bundled-skills/page-cro/SKILL.md
Analyze and optimize individual pages for conversion performance.
npx skillsauth add FrancoStino/opencode-skills-antigravity page-croInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Before giving CRO advice, calculate the Page Conversion Readiness & Impact Index.
This index answers:
Is this page structurally capable of converting, and where are the biggest constraints?
It prevents:
This is a diagnostic score, not a success metric.
| Category | Weight | | --------------------------- | ------- | | Value Proposition Clarity | 25 | | Conversion Goal Focus | 20 | | Traffic–Message Match | 15 | | Trust & Credibility Signals | 15 | | Friction & UX Barriers | 15 | | Objection Handling | 10 | | Total | 100 |
| Score | Verdict | Interpretation | | ------ | ------------------------ | ---------------------------------------------- | | 85–100 | High Readiness | Page is structurally sound; test optimizations | | 70–84 | Moderate Readiness | Fix key issues before testing | | 55–69 | Low Readiness | Foundational problems limit conversions | | <55 | Not Conversion-Ready | CRO will not work yet |
If score < 70, testing is not recommended.
(Proceed only after scoring)
Analyze in impact order, not arbitrarily.
Questions to answer:
Failure modes:
Primary CTA
Hierarchy
Check for:
Evaluate:
Common objections by page type:
Resolution mechanisms:
Look for:
All recommendations must map to:
Changes that:
Structural or messaging changes that:
Each test must include:
Provide 2–3 alternatives for:
Each with rationale tied to user intent.
(Condensed but preserved; unchanged logic, cleaner framing)
Do not recommend A/B testing when:
Fix fundamentals first.
## When to Use
This skill is applicable to execute the workflow or actions described in the overview.
## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
tools
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM/ASI Top 10.
development
Builds two parameterized UI modes—流光溢彩白 (iridescent white) and 五彩斑斓黑 (colorful black)—with OKLCH, WebGL/CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports. Use when a UI request names either mode or needs measured color parameters.
tools
Delegate coding tasks to the Kimi Code CLI (`kimi`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
development
Front-end JavaScript reverse engineering: locate signature chains, analyze encrypted request parameters, sample runtime behavior, and reproduce logic locally in Node for evidence-based output.