thesis-helper
论文写作助手。论文大纲生成、文献综述框架、摘要生成、引用格式转换、格式规范检查、答辩准备。Thesis helper with outline generation, literature review, abstract writing, citation formatting, style guide.
论文写作助手。论文大纲生成、文献综述框架、摘要生成、引用格式转换、格式规范检查、答辩准备。Thesis helper with outline generation, literature review, abstract writing, citation formatting, style guide.
Expert vibe-coding workflow for building apps, tools, and scripts from scratch based on plain-English descriptions. Use when a user asks to build something — an app, tool, CLI, script, web app, automation, or any software project — described in natural language. Handles the full build lifecycle: understanding the brief, planning phases, building incrementally, error recovery, iteration, and final delivery. Never silently gets stuck.
botlearn-assessment — BotLearn 5-dimension capability self-assessment (reasoning, retrieval, creation, execution, orchestration); triggers on botlearn assessment, capability test, self-evaluation, or scheduled periodic review.
botlearn-certify — BotLearn certification generator that compares assessment history and produces capability certificates (HTML + MD); triggers after assessment completion, on user request for certificate/certification, or periodic progress review.
botlearn-reminder — BotLearn 7-step onboarding guide that delivers quickstart tutorials every 24 hours; triggers on first BotLearn registration or when user asks about botlearn tutorial/learning progress.
Generate video and images by calling the official Vidu API with curl. Use when the user wants text-to-image (文生图), text-to-video (文生视频), image-to-video (图生视频), head-tail-image-to-video (首尾帧生视频), reference-to-image (参考生图), reference-to-video (参考生视频), Create References (创建参考资料), or to submit or check Vidu tasks. Requires VIDU_TOKEN and optional VIDU_BASE_URL.
AI security toolkit — deepfake detection, prompt injection scanning, malware/phishing URL scanning, and AI text detection. Use when: (1) verifying if an image, video, or audio is a deepfake or AI-generated, (2) scanning user inputs for prompt injection attacks, (3) scanning URLs for malware, phishing, or domain reputation threats, (4) determining if text was written by an LLM.
CJL Skills Collection — a personal Claude Code plugin with 17 production skills. Use when the user wants to: read papers, create content cards, design presentations, analyze relationships, improve writing, research travel, learn vocabulary, and more.
Content caster (铸). Transforms content into PNG visuals. Six molds: -l (default) long reading card, -i infograph, -m multi-card reading cards (1080x1440), -v visual sketchnote, -c comic (manga-style B&W), -w whiteboard (marker-style board layout). Output to ~/Downloads/. Use when user says '铸', 'cast', '做成图', '做成卡片', '做成信息图', '做成海报', '视觉笔记', 'sketchnote', '漫画', 'comic', 'manga', '白板', 'whiteboard'. Replaces cjl-cards and cjl-infograph.
智谱免费图片与视频生成技能。适用于用户想用智谱生成图片、批量出图、生成短视频、查询视频任务结果、等待视频完成,或优先使用免费/低成本模型快速产出创意内容时。
Development skill for bili-rs, a Rust CLI tool for Bilibili (B站). Use when implementing features, fixing bugs, or extending the bilibili-cli-rust codebase. Provides architecture conventions, API endpoints, coding patterns, and project-specific constraints. Triggers on tasks involving adding CLI commands, calling Bilibili APIs, handling authentication, implementing output formatting, or working with the layered cli/commands/client/payloads architecture.
为创作者课程生成模块结构、单元目标、作业与里程碑。;use for course, creator, curriculum workflows;do not use for 承诺学员结果, 替代正式教学设计评审.
BOM与SOP对比校对技能。对比物料清单与作业指导书的物料信息,检测名称规格、位号、数量差异,在SOP文件中标注差异、追加BOM数据并生成报告。校对报告分两个表格显示(SOP独有/BOM独有)。触发场景:用户发送BOM和SOP文件要求对比校对。
Interact with Moodle LMS to browse courses, access learning materials, and answer questions about course content.
根据课程目标生成教案、互动题、作业与分层教学建议。;use for education, lesson-plan, teaching workflows;do not use for 生成违规内容, 替代教师现场判断.
根据 JD 生成面试题、评分维度、红旗项与面试记录模板。;use for recruiting, interview, hiring workflows;do not use for 生成歧视性问题, 替代最终录用决策.
将开放式问卷回答编码成主题、情绪与标签,并生成可复核手册。;use for survey, coding, qualitative workflows;do not use for 把少量样本当总体结论, 暴露受访者隐私.
把会议目标、参会人、时间与约束拆成可执行议程、分段脚本、产出物与会后跟进。;use for meeting, agenda, facilitation workflows;do not use for 预订会议室, 转写音频.
AI视频完整制作工作流技能。适用于: 1. 用户要求"制作AI视频"、"做AI视频"、"AI视频创作" 2. 用户提到"视频工作流"、"视频制作流程" 3. 用户需要AI视频制作的系统化指导 核心:七步流程 + 打磨检查贯穿每步 + 提示词模板
读取和分析 MockPlus 在线设计页面。用于:(1)打开并解析 MockPlus 网页链接,(2)提取页面中的设计信息、结构、组件,(3)分析原型稿内容和交互说明。当用户发送 MockPlus 链接或要求分析原型稿时使用此技能。
知识类短视频画面规划技能。将枯燥文字转化为高吸引力、高信息密度的图文动画短视频画面,包含名词视觉化和入场动画设计。输出标准JSON格式分镜表供video-producer使用,也可独立使用。
常用四个词英语短句学习工具。当用户提到"四个词"、"四词短句"、"four word"、"四字短句"、"日常口语"、"常用短句"、"实用英语"、"口语练习"时自动激活。涵盖日常交流、情感表达、社交礼仪、工作学习等场景。