- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill testimonial-collector -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill testimonial-collector -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill testimonial-collector -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add BrianRWagner/ai-marketing-claude-code-skills --skill testimonial-collector -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/BrianRWagner/ai-marketing-claude-code-skills/tree/HEAD/testimonial-collector來自發布者
Detect from context or ask: "One script, full system, or full system with campaign?"
Default: standard — use quick if they have one client in mind. Use deep if they want a system they can hand to a VA.
Before proceeding, gather:
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.
Before drafting anything, reason through:
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]."
Score the raw testimonial content (or anticipated content) before drafting:
Scoring rule:
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:
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]."
"[One punchy outcome sentence — lead with the result]"
— [Name], [Title] at [Company]
Use for: Homepage, LinkedIn featured section, proposal proof points
"[Problem or situation]. [What changed]. [Recommendation or result]."
— [Name], [Title] at [Company]
Use for: Services page, sales decks, email sequences
Structure:
Use for: Case study pages, downloadable PDFs, high-trust sales assets
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."
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"
Always deliver a placement recommendation with the formatted testimonials:
Cross-reference: If this client has a strong story, suggest running case-study-builder to expand into a full case study.
## 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
Systematically gather, score, and format client testimonials. Use when someone needs social proof, wants to collect feedback, needs to turn happy clients into public advocates, or asks for help reques
---name: testimonial-collectordescription: Systematically gather, score, and format client testimonials. Use when someone needs social proof, wants to…---# testimonial-collector/SKILL.md總覽
Systematically gather, score, and format client testimonials. Use when someone needs social proof, wants to collect feedback, needs to turn happy clients into public advocates, or asks for help requesting or drafting a testimonial.
常見問題
從發布者下載 testimonial-collector/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/BrianRWagner/ai-marketing-claude-code-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。