Research & Search
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
-
majiayu000 Bundle Refactoring 11 CI AutomationUse when adding minimal CI automation for lint, tests, and type checks in Python research code.
567 -
majiayu000 Bundle Research Highrise Studio Lua APIDive into the Highrise Studio Lua API docs and answer questions.
567 -
majiayu000 Bundle BackupAutomated backup strategies for workspace, credentials, and critical data.
567 -
majiayu000 Bundle Searching Scientific LiteraturePubMed search with keyword optimization, result parsing, and metadata extraction
567 -
majiayu000 Bundle Swarm AdvancedAdvanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
567 -
majiayu000 Bundle Simd OptimizeSIMD vectorization for Rust — detects ISA features, identifies vectorizable patterns, generates platform-specific intrinsics (ARM NEON/SVE, x86 SSE/AVX/AVX-512), validates correctness and performance. Uses tiered research with baked-in references and /deep-research fallback.
567 -
majiayu000 Bundle Reflection InterviewInteractive interview for journal entry reflections. Covers all 5 research sub-questions (Workflow, Autorschaft, Iteration, Scheitern, Ästhetik) aligned with the main research question.
567 -
majiayu000 Bundle AnalystBusiness Analyst for requirements engineering and user story creation. Transforms research findings into actionable specifications. Use this skill for requirements, user stories, or specifications.
567 -
majiayu000 Bundle Add ContentCreate new files in knowledge base with directory governance. Use when user wants to save, create, or add content. Reads RULE.md to understand directory purpose and follows specified rules. Recommends target directory based on content analysis.
567 -
majiayu000 Bundle Aget Record ObservationRecord research observations into AGET KB without committing specs. Use when discovering vocabulary candidates, RQ proposals, web findings, patterns, or observations mid-session that should be preserved before continuing.
567 -
majiayu000 Bundle Lead Research Assistant通过分析您的业务、搜索目标公司并提供可操作的联系策略来识别您的产品或服务的高质量潜在客户。非常适合销售、业务开发和营销专业人员。
567 -
majiayu000 Bundle Search 9Searches the web, legal databases, case law, patents, and case.dev knowledge base via the casedev CLI. Use when the user mentions "search", "legal research", "find cases", "case law", "patent search", "web search", "fetch URL", "webfetch", "legal skills", or needs to research legal topics, find similar cases, or retrieve web content.
567 -
majiayu000 Bundle Orthogonal Investor ResearchResearch VCs, angels, and investors - portfolio, thesis, contact info
567 -
majiayu000 Bundle Fact Checker 2Use when documents with quantitative claims need citation verification, especially when every number must trace to a specific inline superscript citation before publication
567 -
majiayu000 Bundle Milestone 3Analyze and summarize GitHub milestone status for this repository.
567 -
majiayu000 Bundle Research 18Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.
567 -
majiayu000 Bundle Researcher 4Use when comprehensive literature research is needed, especially when quantitative parameters must be sourced from primary literature with proper citations and context (species, measurement methods, culture conditions)
567 -
majiayu000 Bundle Slack 3Transform messy work updates into clean, standardized end-of-day Slack sync summaries. Use when asked to "format my updates", "create a sync", "write a standup", or "summarize my work" for Slack.
567 -
majiayu000 Bundle Tdd 28Canon TDD for humans and AI agents. Use for production code changes by writing tests first, proving RED, implementing minimal GREEN, and refactoring safely.
567 -
majiayu000 Bundle Architect 4Planning-only mode: research, analyze, and design — no code changes
567 -
majiayu000 Bundle Deep Research 13Deep research before design — 3-5 parallel research agents survey papers, production systems, failure modes, and prior art, then a synthesizer compiles evidence, and an integrator maps findings to a concrete codebase plan with citations
567 -
majiayu000 Bundle Orthogonal Yc Batch EvaluatorEvaluate YC batch companies for investment — scrapes the YC directory, researches each company and its founders (work history, LinkedIn, website), assesses founder-company fit, and exports to Google Sheets with priority rankings. Use when asked to evaluate YC companies, research a YC batch, screen startups, or do due diligence on YC companies.
567 -
majiayu000 Bundle X Research 3X/Twitter research via Composio — search, threads, profiles, watchlists
567 -
majiayu000 Bundle Research 23Comprehensive research, analysis, and content extraction system. Multi-source parallel research using available researcher agents. Deep content analysis with extended thinking. Intelligent retrieval for difficult sites. Fabric pattern selection for 242+ specialized prompts. USE WHEN user says 'do research', 'extract wisdom', 'analyze content', 'find information about', or requests web/content research.
567 -
majiayu000 Bundle Project Init 5Scaffold new projects with standard structure. Use when: (1) user says "create project", "scaffold", "initialize", (2) starting from scratch, (3) need consistent project layout. Creates CLAUDE.md, README.md, PLAN.md, RESEARCH.md, AGENTS.md, .gitignore, and .claude/skills/ directory.
567 -
majiayu000 Bundle Orthogonal Competitor ResearchResearch competitors - products, pricing, team, funding, and strategy
567 -
majiayu000 Bundle Fact Checker 3Use when documents with quantitative claims need citation verification, especially when every number must trace to a specific inline superscript citation before publication
567 -
majiayu000 Bundle Migrate 5Migration workflow - research → analyze → plan → implement → review
567 -
majiayu000 Bundle Research 24[Planning] Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable. For implementation planning, see also `planning` skill.
567 -
majiayu000 Bundle Research 26Document codebase as-is with thoughts directory for historical context
567 -
majiayu000 Bundle Market Analysis 2Competitive research, SWOT analysis, and feature differentiation.
567 -
georgeqle Skill Assumption Tracker 3Extract and risk-rank assumptions from research docs — living register of what to validate first
1 -
georgeqle Skill Youtube Format Research 2Break down a YouTube video's format, visual system, pacing, editing grammar, motion, audio, and Remotion-ready production patterns
1 -
georgeqle Skill Youtube Format Research 3Break down a YouTube video's format, visual system, pacing, editing grammar, motion, audio, and Remotion-ready production patterns
1 -
georgeqle Skill Youtube Vid Research 3Research one or more external YouTube videos for context, claims, structure, examples, terminology, and transferable takeaways
1 -
georgeqle Skill Youtube Format Research 4Break down a YouTube video's format, visual system, pacing, editing grammar, motion, audio, and Remotion-ready production patterns
1
Frequently asked questions
What are Research & Search agent skills?
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
Which Research & Search skills are most installed?
Popular Research & Search skills on SkillMD right now include orthogonal-competitor-research, fact-checker, migrate. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Research & Search skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.