sharaf/landing-page-audit
Use when the user wants a landing page audit, CRO review, marketing conversion review, copy audit, funnel alignment check, brand positioning critique, technical performance marketing audit, or prioritized issue report for a landing page, pricing page, signup page, lead magnet, or product page. Runs evidence-first context gathering, parallel specialist analysis, synthesis, and severity-ranked recommendations.
100
100%
Does it follow best practices?
Impact
100%
1.81xAverage score across 3 eval scenarios
Passed
No known issues
README.md
Landing Page Audit
Use this Tessl skill to audit a landing page for conversion effectiveness, copy quality, brand positioning, technical performance, and funnel alignment.
The skill helps an agent build a factual context brief from repo and live-page evidence, run five specialist marketing lenses, and synthesize a narrative audit report with severity-ranked issues, benchmark-backed impact, concrete fixes, and specific strengths to preserve.
When to Use
- Landing page audits and CRO reviews
- Marketing conversion reviews for pricing, signup, lead magnet, or product pages
- Copy, CTA, messaging hierarchy, and objection-handling audits
- Brand positioning, differentiation, social proof, and trust signal critiques
- Technical marketing reviews for performance, tracking, mobile readiness, and SEO/social metadata
- Funnel alignment checks for cold, warm, or hot traffic
Install
tessl install sharaf/landing-page-auditOrganization
| Path | Purpose |
|---|---|
skills/landing-page-audit/SKILL.md | Main workflow, triage, severity scale, and output contracts |
skills/landing-page-audit/references/context-gathering.md | Context brief, live page fetch, repo scan, and fallback rules |
skills/landing-page-audit/references/specialist-agents.md | Copy, CRO, brand, technical, and funnel specialist checklists |
skills/landing-page-audit/references/synthesis-report.md | Final report structure and synthesis rules |
skills/landing-page-audit/references/guardrails-decision-logic.md | Guardrails, page-type logic, funnel logic, and success criteria |
tile.json | Tessl manifest and registry summary |
README.md | Registry-facing overview |
Output Shape
Default output is a landing page audit report with:
- Executive summary
- Detailed analysis by specialist lens
- Prioritized issue list sorted by severity
- Specific "What's Working Well" section
- Evidence gaps and assumptions
Each finding includes evidence, why it matters, suggested fix, and severity.
Eval Results
Tested on May 22, 2026 across three scenarios:
| Scenario | Baseline | Sonnet | Opus | Haiku |
|---|---|---|---|---|
| Source-code-only full audit | 49% | 100% | 100% | 100% |
| Pricing page with ad cohesion | 73% | 100% | 97% | 85% |
| Webinar lead magnet audit | 67% | 100% | 100% | 88% |
| Average | 63% | 100% | 99% | 91% |
Activation: 3/3 scenarios fired tessl__landing-page-audit.
Haiku showed model-tier variance on exact pricing-stage and CTA-label anchors. Sonnet is the recommended eval target; Opus also cleared the cross-model threshold.