Research

Searches the NIST NVD database for CVE vulnerabilities using API 2.0. Returns CVE details, CVSS scores, affected software, and references. Use when user asks about "CVE", "vulnerability database", "NIST", "NVD", "security advisory", "CVE-2024", "CVE-2023", "脆弱性", "セキュリティアドバイザリ", or wants to find known vulnerabilities for specific software.

Google Apps Script documentation, guides, and API reference for automating Google Workspace applications

Deep exploration from a key paper. Triggers: 這篇論文的相關研究, 誰引用這篇, 類似文章, related articles, citation tree, paper exploration

Provide accurate, evidence-based answers by referencing sources from documents, textbooks, or research papers. Use when user asks for factual or source-backed responses.

Conduct comprehensive academic research using OpenAlex, PDF extraction, paper search MCPs, and web search. Always produces comprehensive reports with 5+ evidence cards covering conflicting ideas and best approaches. Integrates academic papers (high weight) and non-academic sources (blogs, docs - lower weight but valuable for SOTA). Use when: (1) Researching software architecture patterns, (2) Finding academic papers on technical topics, (3) Conducting literature reviews, (4) Analyzing research papers for evidence-based decisions, (5) Building evidence cards from papers, (6) Finding related works and citations, or (7) When you need grounded, paper-backed technical recommendations. Triggers: research, find papers, literature review, evidence-based, academic research, compare approaches, what does research say, find studies on, search for papers about.

Skriptoteket-specific brutalist/academic UI design. Use for Vue/Vite SPA and SSR templates when you want grid-based layouts, systematic typography, and high-contrast “academic” aesthetics, while staying compatible with Skriptoteket’s pure-CSS + HuleEdu token stack (no Tailwind).

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Design, configure, launch, and analyze ablation sweeps for GRPO training. Use for hypothesis testing, hyperparameter experiments, and systematic comparisons.

Use PROACTIVELY when creating research reports, experiment writeups, technical whitepapers, or empirical study documentation. Orchestrates the complete benchmark report pipeline with structure, diagrams, hi-res PNG capture, and PDF export. Provides working scripts, CSS templates, and complete command sequences for publication-quality AI/ML benchmark reports. Not for slides, blog posts, or simple README files.

Perform SQL joins and multi-table analysis on DST data in DuckDB. Use whenresearch requires combining multiple tables on common dimensions (time, region).Provides patterns for common DST dimension joins and multi-table comparisons.

Naming conventions for planning documents in prompts/. Use when creating plans, PRDs, research reports, idea capture or other workflow documents. Triggers on (1) creating new planning documents, (2) naming PRDs or research reports, (3) questions about document organization in prompts/.

Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Orchestrate the complete LA-Bench experimental procedure generation workflow from JSONL input to validated output. This skill should be used when processing LA-Bench format experimental data to generate and validate detailed experimental procedures. It coordinates parsing, reference fetching, procedure generation, and quality validation with 10-point scoring.

Self-reference guide for Claude Code's own architecture, configuration, and extension points. Use when needing to know where Claude Code stores its configuration files, skills, plugins, hooks, MCP servers, settings, or any other internal structure. Triggers on questions like "where do skills go?", "how do I configure hooks?", "where is the settings file?", or when creating/modifying Claude Code extensions.

Execute project release workflows by locating and following project-specific RELEASE_GUIDE.md in the repository root or docs/. Use when asked to perform a release, publish a release, cut a tag, run release steps, or when a user references RELEASE_GUIDE.md.

Apply a Research → Plan → Implement → Validate workflow with Copilot CLI, including context budgeting and persistent artifacts via /share.

Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.

Curated project templates that guide feature-dev Phase 3 questions with research-backed technology choices. Provides standardized options for common project types (SaaS API, ML Service, CLI Tool, Full-Stack). Use when starting new projects or when feature-dev needs structured decision guidance. Do NOT use for existing projects with established stacks - analyze existing code instead.

Advanced code search tool that finds definitions, usages, tests, and references across the entire codebase. Use when you need to understand how a symbol is used throughout the project.