Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mattgierhart/PRD-driven-context-engineering --skill prd-v10-testimonial-collectorgit clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-testimonial-collector)<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-testimonial-collector"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-testimonial-collector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mattgierhart/prd-driven-context-engineering/prd-v10-testimonial-collector"><img src="https://agentmods.dev/badge/skills/mattgierhart/prd-driven-context-engineering/prd-v10-testimonial-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 199 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.02628 |
| Opus 5 | $0.00056 | $0.01314 |
| Sonnet 5 | $0.00022 | $0.00526 |
| Haiku 4.5 | $0.00011 | $0.00263 |
Grade A, and why
prd-v10-testimonial-collector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
| Mode | What this skill produces |
|---|---|
| quick | One trigger (e.g., NPS promoters) + collection email + 5–10 testimonials processed |
| standard | 3 triggers (NPS, milestone, post-purchase) + processing workflow + consent management + per-placement formatting |
| deep | 5+ 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
- 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
- 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
- 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.)
- 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
- Measure placement performance [standard+] — Some testimonials convert; some don't. Track per-placement conversion to identify which quotes earn their spot.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 237 lines · 112 tokens per session scan A c8bb8dcfca69
prd-v10-testimonial-collector is a skill published in the GitHub repository mattgierhart/PRD-driven-context-engineering (182 stars, last pushed 10d ago), licensed MIT. It adds 112 tokens to every session and 2,628 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…