Shared reference for the research-knowledge cluster: the evidence ladder (lightest lane first → escalate on synthesis need), the four provenance tiers every claim carries,…
Route a research or knowledge task to the right skill among 12 specialists — current-web research, neural discovery, multi-source cited synthesis, systematic literature review,…
Web research skill for augmenting agent context with current information. Used when
A tiered approach to answering research questions with clear stop rules, evidence capture, and escalation to Tavily/Playwright only when needed.
Research a library and create comprehensive documentation in .claude/docs/libraries/. — from majiayu000/claude-skill-registry
Research a library and create comprehensive documentation in .claude/docs/libraries/. — from majiayu000/claude-skill-registry
Local-first multimedia research library for hardware projects. Capture code, CAD, PDFs, images. Search with material-type weighting. Project isolation with cross-references.
Use when a researcher asks where to start, which project skill fits the current stage of a study, or in what order literature scoping, source access, vault upkeep, drafting,…
Research and investigate Lightdash API endpoints to understand request/response schemas and behavior.
Run the research corpus lint ruleset to detect structural and referential integrity issues — orphan notes, missing frontmatter, broken references, missing GRADE assessments.
Search and analyze research papers, find related work, summarize key ideas. Use when user says \"find papers\", \"related work\", \"literature review\", \"what does this — from…
Search and analyze research papers, find related work, summarize key ideas. Use when user says \"find papers\", \"related work\", \"literature review\", \"what does this — from…
Auto-saves deep search results to SQLite and Langfuse. Combines search with persistent logging — every research query is saved with topic tags, timestamps, and full results.
Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic — from…
Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.
Look up current research information using Perplexity Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.
Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches).
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter.
Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), or Perplexity sonar-pro-search (academic — from…
Scaffold a research-grade experiment that tests whether a Looped / Recurrent-Depth Transformer (RDT) is better than a parameter-matched vanilla transformer at vulnerability…
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends — from…
Hierarchical information retrieval following strict order: KB first (smart_query/crag_search), then MCP/Context7, then web search, then LLM knowledge as last resort.
Technical research methodology with YAGNI/KISS/DRY principles. Phases: scope definition, information gathering, analysis, synthesis, recommendation.
On-demand deep-dive on a single ticker. Use when the user asks to "research NVDA" or similar.
Processes research branches from Claude Code Web sessions - merges content, moves docs to docs/research/, and creates GitHub issues.
研究方法選擇顧問:判斷一個研究題目適用量化(檔案資料/問卷)、質化(訪談/個案)、實驗、或混合方法,並給出 Q1 期刊等級的完整研究過程套模與 skill 呼叫鏈。核心邏輯:Edmondson & McManus (2007) 方法論適配(methodological…
Conduct traceable literature reviews for LLM tutoring and education research. Use when Codex must define a search protocol, screen studies, build an evidence matrix, synthesize…
Best practices for systematic research, source evaluation, and evidence gathering
Structured research using sophisticated query design, source vetting, and synthesis techniques. Use when conducting competitive analysis, market scans, historical investigations,…
Ethan Perez's tips for empirical alignment research - velocity, experimentation, collaboration
Research methodology in psychology. Covers experimental design (independent/dependent variables, random assignment, control conditions, between/within-subjects designs), research…
Research libraries, APIs, and patterns using searchGitHub and Exa tools. Finds real-world implementations and saves structured reports to docs/research/.
Anti-hallucination protocol for tasks where accuracy matters. Enforces evidence-first reasoning, source-cascade workflow, and explicit "I don't know" over speculation.
Design causal research into model activations, features, attention, residual streams, probes, and circuits.
Produces a Research Brief (deep mode) or Landscape Map (wide mode) document synthesizing findings into actionable recommendations.
Research Next.js 15 patterns, examples, and documentation using Exa code search and Ref documentation
Generate a professional Word document research note
Use when targeting 《经济与管理研究》(Research on Economics and Management — 首都经济贸易大学主办的经管交叉月刊, 1980 创刊, 北大核心/CSSCI, 不收费) or deciding whether a Chinese econ/management manuscript fits this…
Use when targeting 《财经问题研究》(Research on Financial and Economic Issues — 辽宁省教育厅主管、东北财经大学主办的经济管理类月刊, 1979 创刊, CN 21-1096/F, 双向匿名审稿, 不收任何费用, 在线投稿 cjwt.cbpt.cnki.net) or deciding…
Use when turning a new or existing workspace into a PM-ratifiable Project proposal.
Use when a governed research-state query, package mutation, Scope commit, knowledge registration, run reconciliation, or self-evolve transition is required.
中文优先：用于研究运维相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Evidence-first current-state research workflow for ECC.
Use when planning, funding, scoping, or synthesizing enterprise research across workstreams — clinical study design, R&D program finance, market sizing/surveys, or product/user…
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
Triggered when the user types /research or asks to start a research workflow. Guides the user through the full academic research lifecycle by suggesting the right skills at each…
研究总编排入口：为新方向启动、已有报告增量扩展、专题深挖、概念边界辨析、概念注册表同步、survey 到技术方案转换、repo 页面维护、机构路线图拆解、critical thinking 报告、methodology/样本流深挖与主稿成熟化合并选择合适的中文研究工作流，并串联…
Implement research-related code, parsers, analysis scripts, demos, simulations, or PoC tools after reading relevant research-os wiki context.
Bootstrap a structured research project on any topic — generate an initial items list and research-field schema from model knowledge, supplement with up-to-date web search, then…
Download academic papers from open-access sources when the user provides a DOI/arXiv ID or requests a keyword-based paper search, and return the saved PDF path.
Search for research papers and academic content using Exa advanced search. Full filter support including date ranges and text filtering.
Summarises academic papers into methodology, findings, limitations, statistical strength and practical implications.
End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM.
Research ML techniques, architectures, or papers relevant to the current task and summarize actionable insights.
4-phase research methodology: codebase recon, targeted web search, deep source analysis, and evidence synthesis.
Create refined user personas from research data — 3 personas with JTBD, pains, gains, and unexpected insights.
プロジェクト プロジェクトの Product Discovery スキル。 feature-pilot 進入前に「この機能を作るべきか？」と「どのように作るべきか？」を 業界標準フレームワーク（OST + Double Diamond + Shape Up）で検証する。
Full research pipeline: Workflow 1 (idea discovery) \u2192 implementation \u2192 Workflow 2 (auto review loop).
Use when you need a complete research workflow from initial literature search to polished, fact-checked document.
Full research pipeline: Workflow 1 (idea discovery) \u2192 implementation \u2192 Workflow 2 (auto review loop).