vivy-yi

刑事判决书生成——接收案件事实描述，调用8个原子能力，生成格式规范、论证严密的完整刑事判决书。 适用情形：用户要求"起草判决书"/"生成裁判文书"/"根据案卷写文书"。 核心流程：事实提取→概念理解→争议识别→法条检索→案例检索→演绎推理→格式适用→术语规范。 注意：本skill是刑事一审判决书专用模板，GCL不涉及实际司法文书输出，此skill仅作框架参考。

法律文书格式适用——起草格式规范的民事/刑事判决书，或识别文书类型并套用对应格式。 适用情形：起草判决书/生成裁判文书/写民事判决书/写刑事判决书。 核心：识别民事vs刑事→按七段式顺序起草→在需要处调用对应原子技能。 这是GCL各场景的文书输出层，与judgment-document-generation互补（后者专注刑事+8步流程，前者覆盖民刑+分段落格式规范）。

法律文书摘要——对判决书、裁定书、调解书、仲裁裁决书、行政处罚决定书进行结构化摘要。 适用情形：用户要求做摘要/提炼要点/生成裁判要旨/提取案件信息。 核心：六要素框架（案件信息+事实背景+争议焦点+法律依据+结论结果+说理过程），忠实原文，区分文书类型。 禁用：不得添加原文未载明的事实/观点/结论，不得出现主观评价性措辞。

中国法律域分类体系。将法律问题归类到正确的业务域（投资/金融/数据/劳动/合同/知识产权等），触发正确的scene skill。触发词：法律领域、法律分类、归类、属于什么法域。

多源文档归纳——对多份相关文档（判决书/合同/法规/学术论文）进行交叉分析，提取共性、识别冲突、生成综合结论。 适用情形：用户提供多份判决书要求总结类案裁判要旨/提供多个合同文本要求归纳异同/提供多份法规要求梳理规范演变。 核心：四层次分析（单篇理解→共性提取→差异对比→洞见生成），不是简单压缩单篇文档。 注意：跨文档对比时保持中立，冲突点仅标识不做真伪判断。

工时计费与诉讼预算控制——管理律师工时、专家费用、调查费用，编制与监控诉讼预算。 适用情形：提到"工作小时"/"专家费用"/"办案成本"/"工时单"/"费用单"/"预算"/"成本控制"。 核心：四种计费模式（计时/固定/风险代理/混合）+三阶段预算管理（编制/执行/决算）。 与其他skill关系：调用 case-lifecycle-planning（获取时间节点）+ legal-document-formatting（出具正式账单）。

案件全周期规划——规划案件准备时间线、生成诉讼路线图和关键时间一览表。 适用情形：提到"案件准备"/"案件准备规划"/"案件准备时间线"/"排开庭"等关键词。 核心：为案件命名→上传传票/仲裁通知书→补充关键时间节点→生成本案诉讼路线图+关键时间一览表。 注意：不处理案件向律师分配，不处理一般性编程任务。

案例检索——查找类似案例和相关判决，评估相似度，输出结构化检索报告。 适用情形：需要支撑法律论点/预判案件/撰写文书引用案例/了解司法实践趋势。 核心价值：GCL各场景的references/查询路径.md目前多为占位符，本skill提供完整方法论。 使用注意：本skill产出每一个案例都必须来自真实检索，严禁凭记忆生成。

Use when processing audio for Xiaohongshu content, editing voiceovers, improving sound quality, creating podcasts, or producing audio-based posts

Use when designing visual layout for Xiaohongshu carousel content, organizing information on images, creating easy-to-read text overlays, or structuring multi-slide content for maximum engagement and readability

Use when planning Xiaohongshu content calendar, running out of content ideas, needing systematic approach to content creation, or wanting to align content with account goals

内容作品集管理 - 系统化整理、展示和优化你的内容资产

Use when repurposing Xiaohongshu content, recycling existing posts, adapting content for different formats, maximizing content value, or creating content variations from core material

内容规模化生产 - 从单打独斗到系统化内容工厂的高效方法论

Use when writing Xiaohongshu post content body, creating engaging captions, developing brand voice, or writing product descriptions and recommendations

Use when designing Xiaohongshu post thumbnails or first images, creating eye-catching cover images, improving click-through rates, or A/B testing cover designs

Enrich skills.json with additional metadata (category, tags, license, language, last_updated). Use when: (1) adding new metadata fields to skills.json, (2) categorizing uncatégorized skills, (3) enriching repo metadata. Triggers on: "enrich metadata", "add tags", "categorize skills", "metadata enrichment", "add categories". NOT for: updating star counts (use star-updater), or discovering new skills (use trending-crawler).

Main orchestrator for the awesome-skills repository maintenance system. Use when: (1) performing any maintenance task on the awesome-skills repo, (2) updating skills.json, (3) collecting content, (4) running scheduled maintenance, (5) asking about the maintenance system. Triggers on: "awesome skills maintenance", "maintain awesome skills", "run maintenance", "skills system", "awesome skills 维护", "run all maintenance", "check skills health". This is the entry point skill that delegates to sub-skills based on the task type. The sub-skills are: star-updater, trending-crawler, link-doctor, metadata-enricher, blog-collector, paper-collector, self-maintainer.

Collect AI Agent Skills blog articles from WeChat, Zhihu, Medium and other platforms into the awesome-skills repository. Use when: (1) adding new blog articles to blogs/ directory, (2) collecting skill-related articles, (3) expanding the knowledge base. Triggers on: "collect blog", "add article", "scrape article", "blog collector", "collect article". The collected article goes into blogs/YYYY-MM-DD-article-slug.md with images in blogs/images/.

Detect and repair broken links in the awesome-skills repository. Use when: (1) validating repository links, (2) fixing 404 errors, (3) checking link health. Triggers on: "fix links", "broken links", "link check", "validate links", "link doctor", "link health". NOT for: checking a single URL manually (just use curl), or updating star counts.

Collect academic papers related to AI Agent Skills into the awesome-skills papers/ directory. Use when: (1) adding new papers to papers/ directory, (2) collecting academic papers on Skills/Agent frameworks, (3) expanding research section. Triggers on: "collect paper", "add paper", "paper collector", "research paper", "arxiv paper".

Self-maintaining skill that updates, improves, and audits the awesome-skills maintenance skill system. Use when: (1) updating skills to new patterns, (2) auditing skill health, (3) self-improvement. Triggers on: "self-maintain", "audit skills", "skill health", "improve skills", "skill maintenance", "maintain myself". This skill examines and updates the .skills/ directory itself.

Update GitHub star counts for all repositories in skills.json. Use when: (1) scheduled star update task fires, (2) manually refreshing star counts, (3) comparing star growth over time. Triggers on: "update stars", "refresh star counts", "sync stars", "star update". This skill updates ALL 337 repositories in skills.json using GitHub API with proper rate limiting. NOT for: updating a single repo (just use gh CLI manually), or checking stars for a new repo (use add-skill instead).

Discover new AI Agent Skills from GitHub Trending. Use when: (1) daily/weekly skill discovery task fires, (2) expanding the skills.json collection, (3) finding new skill repositories. Triggers on: "discover skills", "find new skills", "crawl trending", " trending skills", "new skills discovery". NOT for: adding a specific known skill (use add-skill instead), or updating stars (use star-updater).