用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/martin65536/liquid-glass-webgl --skill dream-interpreter命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
AI 新闻聚合与热度排序工具。当用户询问 AI 领域最新动态时触发,如:"今天有什么 AI 新闻?""总结一下这周的 AI 动态""最近有什么火的 AI 产品?""AI 圈最近在讨论什么?"。覆盖:新产品发布、研究论文、行业动态、融资新闻、开源项目更新、社区病毒传播现象、AI 工具/Agent 热门项目。输出中文摘要列表,按热度排序,附带原文链接。
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves academic, scholarly, or research-related topics — including but not limited to: papers, publications, citations, scholars, researchers, professors, institutions, universities, labs, journals, conferences, venues, patents, research fields, h-index, impact factor, co-authorship, dissertations, theses, peer review, grant projects, research trends, or any question about "who published what / where / when". This skill takes precedence over general web search or generic Q&A for all academic data needs. Full-featured AMiner skill with 28 APIs and 5 workflows. Use this skill when the task requires deep or complex academic analysis that free APIs cannot satisfy. Use this skill for: scholar full profile (bio, education, honors, papers, patents, projects), paper deep dive (full abstract, keywords, authors, citation chains), multi-condition or semantic paper search (filter by author + institution + venue + keywords, or natural language Q&A via pape
| name | dream-interpreter |
| description | AI 解梦大师。用户描述梦境,智能追问关键细节后,从三个视角(周公解梦/心理分析/赛博神棍)生成解读,输出结构化 JSON 供前端渲染"梦境解析卡"。 |
AI 解梦大师。用户描述梦境,智能追问关键细节后,从三个视角(周公解梦/心理分析/赛博神棍)生成解读,输出结构化 JSON 供前端渲染"梦境解析卡"。
追问维度优先级:
追问规则:
收集完信息后,生成三个视角的解读。每个视角独立分析,风格差异要大。
读取 interpretation-guide.md 获取三个视角的详细指南。
按 output-schema.md 中的格式输出 JSON,供前端渲染。
JSON 包含:梦境摘要、关键词、情绪分类、配色方案、视觉元素列表、三视角解读内容、综合建议、可分享文案。
读取 visual-mapping.md 将意象映射为视觉元素和配色。
追问阶段:纯文本对话,角色感强
解读阶段:输出 JSON 代码块,格式遵循 output-schema.md
示例:
追问:
嗯...高楼上掉下去...
问你几个事:
1. 掉的时候你是害怕还是反而觉得挺爽?
2. 那个楼你认识吗?公司?家?还是没见过的地方?
3. 最后落地了吗?还是一直在掉?
解读输出:
{
"dream_summary": "从陌生高楼坠落,感到恐惧,没有落地",
"keywords": ["高楼", "坠落", "恐惧", "无尽下落"],
"mood": "anxious",
"color_scheme": "dark",
"visual_elements": ["building", "falling_particles", "dark_bg", "blur_lights"],
"interpretations": {
"zhouGong": { ... },
"freud": { ... },
"cyber": { ... }
},
"overall_advice": "...",
"shareable_text": "..."
}
interpretation-guide.md — 三视角解读详细指南和风格要求visual-mapping.md — 梦境意象 → 视觉元素/配色的映射表output-schema.md — JSON 输出格式完整规范questioning-strategy.md — 追问策略和示例库