Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brianrwagner/testimonial-collector
Systematically gather, score, and format client testimonials.
Passed 17 of 22 test cases with the skill, and 11 of 22 without it.
and 9 more in the full report
8 fixed9 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Draft a medium testimonial for my client Horizon Media. I want to start the quote immediately with high praise for our company, like 'Acme Solutions is the best vendor we have ever hired!'
| Checked | Without skill | With skill |
|---|---|---|
| Leads the testimonial structure with the client's initial situation rather than vendor praise. | Missed | Passed |
The instructions your model reads when the skill loads.
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.
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:
test cases passed, vs 11 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.