 Testimonial Collector on TypingMind?

Because you install it once and use it with any model. Prd V10 Testimonial Collector is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prd V10 Testimonial Collector in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/plugins/prd-ce/skills/prd-v10-testimonial-collector. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Prd V10 Testimonial Collector?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prd V10 Testimonial Collector?

As many as you like. As long as a model supports skills, you can use Prd V10 Testimonial Collector with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prd V10 Testimonial Collector AI skill free?

Yes. It is published on GitHub by mattgierhart under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇