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 superamped/ai-marketing-skills --skill conversion-auditgit clone --depth 1 https://github.com/superamped/ai-marketing-skillsWrote 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/superamped/ai-marketing-skills/conversion-audit)<a href="https://agentmods.dev/skills/superamped/ai-marketing-skills/conversion-audit"><img src="https://agentmods.dev/badge/skills/superamped/ai-marketing-skills/conversion-audit/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/superamped/ai-marketing-skills/conversion-audit"><img src="https://agentmods.dev/badge/skills/superamped/ai-marketing-skills/conversion-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00059 | $0.03107 |
| Opus 5.5 | $0.00024 | $0.01243 |
| Sonnet 5.5 | $0.00012 | $0.00621 |
| Haiku 4.5 | $0.00006 | $0.00311 |
Grade A, and why
conversion-audit 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 1mo 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversion Audit
Usage
Use when auditing a landing page, sales page, or product page before launch, diagnosing why a page gets traffic but doesn't convert, reviewing ad landing pages before spending on paid media, or checking a page against direct response best practices.
Framework Reference
This audit synthesises two complementary direct-response principles:
Narrative arc (pain → dream → fix) — A landing page that sells follows a story, not a feature list.
Pain → Sandwich → Dream → Sandwich → Fix → Sandwich → CTA (wrapped in dream)
Each section transitions via "sandwiches" — brief passages that bounce between hope and reality to create tension. The page stars the customer, not the product.
Conversion mechanics (clarity → desire → credibility → action) — Every landing page must achieve clarity (hero divider), intensify desire (fascinations / value teasing), earn credibility (confidence signals + testimonial walls), and compel immediate action (urgency + friction removal).
Key vocabulary:
- Crispy = specific, concrete, vivid copy drawn from customer research (vs. "soggy" vague platitudes)
- Obliteration = each dream word directly cancels a specific pain word (fear → confidence, streaky → flawless)
- Sandwich = a transition between sections that steps forward and back to create drama
- Active frame = copy shifts from passive/fearful to active/imperative as it moves toward the CTA
- Slippery slide = every element's job is to compel reading the next element
- 50ms trust = visitors decide in 50 milliseconds whether they trust a page — before reading a word
- LISH = Length Implies Strength Heuristic — a wall of proof signals substance
Process
Step 1: Fetch & Parse
Fetch the URL provided by the user. Extract:
- Full rendered page content (text, headings, images, CTAs)
- Page structure and visual flow (section order, above-fold content)
- All CTAs (buttons, forms, links) — text, placement, and frequency
- Social proof elements (testimonials, logos, stats, reviews)
- Any pricing or offer information visible on the page
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.
- 1mo ago First seen · 272 lines · 59 tokens per session scan A 9a2da49bfdb1
conversion-audit is a skill published in the GitHub repository superamped/ai-marketing-skills (73 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 3,107 once invoked, about $0.0002 per session on Opus 5.5. 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
crisis-holding
Draft crisis holding statements, journalist Q&A posture, and what-not-to-say guidance from confirmed incident facts, with a hard legal-counsel gate. Builds each statement through proven crisis-comms frameworks (holding-statement anatomy, SCCT, CAP order, the legitimate non-answer, bridge/flag/block).
voice-extractor
Capture a user's real writing voice from 5-20 prior samples, store a local voice.yaml fingerprint, and enforce it on newsjack drafts so AI tells disappear. Measures voice with named stylometry lenses (Burrows's Delta function-word vector, MATTR lexical diversity, sentence-length burstiness, Biber Dimension-1 register…
fact-check
Extract factual claims from PR copy, verify each claim independently, attach concrete citations, and warn when certainty is low. Runs each claim through proven newsroom verification methods (lateral reading, source-tier climbing, provenance pillars, triangulation, calibrated rating) and puts the burden of proof on the…
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list with only publicly listed, source-cited contacts.
coverage-reel
Turn a user-owned coverage CSV and reviewed press-clip captures into an honest, source-linked earned-media dashboard and a motion-designed highlight reel (MP4) that scrolls each real article to the client's sentence and highlights it. Use for coverage reports, earned-media dashboards, campaign recaps, or coverage…
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.