83,201 skills sorted by stars.
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan vi...
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipel...
Use this skill when you need to conduct thorough research on a repository's structure, documentation, and patterns. This...
将deep调研结果汇总为markdown报告，覆盖所有字段，跳过不确定值。
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
Resume a research plan. Spawns parallel agents if not started, checks progress, or synthesizes findings.
Perform iterative research document review using Rule of 5 methodology. Reviews accuracy, completeness, clarity, actiona...
Iterative review of research documents using Rule of 5
Get a deep critical review of research from GPT using a secondary Codex agent. Use when user says "review my research",...
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review"...
Get a deep critical review of research from Gemini via gemini-review MCP. Use when user says "review my research", "help...
Get a deep critical review of research from Claude via claude-review MCP. Use when user says "review my research", "help...
Expertise in reviewing technical research for objectivity, evidence, and completeness. Use to ensure the "Documentarian"...
调研最佳实践的 Skill。当需要了解某个领域的方法论、工具、最佳实践时触发。触发词：调研、research、了解一下、有什么方法、最佳实践。
Conduct systematic research with confidence scoring, source validation, and structured reporting for technology decision...
Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and doc...
Systematic methodology for gathering, analyzing, and synthesizing research from multiple sources into coherent insights...
Synthesize insights from multiple research sources into cohesive analysis
Synthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd:new-project after 4 resear...
Research Tailwind CSS v4 patterns, components, and responsive design using Exa code search and Ref documentation
Research Tanstack Query (React Query) patterns for server state management using Exa code search and Ref documentation
Apply research-through-design (RtD) methodology to investigate wellbeing in design contexts. Use when conducting user re...
Convert SOTA research into executable plans. Use when: (1) starting features with unknowns, (2) need current best practi...
Transform academic research insights into practical workflow optimizations
Deep research on a technical topic for blog writing. Use when user says research, look into, explore, or provides a blog...
Crawl and collect resources for a financial research topic using Exa with full HTML and chart extraction.
Research a topic for content creation
Research a philosophical topic using web search. Outputs research notes, not finished content.
Research voids (cognitive gaps, unchartable territories). Daily. Outputs research notes for voids articles.
Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-res...
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across t...
Conduct thorough research with proper citations and source verification for academic and professional content
Systematic research workflow orchestrating multi-source research operations for comprehensive domain investigation. Sequ...
Research writing conventions for academic and professional contexts. Covers the research process (question formation, li...
Research Zod validation patterns, schema design, and TypeScript integration using Exa code search and Ref documentation
Multi-repository analysis and research specialist
Generates or refreshes research artifacts and RLM evidence for a ticket. Use when research stage should produce or updat...
Conducts investigative-grade research with primary source analysis, cross-verification, and trial-level depth. Use when...