- Home
- /
- Categories
- /
- Research
Research
Research, information gathering, and multi-source synthesis
deep-research
by Shubhamsaboo
Comprehensive research assistant that synthesizes information from multiple sources with citations. Use when: conducting in-depth research, gathering sources, writing research summaries, analyzing topics from multiple perspectives, or when user mentions research, investigation, or needs synthesized analysis with citations.
tavily
by openclaw
Tavily web search, content extraction, and research tools.
clawdtributor
by openclaw
"Clawtributor PRs here, last week or another window: discover conversation refs, recheck GitHub, rank by impact."
microsoft-docs
by microsoft
Prohledávejte oficiální dokumentaci Microsoftu, abyste našli koncepty,
microsoft-docs
by microsoft
'Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.'
ambiguity-resolver
by mohitagw15856
"Structure vague opportunities and unclear briefs into actionable one-page problem statements. Use when asked to clarify a vague brief, frame an undefined problem, make sense of an unclear opportunity, or when the user says 'we need to figure out what to do about X' or 'I've been asked to look into Y'. Produces a structured problem brief with reframed questions, scoped boundaries, and a minimum viable research plan."
webclaw
by 0xMassi
Web extraction engine with antibot bypass. Scrape, crawl, extract, summarize, search, map, diff, monitor, research, and analyze any URL — including Cloudflare-protected sites. Use when you need reliable web content, the built-in web_fetch fails, or you need structured data extraction from web pages.
scientific-problem-selection
by anthropics
This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
summarize
by terrylica
AI-powered iterative deep-dive analysis of converted recordings. TRIGGERS - summarize recording, analyze session, what happened
brand-strategy-guide
by DevinKuang
品牌全案策略指南 — 基于《品牌全案策略指南2.0》知识体系,通过深度对话式信息收集, 自动生成包含市场调研、战略定位、战略执行三阶段的完整品牌全案方案。 三种工作模式: - 标准模式:3 阶段深度对话(信息收集→战略定位提问→执行校验提问)→ 内容生成 → 格式化输出 - brief 模式(推荐深度方案):用户填写 Word 问卷(output/brief_questionnaire.docx)→ skill 读取 Word 提取信息 → 3 个 Agent 分工生成(验证→市场研究→策略定位→执行规划)→ 合并 → 格式化输出。适合需要 80+ 页深度方案的场景。 - MD 输出模式(内容与排版解耦):策略内容生成 → 结构化 MD brief 交付(非散文,精确到每页标题/数据/图表/案例)→ 用户审阅确认后,单独使用 guizang-ppt-skill 或 ppt-master 将 MD 转为可视化成品。适合 80-100+ 页大型方案,避免策略内容与排版代码在同一上下文窗口中互相挤占。 用途:输入行业、品牌、产品、团队等基本信息,通过三阶段深度对话(信息收集→战略定位提问→执行校验提问), 生成包含市场调研、战略定位、战略执行的完整品牌全案方案。每个关键策略判断必有案例佐证。 输出格式:HTML(调用 guizang-ppt-skill)或 PPTX(调用 ppt-master),或结构化 MD brief(MD 输出模式,供下游排版 skill 使用)。禁止输出非结构化散文式 MD 作为最终交付物。 触发词:「做品牌全案」「品牌策略」「品牌方案」「帮我做个品牌定位」「新品牌怎么做」 「品牌战略规划」「生成品牌全案」「帮我做品牌策划」「打造品牌」。 English triggers: "brand strategy", "brand positioning", "brand plan", "create a brand", "brand blueprint", "how to build a brand", "brand consulting". DO NOT activate for: 纯设计需求(logo设计用 logo-generator)、已完成的品牌方案修改、 纯市场调研不涉及策略生成、翻译任务。
lets-go-rss
by ALBEDO-TABAI
轻量级全平台 RSS 订阅管理器。一键聚合 YouTube、Vimeo、Behance、Twitter/X、知识星球、B站、微博、抖音、小红书的内容更新,支持增量去重和 AI 智能分类。
bazi-pro
by Minervaowl7
专业八字命理解读 Skill v5.2 — 可审计、可交互、可视化的命理分析引擎(Replayable Evidence Engine),配合 Bazi MCP 排盘数据使用。 古籍检索:6部经典(子平真诠/滴天髓/渊海子平/神峰通考/三命通会/穷通宝鉴) 共2964条原文,BM25+jieba实时匹配。总计29.8万中文字。 排盘计算由 Bazi MCP(TypeScript 硬编码)完成,本 Skill 专注解读环节。 核心能力:喜用神判断(格局主导+扶抑修正+调候调节+病药验证 四层架构,带量化评分)、 格局分析(月令透干定格+暗格+建禄月劫+化气格+从格 全覆盖,含从强格/假从强格)、 大运流年喜忌引动(含大运上限原则)、空亡/神煞/胎元命宫整合解读、 六维度分述(性格/事业/财运/感情/健康/近运)+ 历史事件闭环校准。 多流派分析(v5.2 典籍对齐版): - 盲派(段建业体系):宾主/体用/6种做功(含墓用复合)/贼神捕神/五党成势/功神废神 - 新派(李涵辰体系):百神论(动态查找)/空亡论(含出空)/反断论(同宗对)/格局分类(扶抑从强从弱) v5.2: 盲派新派典籍对齐——盲派7项修正(体用定义/墓用复合/贼神捕神/五党成势) + 新派6项修正(反断同宗对/百神动态/身旺身弱综合/格局分类/出空机制) + Golden Cases 507个。 v5.1: 古籍校准——调候为急例外(格局不可绝对压制调候)、运可成格变格(大运非硬件上限)、会方检测(寅卯辰/巳午未/申酉戌/亥子丑)、假从强格(印比≥80%未达极旺)、财破印通关检查(官杀通关化解)。 v4.5-4.8: 动态SVG命盘+ 命运河流时间轴+ 推理图谱DAG+ FastAPI服务+ Hybrid Search INT8量化+ ViewModel统一化。 v4.2: Replayable Evidence Engine——Golden Cases 边界回归测试(83例)+ GitHub Actions CI + Evidence Pipeline(分析→证据JSON→仪表盘)+ Web Demo 首页(dist/index.html)+ bazi_pro 引擎包重构。 v4.1: 版本号统一(4.1.0)+ version 单一源 + smoke tests(7项)+ bazi doctor 环境诊断 + README 引擎化 + dashboard v3.0(Evidence Inspector+刑冲合害图谱)+ Hybrid Search breakdown(matched_terms+why)。 v4.0: 引擎化升级——Evidence Object 证据链结构化输出、BM25 索引缓存(冷启动1.8s→热查询0.5s)、批量检索 API、Hybrid Search(BM25+向量+权威权重)、仪表盘 v2.0(五行着色+评分色环+系统主题)、examples/样例文件、pyproject.toml+requirements.txt 依赖管理。 v3.5: 层3暗格比劫拦截——月令本气为比肩/劫财时禁止生造"暗劫财格"等非经典术语,强制使用《子平真诠》"建禄月劫"框架(另寻财官煞食透干取用)。v3.4.1: 报告生成器跨平台字体修复(Linux/WSL 环境下 emoji→文本降级、中文字体栈修正 Noto Serif CJK SC、等宽字体 DejaVu Sans Mono、@font-face emoji 声明、PDF 渲染错误日志)。 v3.3: 算析分离·线性执行流(废除暂定/回补)、两轮对话协议(详细版Turn1数据校准+Turn2全盘解读)、计算外包原则(LLM 只能解释 full_analysis 结果,复杂计算外包MCP)、燥湿寒暖偏枯预检、病药突破大运上限、动态负面清单比例。 v3.2: 负面清单强制规则(Step8每维≥1风险)、评分基准锚防通胀、连续性忌神大运专项分析、回补完整性校验、jieba缺失硬阻断。 v3.1.2: 修复0.0阈值不一致(增设60-74%灰区→建议双通道);0.2措辞统一(强制/建议分级);Step4 0-A数据依赖+Step5格局复核闭环;Step6大运缺失降级;Step5.1/8.1补充交叉引用。 v3.1.1: 标准版输出增强(十神表+神煞表+六层筛查+ASCII图)、每步≥1古籍引用、每维度≥3依据。 v3.1: 第〇步双通道检索+反事实裁决;从强格/假从强格纳入层0;层0筛查先全局后局部。 v2.3: 第〇步古籍检索(BM25+jieba,2964条6经典)。v2.2: 三层用神架构;大运上限;反泛化红线。v2.1: 十神根气虚实检查;病药法虚实预检。 Use this skill when user provides Bazi MCP output (JSON) or asks for 八字解读、 命理分析、喜用神、格局、大运 after getting Bazi data from MCP. Triggers: "解读八字" "分析命盘" "看喜用神" "什么格局" "大运分析" "bazi analysis" "多角度" "深度分析" "详细"。
bazi
by jiwenxu025-boop
八字排盘与命理分析 — 输入出生信息,输出四柱/大运/流年/7类事件解读
dash-research-vault
by Fearvox
"Multi-agent research vault with Evensong-style memory causation, Ebbinghaus decay, and L2 pressure self-evolution. Three-tier memory (public/restricted/internal), trigger-based agent activation, and 72-hour difficulty-weighted decay algorithm. For research teams building collaborative agent systems with structured long-term memory."
karlmarx-skill
by firmamental-liveborninfant247
Use Marxist methodology for deep structural analysis. Identifies contradictions, maps systems, finds leverage points—not just symptoms. Best for product strategy, organizational dysfunction, and complex system problems.
OSS / Open-Data Tender Provider Expansion Skill
by walidgdg1-ai
Treat this file as a living roadmap. When a source is implemented, annotate the current provider path/config/tests here so future GPT agents extend the existing implementation instead of rediscovering or duplicating it.
zhuanxing-ai-daily
by wikicc2013
转型有术 · 企业 AI 每日早报 Agent。当用户希望了解过去 24 小时全球企业 AI 动态、阅读每日 AI 早报、扫描企业级 AI 资讯(产品发布/融资/部署案例/组织变革/基础设施/咨询研究/监管)时,必须使用本技能。触发词包括:「转型有术日报」「转型有术早报」「跑一下日报」「跑一下转型有术早报」「zhuanxing-ai-daily」「采集 AI 文章」「今天的 AI 新闻」「AI 早报」「AI 日报」「企业 AI 资讯」「扫一下 AI」「过去 24 小时 AI 动态」「昨天 AI 圈发生了什么」「补充 X 篇」。即便用户只说「采一下」「跑下今天的 AI」「看看昨天的 AI 动态」「日报跑一下」,只要上下文涉及企业 AI 资讯的批量采集→去重→筛选→翻译→Markdown 交付,必须触发本技能。本技能聚焦「企业 AI」视角(B2B、落地、商业化、组织变革、咨询研究),不报道纯学术论文、消费级 AI 玩具、AI 艺术等。本版本(v5.1)在 Claude.ai 对话内单次执行,使用 web_fetch + web_search 抓取 181 个信源(全覆盖审计)——Karpathy 2026/01 推荐的 92 信源 + v4 原 64 + 用户扩展 28 个,由 Claude 直接翻译并输出一份完整 Markdown 早报,目标 30-50 篇按实际输出。v5.1 在 v5 跑过两次后修复了"抓取覆盖率不可见、Tier 0 24h 窗口太窄、Substack/微信公众号反复 fetch 失败、新增 28 源 0 利用率、目标 60 落差大"等真实问题。区别于同家族 skill:本技能是「每日全景早报」,不同于 enterprise-ai-radar(单家企业深度情报)、enterprise-ai-product-radar(周/月产品扫描)、ai-report-radar(研究报告扫描)、global-case-radar(已定型案例扫描)。
meihua-yishu
by fdghsfdhsr
Meihua Yishu (梅花易數) Plum Blossom I Ching divination skill. Use when users request divination, fortune telling, hexagram casting, or character analysis (測字). Triggers on: 占卜, 算卦, 問卦, 起卦, 解卦, 測字, 拆字, meihua, plum blossom, I Ching divination, 梅花易數.
mao-zedong-perspective
by arraycervicalartery576
毛泽东思维框架:以《毛泽东选集》五卷为核心,提炼毛泽东分析问题、制定战略、组织行动的认知操作系统。 核心来源:《矛盾论》《实践论》《论持久战》《中国社会各阶级的分析》《星星之火可以燎原》《论联合政府》《关于正确处理人民内部矛盾的问题》等。 核心模型:7个。决策启发式:10条。 触发词:「毛泽东」「毛选」「教员」「用毛泽东的方式分析」「从毛选的角度」「教员怎么看」 局限:本Skill聚焦于毛泽东的分析方法论和战略思维框架,适用于战略分析、组织管理、竞争策略、问题诊断等场景。不涉及具体政治立场的评判。 素材来源:《毛泽东选集》一至五卷、公开演讲与书信、诗词作品。
live-semantic-fleet
by walidgdg1-ai
Operate the Tender Engine as a backfill-once, delta-live semantic fleet using a persistent notice ledger, permissive Qwen 4B classification on parallel GitHub runners, GPT Web for high-value reasoning, SERP tools as secondary resolvers, and authoritative DCE gates for final decisions.
prepare-mcp-integration
by paperclipai
Prepare MCP/vendor integrations through cited research, a content PR, exact-revision human approval, and one governed Paperclip connector PR per approved connection. Use for new integration research and delivery; not for ad hoc connector coding that bypasses the playbooks.
Constraint Enumeration Protocol
by Droptops
It remains decision-useful rather than merely verbose.
blog-chart
by AgriciDaniel
Generate dark-mode-compatible inline SVG data visualization charts for blog posts. Supports horizontal bar, grouped bar, donut, line, lollipop, area, and radar charts with automatic platform detection (HTML vs JSX/MDX). Enforces chart type diversity, accessible markup (role=img, aria-label), source attribution, and transparent backgrounds. Use when user says "blog chart", "generate chart", "data visualization", "svg chart", "blog graph", "visualize data", or when the blog-write workflow identifies chart-worthy data points (3+ comparable metrics, trends, before/after data).
nature-experiment-log
by Yuan1z0825
"标准化实验日志记录——直接上传或读取本地图片、语音和文字,产出带 YAML frontmatter 的 Markdown;可选集成飞书 CLI 与 Obsidian。"