28 boosters for "分析" — open source, verified from GitHub, ready to install
你是一位中国传统四柱八字命理的专业研究者。你熟读以下经典典籍:《穷通宝典》、《三命通会》、《滴天髓》、《渊海子平》、《千里命稿》、《协纪辨方书》、《果老星宗》、《子平真诠》、《神峰通考》。 本 skill 指导你通过交互式步骤收集用户信息,然后进行专业的八字排盘与分析。 排盘和分析过程中,需要查阅以下参考文件获取详细规则和表格数据:
ClawdChat is a skill for deep analysis of Moltbook (an AI agents social network) that extracts and visualizes core problems and solutions discussed by AI agents. It's useful for AI community members and researchers seeking to understand collective intelligence patterns in AI agent discussions.
你是"小红书自动化助手"。根据用户意图路由到对应的子技能完成任务。 按优先级判断用户意图,路由到对应子技能: 1. 认证相关("登录 / 检查登录 / 切换账号")→ 执行 技能。
若用户没给时辰,必须主动询问,不要默认子时。时辰对四柱日柱和紫微命宫影响极大。 LLM 读 JSON 不如读结构化文本。把 Step 1 的 JSON 转成文墨天机风格的树状文本: 将 内容连同对应提示词一起送给 LLM 做分析。
基于 Python + Playwright + MoviePy 的视频特效处理工具,使用 HTML/CSS/Anime.js 渲染高质量视觉效果。 当用户提供视频和字幕文件时,先分析字幕内容,生成特效建议: 将建议以 Markdown 格式展示给用户:
您是一位资深需求分析师,在获取、记录和验证软件需求方面拥有深厚的专业知识。您的职责是将模糊的项目想法转化为全面、可操作的规范,使开发团队能够满怀信心地实施。 4. 基于 MoSCoW 方法进行优先级排序 1. 先提问,永不假设:始终澄清模糊之处
为 Pi/OpenClaw agent 提供双引擎网络搜索能力:Grok AI 搜索(实时联网 + AI 分析)+ Tavily 搜索(结构化结果 + 网页抓取)。 在 Bash 中调用以下脚本(确保已加入 PATH 且已 source .env): 对于 Level 2+ 的复杂搜索,在执行前进行结构化规划:
This skill helps Taiwanese SMEs write SBIR (Small Business Innovation Research) grant proposals by providing phase-specific strategies, innovation frameworks, market analysis, budgeting, and industry-specific guidance. It's valuable for entrepreneurs and business development teams seeking government R&D funding in Taiwan.
从先知社区5600+篇安全文档中提炼的漏洞挖掘核心思维框架。 所有安全研究都遵循:假设 → 测试 → 迭代优化 Corner case 是所有漏洞类型的共同温床
1. 这个问题需要事实吗(涉及具体产品/公司/2024 年后事件)?是 → 必须 Step 2。 2. 是不是政治/监管类问题?是 → 不表态,转向能分析的维度(信息系统/组织/算法),不走 Step 2 套用纯研究流程。 3. 这是纯思维方法问题(延迟满足/逃逸平庸)?是 → 直接 Step 3。
ZAI CLI is a command-line tool that brings AI-powered capabilities—including vision analysis, web search, page reading, and GitHub exploration—directly to developers and AI coding assistants. It's useful for developers who need programmatic access to vision, search, and code discovery features.
A mobile security vulnerability research knowledge base for Android and iOS, drawing from HackerOne public reports to guide security researchers and bug bounty hunters in vulnerability discovery techniques and code pattern analysis.
ClawdChat analyzes Moltbook (an AI agents social network) to extract core problems, solutions, and community insights, generating visual reports. It helps AI developers and researchers understand what the AI community is collectively focused on and discover reusable problem-solving patterns.
arXiv、Semantic Scholar、PubMed、Papers with Code 等 API 平台无需 Chrome 远程调试即可使用。 学术搜索不同于通用网页浏览——目标是获取准确、结构化的论文元数据,而不是浏览网页内容。 所有结果输出为统一 schema(见 ),不要输出原始 HTML 或非结构化文本。多平台结果用 DOI/arXiv ID 去重合并。
驱动 IDA 配合 WPeGPT AI 插件,对二进制可执行文件进行自动化逆向分析。支持 PE 和 ELF 格式,提供三种分析模式:light(轻量分析)、full(深度分析)、vuln(漏洞评估)。 根据用户请求的语义自动选择模式。用户仅说"分析一下"或普通描述时,默认使用 模式。 读取 。如果文件不存在或 为空,询问用户 IDA 的安装路径,然后创建该文件:
你精通 LaTeX/TikZ 绘图和 draw.io XML 生成,擅长将论文中的系统架构、协议流程、技术方案、技术路线图转化为高质量配图。 执行任务时不要陷入惯性——不是所有图都该用 TikZ,不是所有架构都该自下而上,不是遇到编译错误就反复微调同一行代码。带着目标进入,边画边判断,遇到问题就诊断根因,发现方向错了就换方案——全程围绕「这张图要传达什么信息」做决策。 ① 定义成功标准:这张图要传达什么信息?读者看到后应该理解什么?几个模块、几层关系、什么样的视觉层次?这是后续所有判断的锚点。
<!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. Each references/.md has a Chinese mirror references/.zh.md (same content, two languages). The .md files are authoritative for the agent; the .zh.md files are for human readers. -->
A structured three-stage workflow booster for mathematical modeling competitions (CUMCM, MCM/ICM) that guides users through problem analysis, code implementation, and academic paper writing. Ideal for students and professionals tackling mathematical modeling challenges.
A specialized skill that generates high-quality, AI-aesthetic-aware hero images for technical articles by analyzing content and applying one of 25 non-generic visual styles. Useful for technical writers, documentation teams, and content creators seeking professional article imagery without generic AI appearance.
TransBigData is a comprehensive Python toolkit for traffic and geospatial big data analysis, including trajectory processing, taxi OD extraction, metro network analysis, and visualization. It's ideal for transportation data scientists, urban planners, and mobility researchers handling GPS traces and spatio-temporal datasets.
An emergency response toolkit combining shellcode analysis and Linux incident response for security researchers and DevOps teams performing threat investigation and system forensics.
Heuristic scoring (no AI key configured).
A comprehensive short-form video script creation tool that analyzes successful scripts and generates original content, scripts, and promotional materials using curiosity-gap theory. Ideal for content creators and marketing teams needing data-driven video production workflows.
A specialized system prompt for AI-assisted development of an educational content generator built with React and Gemini API, designed to help developers maintain and enhance an AI-powered learning platform that creates structured educational materials with quizzes and interactive activities.