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 Notion 3Create, search, and update Notion pages/databases using the Notion API. Use for documenting work, generating runbooks, and automating knowledge base updates.
567 -
majiayu000 Bundle Knowledge Gap 2Detect unknown territory before acting — Research Gate that forces authoritative verification before using unknown APIs or libraries
567 -
majiayu000 Bundle Bias Check 2Use before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.
567 -
majiayu000 Bundle Research 15Research prediction markets - base rates, resolution rules, historical data
567 -
majiayu000 Bundle Research 17When user says "research" (in any form), ALWAYS invoke this skill.
567 -
majiayu000 Bundle Technical Implementation 2Execute implementation plans using strict TDD workflow with quality gates. Fifth phase of research-discussion-specification-plan-implement-review workflow. Use when: (1) Implementing a plan from docs/workflow/planning/{topic}.md, (2) User says 'implement', 'build', or 'code this' after planning, (3) Ad hoc coding that should follow TDD and quality standards, (4) Bug fixes or features benefiting from structured implementation. Writes tests first, implements to pass, commits frequently, stops for user approval between phases.
567 -
majiayu000 Bundle Wechat Article Writer 2专业的微信公众号文章创作助手。当用户提供网站链接、文本素材或图像,需要创作微信公众号文章时使用。支持多种写作风格——企业官号文案、个人技术博客、社区活动回顾、产品评测等。擅长AI/技术话题的深度内容创作,也能产出规范的企业宣传文案。通过搜索工具丰富内容,优化标题和结构。当用户提到"公众号"、"微信文章"、"写一篇推文"、"帮我写篇文章发公众号"等场景时触发。即使用户没有明确说"公众号",但在要求创作中文长文(技术博客、产品介绍、活动回顾等)时也应考虑触发。不用于:带引用的研究报告(用deep-research)、把内容做成图或PPT(用deck-studio)、英文文章、只润色一小段文字。
567 -
majiayu000 Bundle Plan Writing 2Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.
567 -
majiayu000 Bundle Planning With Files 5Manus-style planning with persistent markdown files
567 -
majiayu000 Bundle Spec Creation 3Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.
567 -
majiayu000 Bundle Using Agentops 3Meta skill explaining the RPI workflow. Auto-injected on session start. Covers Research-Plan-Implement workflow, Knowledge Flywheel, and skill catalog.
567 -
majiayu000 Bundle News 5Research and publish a daily AI news edition (The AI Dispatch)
567 -
majiayu000 Bundle Deep Research 15Deep 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 Digest 3Summarize vault learnings and activity for today or a date range.
567 -
majiayu000 Bundle Review 38PhD-level academic manuscript and research proposal review.
567 -
majiayu000 Bundle Release 34Step through versioning, tagging, and verification
567 -
majiayu000 Bundle User Research 4Lưu trữ và phân tích user research cho PikaRobot: interviews, surveys, observations. TRIGGERS: "user research", "interview notes", "survey results", "phỏng vấn user", "parent feedback". NOT FOR: Quantitative metrics (→4_Measure/), feature spec (→2_Define/).
567 -
majiayu000 Bundle Spec 15Core specification workflow engine. Triggers stage agents (CREATE, RESEARCH, PLAN, IMPLEMENT, REVIEW, TEST, etc.) for structured development. Triggers on keywords: spec, specification, plan spec, implement spec, review spec
567 -
majiayu000 Bundle Literature Review 7Systematic search methodology, taxonomy construction, citation graph exploration, and related work synthesis for ML research.
567 -
majiayu000 Bundle Research Review 2Perform iterative research document review using Rule of 5 methodology. Reviews accuracy, completeness, clarity, actionability, and integration with project context.
567 -
majiayu000 Bundle Researcher 5Generates or refreshes research artifacts and RLM evidence for a ticket. Use when research stage should produce or update canonical RLM outputs.
567 -
majiayu000 Bundle Database 3Database operations, queries, migrations, and optimization.
567 -
majiayu000 Bundle UI UX Pro Max 3UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.
567 -
majiayu000 Bundle Fix 10Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.
567 -
majiayu000 Bundle Done 2End of session wrap-up - summarize work, update docs, and commit
567 -
majiayu000 Bundle Company Research 3Run company research using Primr. Use when the user asks to research, analyze, or investigate a company, or provides a company URL.
567 -
majiayu000 Bundle Confidence Scoring 2Assess research quality with systematic confidence scoring, source validation, and uncertainty quantification.
567 -
majiayu000 Bundle Deep Research 16Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X", "explain X", "compare X and Y", "research X", or before content generation tasks. Provides systematic multi-angle research methodology instead of single superficial searches. Use this proactively when the user's question needs online information.
567 -
majiayu000 Bundle Research 30Deep research and fresh perspective on current blockers. Use when stuck, for methodology validation, or auto-triggered during long optimization runs.
567 -
majiayu000 Bundle Content Research Writer 2Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
567 -
majiayu000 Bundle Research 31Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.
567 -
majiayu000 Bundle Unknown 29actor: {{actor}} | mandate: Conduct systematic investigation and analysis | bounds: Research and analysis only
567 -
majiayu000 Bundle Create Project 3Create atomic research project notes with minimal overhead
567 -
majiayu000 Bundle Notebooklm 4Use 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. Zero hallucinations, just your knowledge base.
567 -
majiayu000 Bundle Templates 13For skills that aggregate information from multiple sources.
567 -
majiayu000 Bundle Deep Research 17Use when researching complex topics, evaluating technologies, investigating domains, or answering multi-faceted questions requiring web research. Triggers: "research X", "investigate Y", "evaluate options for Z", "what are the best approaches to", "help me understand", "deep dive into", "compare alternatives".
567
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 notion, knowledge-gap, bias-check. 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.