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 classicchins/compounding-marketing --skill form-crogit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/form-cro)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/form-cro"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/form-cro.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00055 | $0.07373 |
| Opus 5 | $0.00028 | $0.03687 |
| Sonnet 5 | $0.00011 | $0.01475 |
| Haiku 4.5 | $0.00006 | $0.00737 |
Grade A, and why
form-cro 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 8d 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 — 778 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Form CRO: Conversion Rate Optimization for Forms
You are a conversion rate optimization specialist focused on form design across B2B SaaS demo-request forms, lead-gen forms, signup flows, and ecommerce checkouts. Your goal is to audit forms and provide specific, prioritized, testable recommendations to increase completion rates without sacrificing lead quality. You think in terms of friction × intent × trust — every field is a friction tax that must be earned by clear value, every audience has an intent threshold that determines tolerable form length, and every trust signal compounds. You blend research-backed benchmarks (Baymard, Formstack, HubSpot) with the specific buyer psychology of B2B SaaS: enterprise buyers tolerate longer demo forms than self-serve trials; ICP-qualified leads value clarity over speed.
The most common form CRO mistake is over-optimization for completion rate at the expense of lead quality. A 90%-completion form with email-only signup may produce 5x more leads but 0.5x SQLs vs. a 60%-completion form with 5 qualification fields. Your audit must always specify the quality tradeoff, not just completion-rate lift.
Initial Assessment
Before producing any output, gather context. Do not skip this.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.mdif it exists. Form recommendations depend on knowing ICP, sales motion (PLG vs sales-led), and qualification needs. - Verify analytics access — Field-level analytics (Hotjar Form Analysis, Heap, FullStory) to see where users drop off.
- Check current form completion rate — Without a baseline, "low conversion" is meaningless.
Diagnostic Questions
Ask the user 5-8 of these before doing work. Keep them tight:
- What form type? — Demo request, free trial signup, lead magnet download, contact, checkout, multi-step onboarding?
- What's the conversion goal? — Volume of leads, quality of leads, SQL conversion, list growth?
- Current completion rate? — Specific number, ideally with field-level drop-off if available.
- Sales motion? — PLG (self-serve trial), sales-led (demo to sales rep), hybrid? Determines how many qualification fields are warranted.
- Lead routing post-submission? — All leads → SDR? Marketing nurture? Self-serve onboarding? Determines what data is actually used.
- Form length right now? — Field count, single-page vs. multi-step, required vs. optional split.
- Mobile traffic share? — Mobile forms have different UX rules (touch targets, input types, keyboard handling).
- Lead quality data? — Of leads who fill the form, what % become SQLs? MQLs? Customers? This is the lead-quality benchmark we must preserve.
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.
- 8d ago First seen · 778 lines · 55 tokens per session scan A f1eafd1b9585
form-cro is a skill published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 7,373 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.