← ClaudeAtlas

lp-insightslisted

Generate hypothesis-driven landing-page feedback with simulated personas.
re-sianturi/lp-insights · ★ 0 · AI & Automation · score 66
Install: claude install-skill re-sianturi/lp-insights
# Landing Page Insights (OpenClaw Adapter) OpenClaw project skill adapter for landing page persona analysis. ## Overview Adapts the LP Insights methodology to the OpenClaw skill schema format. ## Usage `/lp-insights <url> [traffic_source] [group_persona]` ## Core Loading & Security Procedure Before starting the analysis, the agent must perform the following: 1. Load URL restriction lists and prompt injection rules from `core/SECURITY.md`. 2. Load and follow the execution rules in `core/WORKFLOW.md`. 3. Load the persona groups from `core/personas/_registry.md` and prompts from `core/prompts/persona-analysis.md`. 4. Validate outputs using schemas under `core/schemas/`. ## Runtime Policy & Tool Availability The availability of browser tools and subagent execution is determined by the system's runtime security policy. The agent must check the runtime environment capabilities: - **Capability Fallback:** If browser automation tools are unavailable, fallback to retrieving page source or text via standard text fetch tools. If subagents are unavailable, run simulation loops sequentially in the same execution context. - **Tools:** Use standard system tools, never invent tool names. ## Methodology & Disclaimer - Output declares `evidence_type` as `synthetic_hypothesis` for all analytics. - Findings report exact count of affected personas, never claiming empirical conversion metrics or observed user behavior.