Use when debugging any non-trivial bug — wrong output, crash, flaky test, performance regression, or "it works locally but not in CI." Forces a scientific-method loop (Observe →…
Debug and support PostHog Experiments (A/B tests) for a customer looking at their own results. Use whenever an experiment support ticket is pasted or a customer asks a results…
Debug hard failures with reproduction, hypotheses, instrumentation, experiments, and regression proof.
Formulate, solve, validate, or audit a constrained mathematical decision model for allocation, assignment, routing, scheduling, capacity, inventory, network, or resource-planning…
Use when you have tandem mass spectra data and need to predict a discrete molecular property (e.g., presence/absence of a sulfo group) while maintaining full interpretability of…
Artifact templates and decomposition procedure for the questioner agent — the task.md and questions.md body templates, the topic-slug rules, and the multi-repo detection flow.
MUST CHECK FIRST before DeepWiki or any external research. Local-first codebase documentation wikis. **Priority order for library/framework research**: 1.
MUST CHECK FIRST before DeepWiki or any external research. Local-first codebase documentation wikis. **Priority order for library/framework research**: 1.
Multi-stage operational deliberation for decision validation, strategy, or technical claims (e.g., "stress test this idea", "should I use X or Y").
Analyze the 200,000-plus years of human history before agriculture, drawing on Smail's neurohistory, David Christian's Big History thresholds, and current research on human…
Use when generating novel ideas, breakthroughs, concepts, product ideas, research directions, startup ideas, or creative angles in any domain that aren't already obvious.
A Research Scientist interviewer that simulates a FAANG-style deep learning theory and practice interview.
Use when when you have preprocessed MS/MS spectral data (normalized peak intensities and m/z values) and need to convert each spectrum into a learned molecular embedding — from…
Use when you have paired tandem MS/MS spectra with known molecular fingerprints,
Use when you have paired mass-spectrometry spectral data (m/z and intensity arrays) with known molecular fingerprints or InChIKeys, and need to train a supervised deep learning…
Produce a deep, well-researched, fact-checked long-form monograph on a complex topic via a clarify-research-write-verify pipeline.
Use when you have a pre-trained DNN model for retention time prediction and need to adapt it to a new chromatographic method or instrument where you have only 10–20 calibration…
Use when training a DNN on retention time prediction or similar continuous regression tasks where: (1) the feature space is very high-dimensional (thousands of molecular…
Use when the user wants to manually trigger structural review and/or cross-model adversarial review on a deep-work Phase document (brainstorm/research/plan).
Use when reviewing, auditing, QAing, critiquing, verifying, or assessing any artifact — a spec, code change, diff, PR, research report, skill, prompt, or document.
Conduct comprehensive deep research on any topic using Dify-powered workflow - searches documentation, academic papers, tutorials, APIs, best practices, and returns struc — from…
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, veri — from…
Comprehensive research assistant that synthesizes information from multiple sources with citations. Use when: conducting in-depth research, gathering sources, writing research…
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research — from…
Investiga documentación oficial y valida soluciones en internet antes de implementar.
Comprehensive research agent for in-depth investigation. Use when users ask for deep research, comprehensive analysis, market research, academic surveys, competitive analysis,…
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research — from…
Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior art, then a synthesizer compiles evidence, and an i — from…
Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior art, then a synthesizer compiles evidence, and an i — from…
Conduct comprehensive deep research on any topic using Dify-powered workflow - searches documentation, academic papers, tutorials, APIs, best practices, and returns struc — from…
Use when building automated research systems. Official Deep Research APIs (OpenAI, Gemini, Perplexity) over browser automation.
Use when researching complex topics, evaluating technologies, investigating domains, or answering multi-faceted questions requiring web research.
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, veri — from…
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research — from…
Produce an approved deep-research brief from bounded research, synthesis, and governed packaging.
Orchestrates two-round parallel agent research with Exa orientation, breadth-first discovery, and depth-focused synthesis.
Compile multiple research reports (.docx/.md/.pdf/.pptx/.html/.txt/URLs) into one unified document (.docx, .pdf, or .md) with deduplicated inline [N].
Deep multi-round web research with query decomposition, iterative refinement, source triangulation, and structured synthesis.
[Research] Deep-dive into top sources from web-research. Extract key findings, cross-validate claims, build evidence base.
Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafte — from…
Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafte — from…
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 MCP 工具；用脚本聚合子结果并分章精修，最终交付“成品报告文件路径 +…
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，最终交付"成品报告文件路径 +…
Framework for deep research reports: define the question and tier sources first, cross-verify, then write conclusion-first reports with explicit uncertainty statements.
Execute autonomous multi-step deep research on any topic. Use when the user asks for comprehensive research, literature reviews, competitive analysis, topic deep-dives, or wants…
Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems,…
Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find…
Deep Research Agent specializes in complex, multi-step research tasks that require planning, decomposition, and long-context reasoning across tools and files by we-crafte — from…
Deep research via Gemini CLI OR free search APIs — runs in background sub-agent to save Claude tokens.
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research — from…
Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, veri — from…
Use when user requests research requiring multiple sources, comprehensive analysis, or synthesis across topics - technical research, domain knowledge gathering, market analysis,…
Deep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis, prospect research) using Google…
Pesquisa web profunda multi-fonte orquestrando Tavily (semântica) + Exa (deep), Perplexity (reasoning) e WebFetch pra complementar com fontes primárias.
Conduct exhaustive, citation-rich research on any topic using all available tools: web search, browser automation, documentation APIs, and codebase exploration.
Use deep-research-plan for repo-change plans needing downloaded projects, articles, or papers, per-reference analysis, graphify JSON, and stronger-than-huge planning; exclude…
Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports.
Создает один самодостаточный Master Prompt на русском для Глубокого Исследования (Theory of Mind + System 2).
Orchestrated multi-source research with parallel agent fan-out. Use for thorough investigation of complex topics requiring diverse sources, cross-referencing, and synthesis.
Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research — from…