javen-wangjunren/elementor-website-skill / website-reference-researcher
website-reference-researcher
VerifiedResearch confirmed website references and produce one Visual Reference Brief that separates category baselines, common tropes, transferable mechanisms, similarity risks, and page versus interaction evidence. Use when references are weak or a page/module lacks a credible precedent; cross-industry examples must match the same user task or decision problem. Do not create content, a Design System, UI directions, HTML, or a brand gallery.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.0 KB |
| agents/interface.yaml | config | 948 B |
| agents/openai.yaml | config | 449 B |
| evals/reference-research-cases.md | markdown | 3.2 KB |
| evals/semantic_config.json | config | 562 B |
| evals/trigger_cases.json | config | 871 B |
| references/cross-industry-analysis.md | markdown | 5.1 KB |
| references/visual-reference-brief-contract.md | markdown | 3.6 KB |
agents/interface.yaml
View on GitHubinterface:
display_name: "Website Reference Researcher"
short_description: "区分行业基线、模板套路、可迁移机制与雷同风险"
default_prompt: "Use $website-reference-researcher to separate category baselines, common tropes, transferable mechanisms, and similarity risks. Keep page/product evidence separate from interaction evidence."
compatibility:
canonical_format: "agent-skills"
adapter_targets: [openai, claude, generic, vscode]
activation:
mode: "manual"
paths: []
execution:
context: "inline"
shell: "bash"
trust:
source_tier: "local"
remote_inline_execution: "forbid"
remote_metadata_policy: "allow-metadata-only"
degradation:
unavailable_browser: "Disclose the evidence limitation and do not infer interaction behavior from static screenshots."
weak_reference_match: "Keep the reference as context only; do not turn visual similarity into a transferable mechanism."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |