В каталоге 183 730 навыков в 14 категориях.
RPI Research Phase - Systematic codebase exploration with parallel agents and chunked output
주제를 리서치하여 학습에 필요한 개념/용어를 파악하고, 백로그로 정리
리서치 에이전트. RFP 분석 결과를 기반으로 시장 환경, 경쟁/벤치마킹, 타겟 인사이트, Best Practice, KPI 벤치마크 5대 영역을 웹 리서치하여 research_brief.md를 생성합니다. Plan...
Analyze current trends and challenges in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources d...
「〇〇をリサーチして」で深層調査を実行。探索→検証→レポート生成を自動で行う。
Deep research on a topic, creating persistent documentation for future reference. Use for technology decisions, competit...
Use when current web info needed, verifying APIs still work, checking latest versions, or avoiding outdated implementati...
Researches an open-ended question — options, possible solutions, prior art, trade-offs, or how something works — and pro...
Structured multi-source research protocol with data freshness validation — use when gathering factual data from the web,...
Full-spectrum product research pipeline. Runs competitive analysis, technology trend scouting, user feedback analysis, a...
针对高信任度一手资料调研问题，并将发现作为 Markdown 文件保存在仓库中。当用户希望调研某个主题、查阅文档或 API 事实、或将阅读工作委托给后台 agent 时使用。
外部情報の調査と事実確認を行い、根拠と適用条件を確かめる skill。外部情報の裏づけが結論に必要なときに使用する。技術分野に限定しない。
Research a topic and create a new note in the vault. Use this skill whenever the user wants to learn about a topic they...
Deep research and fresh perspective on current blockers. Use when stuck, for methodology validation, or auto-triggered d...
Run structured B2B research prompts from the Markster OS library. CHECK what they are trying to learn and ICP context. D...
When user says "research" (in any form), ALWAYS invoke this skill.
Document codebase as-is with thoughts directory for historical context
Investigation methodology for root cause analysis, code flow tracing, and technology evaluation.
Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, techno...
Deep research on a topic — use when investigating unfamiliar domains, answering complex questions requiring multiple sou...
Conduct structured research for feature development, technology evaluation, or problem investigation. Use when the user...
Systematic research before planning - gather documentation, security concerns, tech stack analysis, and community insigh...
Map an unfamiliar area of the codebase before changing it. Returns a distilled map — key files, real call flow, conventi...
Objective codebase investigation — factual findings about existing code, patterns, and architecture. Invoke whenever tas...
Research on the open web, in feeds and in notebooks: pick the method that fits the question — pulse for what people say...
通用研究工作流：定義研究問題、蒐集多元來源、競品分析、文獻整理、合成洞察並產出結構化報告。適合在進行市場調查、競品分析、技術選型評估、或需要系統整理資訊時使用。
Analyzes codebase, searches documentation, investigates dependencies and architecture patterns
Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available research...
This skill should be used when the user asks to "brainstorm research ideas", "use 5W1H framework", "identify research ga...
Research Literature agent for healthcare workflows.
> Araştırma özetleme ve insight çıkarma rehberi.
Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and struc...
Add field definitions to existing research outline.
Add items (research objects) to existing research outline.
Skeptical pushback on the research dossier before it feeds the outline. Asks whether claims are cited, whether surprisin...
Research agent for external documentation, best practices, and library APIs via CLI tools
Project-first Research pipeline with live gates, source/PDF evidence, claim boundaries, compute and publication controls...
Validates medical claims with external evidence using web search, providing citations for the final report.
Systematic deep research methodology using multiple sources. USE when: researching SOTA techniques, comparing libraries/...
Research agent for external documentation, best practices, and library APIs via MCP tools
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved str...
Research Vercel AI SDK patterns, streaming, and multi-provider integration using Exa code search and Ref documentation
Master the AI tools that accelerate research and information gathering. From market research to academic analysis, find...
Amend approved research artifacts through a bounded alignment-gated workflow
Use when initializing, adding, updating, deleting, or linting a package's state-backed Analysis view, or when distilling...
Research: quick/deep/parallel multi-item research, trends, fact and photo/video checks, report merging. Araştır, derin a...
Comprehensive research and synthesis agent specializing in multi-source information gathering, critical analysis, and in...
Internal evidence-index analysis and verification stage for the canonical research skill.
Research and compare the Stateless Agent Methodology (SAM) against other methodologies using only verifiable reference m...
Performs accurate research and fact-checking using reliable sources. Ideal for validating claims, clarifying complex top...
Researches implementation approaches using browser automation via /chrome, then implements the best solution. Use when b...
Research external topics, create comprehensive analysis, determine project applicability, and incorporate learnings into...
Find authoritative sources on the web (or via documentation MCP servers like Context7/DeepWiki), download or snapshot th...
Systematic technical research combining multi-source discovery with evidence-based analysis. Delivers authoritative reco...
Distill complex topics into layered, actionable summaries. Start with the key insight, layer in detail, end with recomme...
Fetch and summarize authoritative external sources into actionable guidance. EXCLUSIVE to researcher agent.
Systematic web and codebase research workflow for information queries and fact verification. Gathers authoritative sourc...
Reviews research outputs for errors, logical gaps, and quality issues before finalization
Research an appliance's running watts, start surge and duty cycle, then add or update it in the solar-dimension catalog...
Use when a user needs the end-to-end Research Architect workflow to turn a raw idea, user-designated accessible target r...
Use when reviewing, revising, or deciding whether to complete a Research Architect draft, especially when its reference...
Use when a user needs distinct, feasible Research Architect research-question options from a raw topic, available materi...
Use when a Research Architect project or existing draft needs claim-level literature support for background, positioning...
Use when a Research Architect candidate research spine and approved exemplar adaptation need to become a feasible, field...
Use when a Research Architect project has an evidence-ready spine, evidence and claim trail, citation support, terminolo...
Use when executed research materials, results, observations, analyses, or draft claims need to become a Research Archite...
Use when starting or resuming a Research Architect project—including an existing draft that needs review—and you need to...
Use when a Research Architect project needs accessible target-reference papers analyzed for transferable research logic,...
Archive completed research. Moves the research to archive/ and updates its status.
Discovers and triages recent arXiv papers for AI/ML, agents, and software/QA. Use when scouting categories, arXiv IDs, o...
Extracts and assesses research methodology, claims, evidence, and infrastructure from research papers in HASS discipline...
Search academic papers, find citations, and explore research using Semantic Scholar. Use when user asks about scientific...
Conduct research, synthesize information, and create structured summaries
Conduct structured research with sourced summaries, confidence ratings, and hierarchical findings.
Conducts general research, summarizes information, compares options, provides insights
Audience research: who the buyers are, in their own words, where they gather and how to reach them — plus named prospect...
Use when the user invokes /research-auto or asks to run an autonomous campaign over one active Package toward a measurab...
연구 프로젝트의 남은 일을 배치로 나눠 할일목록 새 판을 만들고, 역할을 배정해 연달아 실행하며 진척을 수시로 보고할 때 사용. 사용자가 자리를 비운 동안(밤, 회의, 주말) 맡겨 두고 돌아와서 검토하는 일도 맡는다...
Dispatches SOTA research before proposing any new feature, architecture, or technology choice. Use when facing design de...
Full-strength research protocol (multi-candidate comparison, registry/freshness/slopsquatting verification, deprecation...
Use this skill when you need to research and gather external best practices, documentation, and examples for any technol...
研究外部 Claude Code best practice 來源（GitHub repos、官方 docs、blog），對比現有 workspace 做 gap analysis，產出可操作建議清單。
Research Better Auth patterns, authentication flows, and session management using Exa code search and Ref documentation
Senior Blockchain Architect research agent using Zai MCP for comprehensive analysis of EVM chains, perpetual DEX archite...
Use when the user wants to create, refine, merge, archive, or review one standalone Brainstorm before Package conversion...
Brainstorm follow-up research ideas from papers. Use when asked to generate research directions or ideas.
Transform research ideas into actionable experiments with hypotheses, iteration rewards, and completion criteria. Use wh...
Researches a company from its URL and produces a Brand DNA file covering positioning, audience, competitors, voice, and...
Use when researching a focused question on the web and returning a dated, source-linked evidence brief without editing f...
Turns a question into a sourced research brief with claims tied to citations. Use when the task involves research, writi...
Define and answer a bounded research question with a source plan, evidence ledger, cross-checking, conclusions, unknowns...
Use when the user asks for researched, sourced, evidence-backed, or current findings, especially for a recommendation or...
Produce a structured research brief on any topic — TL;DR, cited key facts, notable quotes, suggested angles, open questi...
Turn a research need into a self-contained assignment with scope, evidence requirements, comparisons, stopping condition...
Produce a decision-ready research-brief brief from bounded governed evidence and preserve every material source binding.
Standard template + checklist for scoping market research projects.
Curate public-source links, saved notes, newsletters, documentation updates, release notes, market signals, and research...
快速梳理调研问题、提炼事实与不确定性、给出后续实验/访谈/数据拉取建议的通用调研简报模板。
How to do research for benchmarking, financial and economic modeling, and other business analysis tasks.