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.
- jasonkneen SkillClicky Email Assistant
Draft, rewrite, summarize, triage, and prepare replies or outreach emails. Use for Gmail/Outlook/Mail tasks, email thread summaries, outbound sequences, follow-ups, humanizing drafts, and Gmail sends that require upgraded send permission plus explicit approval.
Audited 1.6k - liangdabiao BundleAmazon One Shot
一站式深度亚马逊产品调研。分析任意ASIN,生成9份综合报告:产品信息提取、关键词研究、竞品分析、评论深度分析(需要登录以获得最佳结果)、销售/收入估算、listing优化审计、图片策略、可复用的listing模板和产品选品可行性评分。当用户提供亚马逊ASIN、产品URL或说'深度调研'/'深度分析'/'调研'/'product research'/'选品分析'时使用此技能。也适用于'analyze this product'、'what do you think of this listing'、'competitive analysis'、'review analysis'等短语,或任何涉及亚马逊产品情报的请求。
Audited 115 - yogsoth-ai BundlePre Write Precision Check
Independently fact-check every claim in a paper's bundle against the raw source text (Factored Verification method), flagging any claim the source doesn't actually support at a correctness score below 0.8. Use this before any article drafting begins, immediately after extract-structured-bundle produces the bundle — never skip this even if the bundle looks obviously correct, since research shows even top models hallucinate subtly when summarizing papers.
Audited 512 - frankxai BundleGolden Age Book Writing
Master-level visionary book writing system with research-driven methodology, author voice modeling, and iterative refinement across 9 quality dimensions
Audited 47 - 2233admin BundleBmad Sprint Planning
Gate planning readiness, generate sprint status tracking from epics, summarize sprint progress, and validate or repair the tracking file. Use when the user says "run sprint planning", "generate sprint plan", "check implementation readiness", "show sprint status", "validate sprint status", or "fix sprint status"
Audited 26 - qa-aman SkillFeature Spec
Write a concise feature spec (one-pager) for engineering handoff. Use when user says "write a spec", "one-pager", "feature spec", "spec this out", "spec for [feature name]", or wants a structured feature brief grounded in product context and user research.
Audited 26 - zimoliao SkillPaper Guided Reading
Use when the user wants guided reading, deep reading, or structured analysis of a single paper, starting from fuzzy keywords or a research question.
584 - frankxai BundleArxiv Paper To Brief
Turn an arXiv (or any research) paper into a structured, citation-faithful brief — problem, method, results, limitations, and why it matters. Use when summarizing a paper, building a literature digest, or asked to 'explain this paper' / 'TL;DR this arxiv link'.
Audited 47 - imbue-ai BundlePropose Experiment
Design and propose the next step: either a regular data-gathering experiment, literature search, or a concrete solution candidate.
Audited 246 - imbue-ai BundleScore Theory Solutions
Score and rank solution candidates relative to the research goal, and update parent theory scores.
Audited 246 - parcadei BundleResearch
Document codebase as-is with thoughts directory for historical context
Audited 3.9k - aws-samples SkillAI Draft
Write a full document draft, incorporating research and outline if available. Invoke ONLY via the /ai-draft slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.
Audited 141 - dobroslavradosavljevic BundleBrainstorm
Read-only brainstorming mode for exploring ideas, plans, architecture, debugging approaches, product decisions, research topics, codebase questions, and alternatives without mutating the user's codebase. Use when the user invokes $brainstorm, says "brainstorm", "brainstorming session", "let's think", "explore this", "research only", "read-only", or otherwise asks to discuss before implementation. Remain read-only until the user explicitly asks to implement, edit, write, apply, commit, install, or otherwise change state.
Audited 3 - fabioc-aloha BundleScout Knowledge Base
Preserve battle-tested session lessons, anti-patterns, failure modes, and reusable decisions in a shared file-based knowledge base for Scout instances.
Audited 5 - winstonkoh87 SkillDeep Research Loop
Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.
Audited 620 - gcwing SkillPlan
Research and write an actionable implementation plan without implementing it. Use when the user asks to plan, design an approach, or inspect a change before coding; stop applying the planning restriction once the user explicitly asks to implement.
Audited 4k - hoangsonww SkillSummarize Url
Fetch and summarize a specific URL for quick insights.
Audited 1.2k - gauss314 BundleBacktesting
Academic backtesting framework for quantitative research. ~30 risk and performance ratios, 10 classes of indicators, event-driven engine with 6+ strategies, MPT optimizer, forward-looking simulation with Johnson SU + t-Copula, walk-forward CV, stress testing, fundamental analysis (Altman Z, Piotroski, DuPont). All flat Python + numpy.
Audited 253 - marin-community SkillUpdate Docs
Update durable docs when explicitly requested or when current work changes behavior, exposes stale instructions, establishes an operational pattern, or yields reusable research guidance.
Audited 4.1k - owl-listener SkillResearch Planning
Use when user needs are unclear, assumptions need validation, or the design brief identifies gaps in understanding — plans what to learn, which methods to use, and from whom
Audited 3.4k - ttttstc SkillVibeflow Learn
独立学习流。用于陌生领域学习、研究文章写作、把资料变成输出。提供 Deep Research / Quick Reference / Write to Learn 三种模式,按 Collect -> Digest -> Outline -> Fill In -> Refine -> Publish 六阶段推进。
Audited 11 - yipng05-max SkillTa Framework Writer
TA(主题分析)理论框架章节写作工具。将理论框架建构结果转化为论文正文章节, 根据理论定位(A理论驱动/B经验驱动/C敏感性概念)自动生成对应形态的章节文字。 当用户需要将理论框架写入论文、撰写理论框架章节, 或在 ta-research-workflow 中到达"理论框架章节写作"检查点时触发。
Audited 322 - b-m-capital-research SkillDeep Stock Research
Admin-only skill for launching deep research on a specific company for about 1-2 hours while reporting progress every minute
Audited 751 - poorvith-mp BundleLiterature Review
Synthesise many papers into themes, contradictions, methodological quality and open questions. Use when synthesizing academic fields, thematic clusters, or research gaps.
Audited 5 - snowflake-labs BundleInvestment Memo Generation
Generates structured investment memos with thesis framing, financial analysis, risk assessment, and catalyst identification. Use when the user asks for an "investment memo", "investment thesis", or "comprehensive company analysis". Requires multi-tool orchestration across SEC data, analyst estimates, and qualitative research.
Audited 54 - poorvith-mp BundleTopic Selection
Turn a broad interest into a tractable research question or essay topic with defensible scope and available sources. Use when narrowing research questions, thesis scopes, or project ideas.
Audited 5 - cdeistopened SkillAsk Kdp
Route any Amazon KDP self-publishing question to the right skill, framework, or transcript search. Use when someone asks about publishing on Amazon, wants niche research, needs keyword help, or says 'ask kdp.' This is the main concierge -- it figures out what the user needs and dispatches to the right specialist skill.
Audited 29 - cdeistopened SkillBook Architect
Generate pain-point-driven book outlines with 10 title/subtitle options and 8-chapter structures. Use after niche and keyword research is complete.
Audited 29 - jackchuka SkillP Activity Digest
Summarize recent communication activity from Slack and meeting recordings. Use when the user wants to know what happened on Slack, review meeting action items, find mentions, or get a communication summary. Triggers on "summarize Slack", "meeting action items", "what was discussed", "activity summary", "search my mentions", "highlight of the day", "/activity-digest".
Audited 15 - xiaolai SkillCitation Hygiene
Prepare citation-ready notes for drafting, fact-checking, and legal review.
Audited 918 - iflytek BundleWeather
Retrieve and summarize current weather and forecasts for locations, rain, temperature, and travel planning using an available web tool or wttr.in over HTTPS.
Audited 5.4k - t46 SkillResearch Strategy Brief
政策動向、研究力分析、公募情報、学内資源を統合し部局・研究グループ向けの研究戦略メモを作る
Audited 17 - atman-33 BundlePermanent Rebuilder
Rebuild and maintain an Obsidian vault's permanent knowledge base for work knowledge and learning notes. Use when asked to reorganize permanent, design hub/leaf/MOC structure, standardize frontmatter (especially required summary), define tag taxonomy, generate a safe restructure plan (dry-run), and apply non-destructive moves/renames while preserving links.
Audited 4 - tkolleh BundleSave Zk
Only when the user explicitly invokes `save-zk` or `/save-zk`. Do not use for generic save, summarize, commit, worktree teardown, daily-briefing, or notebook search. Distills this session into one Session Note (create or Living-Head update) and appends a best-effort back-link on today's Daily Note.
Audited 2 - ruvnet SkillDeep Research
Orchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findings
Audited 104k - google-gemini BundleResearch
Gather source material for the radio show from any content source — web, HN, GitHub, papers, or general topics.
Audited 3.8k
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 paper-guided-reading, propose-experiment, brainstorm. 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 get-skill add <owner>/<name>, or copy the file into your agent's skills directory.