В каталоге 183 730 навыков в 14 категориях.
对书籍内容进行「六层读书法」系统研读并生成教研报告HTML。先看目录分批读，每1-2章暂停确认后再继续，最后综合。当用户说"读书""研读""六层读书法""深度阅读""教研报告"时触发。
Deeply analyze user-supplied articles, papers, reports, transcripts, URLs, or other long-form content using structural r...
Three-pass critical reading framework for systematic document analysis. Supports tech blogs, retrospectives, technical d...
Deep chain-of-thought analysis workflow using the reasoning tool. Covers when to use reasoning, how to provide context,...
Three-stage Chain of Thought (CoT) analyzer for /deep-reasoning page. Performs comprehensive analysis in 3 stages Direct...
4-layer recall procedure (durable → semantic → PostgreSQL → daily notes) before claiming "no context". Invoke when user...
Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angle...
Run deep, multi-hop research over org memory to answer a question or cross-reference an insight, with a cited synthesis....
Analyzes development sessions to extract patterns, preferences, and learnings. Use after significant work sessions to ca...
Comprehensive web research with synthesis and actionable insights
Use when the user wants a deep, multi-source, fact-checked web research report on a topic too broad for a single search....
Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior a...
Conduct comprehensive deep research on any topic using Dify-powered workflow - searches documentation, academic papers,...
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive la...
In-depth research on technical topics using web search, documentation, and codebase analysis. Use when asked to 'researc...
Use when researching complex topics, evaluating technologies, investigating domains, or answering multi-faceted question...
一套遞迴式資訊獲取流程，結合內建 todo 工具、研究日誌與三角論證，處理高度複雜研究任務。
使用firecrawl和exa MCPs进行多源深度研究。搜索网络、综合发现并交付带有来源引用的报告。适用于用户希望对任何主题进行有证据和引用的彻底研究时。
Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context...
Pesquisa aprofundada com metodologia estruturada
Orchestrates two-round parallel agent research with Exa orientation, breadth-first discovery, and depth-focused synthesi...
OpenAIまたはGoogle Gemini Deep Research APIを使用して深層リサーチを実行する統合スキル。Subcommandアーキテクチャ（start/status/poll/result/list）で長時間リサーチを安...
Deep research with NotebookLM + web search. Domain boost, source credibility scoring, and post-research artifact generat...
When you want multi-source, multi-step research on a topic — competitor research before a sales call, market research fo...
MUST read before the first search/fetch. Research a question across multiple sources and synthesize the findings into a...
Orchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured...
Researches a topic across many web sources and writes a sourced report. Use when the user says "research X", "deep dive...
Deep multi-round web research with query decomposition, iterative refinement, source triangulation, and structured synth...
[Research] Deep-dive into top sources from web-research. Extract key findings, cross-validate claims, build evidence bas...
ALWAYS load before attempting a broad web-grounded research report - "deep research this", "do a deep dive on X", "compr...
Run deep research on any topic using parallel AI agents
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full researc...
深度调研的多实例（多 Agent）编排工作流：把一个调研目标拆成可并行子目标，用 Codex CLI（`codex exec`）在默认 `workspace-write` 沙箱内运行子进程；联网与采集优先使用已安装的 skills，其次使用...
Produce por escrito el contexto estructurado previo a un work_plan (estado actual, gaps de conocimiento, alternativas)....
深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终...
Execute autonomous multi-step deep research on any topic. Use when the user asks for comprehensive research, literature...
Advanced multi-source research and comprehensive report generation. Use when the user requests in-depth analysis on a sp...
Deep multi-source research synthesis — web, academic, patent, and internal KB cross-referencing
This skill should be used when conducting comprehensive research on any topic using the OpenAI Deep Research API. It aut...
**深度网络研究**。不仅搜索链接，还会自动访问结果页面，阅读正文，并生成深度整合的综合报告。
Systematic multi-angle web research methodology.
Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.
Deep research and discovery before building something new. Explores local projects for reusable code, researches competi...
Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a to...
Deep research via Gemini CLI OR free search APIs — runs in background sub-agent to save Claude tokens.
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited repo...
Multi-directional deep research with sub-agents, scoring, source verification and cited synthesis. Use for comprehensive...
Deep research agent skill. Use when the user needs thorough, scientific, truth-seeking research on any topic -- investig...
Multi-source web research for non-trivial questions.
Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full researc...
Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should b...
Deep Research Agent for complex, multi-step research requiring web research, planning, and synthesis. Use instead of sin...
Use when a decision-relevant question needs multi-source search, claim-level citations, contradiction handling, uncertai...
Produce cited research reports from multiple web sources using firecrawl and exa MCP tools — plan sub-questions, search...
Use when user requests research requiring multiple sources, comprehensive analysis, or synthesis across topics - technic...
Conduct in-depth research across multiple sources and synthesize findings. Use when the user requests in-depth or compre...
Autonomous multi-step deep research engine implementing an iterative Think → Search → Extract → Synthesize → Stop loop....
Professional deep research report generation — multi-agent collaboration with parallel chapter writing, automatic latest...
Multi-step autonomous research methodology for deep investigation tasks with structured synthesis
Conduct exhaustive, citation-rich research on any topic using all available tools: web search, browser automation, docum...
Orchestrated multi-source research with parallel agent fan-out. Use for thorough investigation of complex topics requiri...
Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "expla...
Comprehensive research assistant that synthesizes information from multiple sources with citations. This skill should be...
Use this skill when the user's prompt requires (1) researching a topic across multiple sources, comparing options or alt...
Produce a decision-ready deep-research brief from bounded governed evidence and preserve every material source binding.
Deep research on any topic — broad parallel web searches, multi-source validation, confidence tracking, and a cited Mark...
Conduct in-depth, multi-step research on a given topic by decomposing queries, finding diverse sources, cross-referencin...
Use when deep-diving a product, tech, or company.
Runs a deep, survey-grade literature investigation on a research topic: freezes research questions, searches from multip...
GOD MODE deep research skill. Multi-phase autonomous research loop: query decomposition → multi-source crawling → claim...
Run a disciplined, multi-source research investigation for a high-stakes question or decision — fan-out web search acros...
Use when conducting deep research on any topic that benefits from multiple behavioral perspectives, evidence gathering,...
Deep web research skill using parallel subagents + chromux browser-explorer + Gemini. Spawns multiple WebSearch research...
Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape...
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs...
Research with scoped depth and counterevidence.
Systematic deep research methodology for complex tasks requiring comprehensive web, GitHub, community, and documentation...
Deep, iterative, multi-source research that explores a topic from multiple perspectives, detects contradictions, and pro...
Conduct multi-source web research, synthesize findings, and deliver cited reports with explicit source attribution. Use...
Run OpenAI deep research to analyze and synthesize web sources into a comprehensive report. Invoked with a research quer...
Structured deep research workflow with human-in-the-loop control. Use /research to generate research outline, /research-...
Conducts multi-perspective strategic research. Use when investigating complex topics, comparing competitors, or gatherin...
Automatically plan and execute deep, evidence-backed, multi-source research when the user says "derin/çok detaylı araştı...
Comprehensive research agent for in-depth investigation. Use when users ask for deep research, comprehensive analysis, m...
Expert guide for autonomous deep research, iterative web search, citation verification, evidence graph synthesis, and ha...
Use when building automated research systems. Official Deep Research APIs (OpenAI, Gemini, Perplexity) over browser auto...
Compile multiple research reports (.docx/.md/.pdf/.pptx/.html/.txt/URLs) into one unified document (.docx, .pdf, or .md)...
Use for deep research, literature reviews, technical due diligence, scientific explainers, market/technical reports, and...
Run evidence-backed research for Ottili agents: score sources 0-10 (authority/recency/corroboration, keep >=6), cite eve...
End-to-end orchestration of the deep research lifecycle across discovery, experimentation, and production gates.
Interactive prompt builder for creating high-quality deep research prompts through adaptive interviewing. Use when users...
Given outputs from 5 research sub-agents (time-sliced or partitioned), validate and synthesize them into a coherent, cit...
This skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "research r...
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from m...
ทำ post-incident retrospective ลึก หา root cause ระดับ process และ action items
Use when asked for a thorough, deep, or multi-angle review of a branch, PR, or recent changes — or when a diff touches e...