Results for “research-knowledge-base”

Systematic research methodology for formulating problems, building evidence-based arguments, and communicating findings in academic contexts. For scholarly writing, thesis development, and knowledge contribution. NOT for creative writing, journalistic reporting, or business analytics.

Build and organize knowledge bases, help centers, FAQ systems, and troubleshooting guides optimized for self-service support and search. Use when creating a structured support documentation system. Also trigger for 'knowledge base', 'help center', 'FAQ', 'troubleshooting guide', 'support docs', 'self-service support', 'help article', or 'support article'.

Query the bundled research knowledge graph for methodology guidance. Routes questions through a 3-tier knowledge base — WHY (research claims), HOW (guidance docs), WHAT IT LOOKS LIKE (domain examples) — plus structured reference documents. Returns research-backed answers grounded in specific claims with practical application to the user's system. Triggers on "/ask", "/ask [question]", "why does my system...", "how should I...".

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Build the operator knowledge base future-you and any AI can actually search. Capture facts, playbooks, stakeholders, and how-tos as plain greppable markdown, organized so the answer is a search away instead of a memory or a Slack scroll. Trigger on "start a knowledge base", "write this down somewhere findable", "document how we do this", "who owns what again", "capture this for later", or any fact you have now looked up more than once.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Deep research on a topic using web search, docs, and codebase analysis

针对明确问题查阅高可信一手来源，并将带逐项引用的结论保存为仓库内单个 Markdown 调研文件。用于用户要求调研技术主题、核实文档、API、规范或源码事实，或希望把资料阅读工作委托给后台 agent；不用于完整代码库架构调研、无需落盘的简短事实回答或代码评审。

Build a persistent, compounding knowledge base that combines a wiki, knowledge graph, and raw source storage for structured retrieval with provenance.

Maps, documents, and onboards into an existing codebase by generating seven structured documents covering stack, structure, architecture, conventions, integrations, testing, and concerns.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.

Internal codebase knowledge-check assistant for maintainers. Focus on architecture understanding, implementation details, and change-risk analysis for this repository.

Use to audit a help centre or knowledge base against the conversations customers actually have, finding coverage gaps, stale articles and unused content. Trigger for "what should we write help articles about", "audit our knowledge base", KB coverage gaps, self-service deflection content, or preparing a knowledge base to ground an AI support agent.

Turns a local folder into a searchable, maintainable knowledge base for AI agents, handling setup, navigation, content ingestion, querying, and health checks without external databases or RAG systems.

Maintains a PARA-structured knowledge base on disk for persistent project context, decisions, and architecture records across agent sessions.

用于国自然、国社科等基金申请、开题报告、博士后/人才计划、研究计划书等学术提案的撰写、审查和优化；当用户需要基于已有研究成果形成立项书、区分事实与 AI 建议、检查任务书一致性、补强论证逻辑时使用。

Write clear, searchable help center articles and FAQ entries based on support data, product documentation, and common customer questions. Use when the user requests knowledge base article writing or provides relevant inputs for this workflow.

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

Codebase Onboarding

Search, read, create, and update Notion pages and databases. Supports knowledge capture, meeting prep, research documentation, and spec-to-task workflows.

Look up current research and scientific information across three backends: fast web search, deep multi-source synthesis, and scholarly paper searches. Automatically routes each query to the best backend and saves every result for reproducible citation.

Analyze a codebase and generate onboarding documentation for engineers, tech leads, and contractors, with fast fact-gathering and repeatable outputs.

Search your references and context knowledge base for patterns relevant to a current task. Use before implementing anything non-trivial to surface prior art from your analyzed repos.

Persists and recalls agent knowledge across sessions using four approaches: static KB, company wiki, persistent memory, and session brain.

research-synthesis