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.
-
thoreinstein Skill ResearchUse when the user asks a question about their vault, wants to explore a topic across notes, or says "research", "find out", "what do I know about", or "summarize my notes on". Chains semantic search, note reading, and link traversal for deep vault research.
-
agoradynamics Skill Wick TldrSummarize long content — document, paper, thread, or conversation — into a faithful TL;DR with key claims, action items, and flagged omissions. Use on long articles, meeting notes, papers, or prior-conversation compression.
-
agoradynamics Skill Wick CatalogExtract structured fields from a source — paper, web page, API doc, or UI screenshot — and save a queryable record to memory/catalog/. Domain-agnostic. Use to build a personal index of things you'll want to find again, compare side-by-side, or reference in later decisions. Complements wick-research (which finds) and wick-tldr (which summarizes) by adding a structured-index layer.
-
agoradynamics Skill Wick ResearchStructured research on a topic — applies CRAAP test, source hierarchy (Tier 1-4), steel manning, and base-rate reasoning. Tags findings with confidence level. Use when closing memory/curiosity.md entries or before major decisions depending on external data.
-
aleksander-dytko Skill Competitive ResearchProduce a sourced competitive matrix for a focused research question
-
andreworia Skill Earnings And Filings TeardownExtracts the financially material content from 10-K, 10-Q, and 8-K filings and earnings call transcripts into a structured one page brief with a source location on every number. Triggers when someone asks to tear down a filing or earnings release, summarize a 10-K or 10-Q, pull KPIs guidance and risks from a transcript, or brief the CFO on what a company reported.
-
jwcodewrote Bundle AI Search Browser UseUse this skill when a task needs AI-assisted web research via a real browser. Uses Chrome CDP (Chrome DevTools Protocol) as the primary automation method, with browser-use as fallback. Supports Gemini + Qwen queries with consolidated answers and citations.
-
jasoncodemaker Bundle Research OpUse when a governed research-state query, Package mutation, Research Plan update, knowledge registration, Run reconciliation, or self-evolve transition is required.
-
jasoncodemaker Bundle Research RunUse when the user invokes /research-run or asks to execute, continue, monitor, verify, or finish an existing research package.
-
jasoncodemaker Bundle Research InitUse when installing, attaching, initializing, repairing, or validating ARC in a research workspace.
-
jasoncodemaker Bundle Research OnboardUse when turning a setup-ready workspace into one ratified Project through a single natural-language review.
-
jasoncodemaker Bundle Research PackageUse when converting a Brainstorm, maintaining user-owned Package working state, restructuring an Experiment plan, or recording its terminal outcome.
-
jasoncodemaker Bundle Research AnalysisUse when initializing, adding, updating, deleting, or linting a package's state-backed Analysis view, or when distilling an evidence-backed insight into a package Rule.
-
jasoncodemaker Bundle Research Exp LiveUse when launching, monitoring, resuming, or stopping a long-running research Experiment with structured run evidence and scheduled live checks.
-
jasoncodemaker Bundle Research ResourceUse when registering predefined compute resources, probing short-term availability, choosing placement, allocating capacity, or releasing an allocation.
-
jasoncodemaker Bundle Research DashboardUse when building, serving, repairing, or validating the read-only .research/interface projection.
-
jasoncodemaker Bundle Research BrainstormUse when the user wants to create, refine, merge, archive, or review one standalone Brainstorm before Package conversion.
-
symbaiex Bundle Gpt Engineer MemMemory-aware GPT engineering for codebase research, implementation, verification, and release. Use when a task should reuse Claude Mem or Codex session history without trusting stale recollections, flooding context, changing memory settings, or weakening the GPT-5.6 Sol/Terra/Luna engineering workflow.
-
tubeliu Bundle Research多源客户调研——对客户问题、产品主题或账户相关查询进行系统性多源调研, 带来源归属和置信度评分。 触发:「调研客户 / 查一下 XX 公司背景 / 做一个客户调研 / research customer / 客户背景调查 / 行业调研 / 竞品调研 / 摸排客户需求」。 适用场景:方案撰写前的客户画像准备、竞品分析、技术可行性验证、历史沟通回顾。 不直接写方案(solution-master 接管)、不直接画图(drawio 接管)。
-
walterkken Bundle Design Thinking SprintRun a design thinking workflow: empathize, define, ideate, prototype, and test. Use when Codex is asked to solve user-centered product, service, interface, education, or experience problems through research, framing, ideation, prototyping, and user feedback.
-
ace-step Skill ComposeProcess-oriented full-song composition workflow for ACE-Step-DAW. Guides Claude through a principled research-first composition process: research genre → analyze references → extract principles → compose → evaluate. Invoke with /compose followed by a description of the desired song.
-
ace-step Skill Quick ResearchQuick Research Skill
-
ace-step Skill Strudel MaestroProcess-oriented Strudel pattern generation skill for ACE-Step-DAW. Teaches Claude how to research Strudel techniques, find examples, and generate patterns through a principled workflow — not by memorizing templates.
-
ace-step Skill Music Theory EngineProcess-oriented music theory skill for AI-assisted composition in ACE-Step-DAW. Instead of dumping all theory upfront, this skill teaches Claude HOW to research, analyze, and apply music theory for a specific composition task. Invoke when composing, arranging, or analyzing music.
-
croftspan Bundle GigoAssembles an expert team and scaffolds a Claude Code project for any domain — software, writing, game dev, research, design, anything. Researches the best practitioners in the field, blends their philosophies into focused personas, and writes lean .claude/ project structure with rules, standards, and workflow. Use this skill when the user wants to start a new project, set up Claude Code for a project, kick off work in an unfamiliar field, or says 'gigo.' This is the initial assembly — for adding expertise or auditing an existing project, use gigo:maintain instead.
-
futuremls-lab Skill Generate ProfileGenerate an e2e profiling trace of an SGLang server run. Launches a server, validates accuracy, captures a Chrome-compatible trace, and returns the profile path.
-
pymc-labs Skill ResearchStructure a research based on the user request. Identify what must change in order to complete the task.
-
pymc-labs Skill Make PlanCreate a plan based on document research through an interactive, iterative process.
-
stacklok Skill Implement StoryImplements a GitHub user story from planning through PR creation, with research, codebase analysis, and structured commits.
-
homingo Skill Document SummarySummarizes documents of any type — reports, memos, articles, and research papers. Extracts key points, action items, and important details from lengthy documents.
-
hutzelmann Bundle Proposal CheckLow-level check of a thesis proposal — required sections, citation consistency, forbidden content, format guardrails, typos. Use when the user asks to check their proposal, suspects a section or citation is missing or malformed, or wants a quick gate before publishing. Not content feedback — for whether the argument holds, use proposal-review. Advisory only.
-
hutzelmann Bundle Proposal WriteWrite a thesis proposal from scratch or refine an existing one, following the proposal guidelines and grounding claims in the literature. Use when the user wants a draft, wants sections improved, wants bullet points turned into prose, or asks to apply review findings.
-
hutzelmann Bundle Proposal IdeateSocratic development of a thesis idea — refine a vague topic into an academically grounded starting point scoped to the study program and target research group, keep durable session notes, and seed the proposal file. Use when the user has a rough idea, does not know what to write about or their research questions yet, wants to talk a topic through or weigh whether it is worth pursuing, asks where to start, or wants to resume an earlier ideation session.
-
hutzelmann Bundle Proposal ReviewHigh-level content review of a thesis proposal — argument structure, soundness, literature grounding, sharpness. Writes a review file opening with a three-tier verdict (ready / needs revision / no viable thesis core) followed by enumerated actionable findings. Use when the user asks for feedback or a review, doubts whether the argument holds or the thesis core is thin, or asks whether the proposal is ready for their supervisor — including before handing it to a supervisor.
-
hutzelmann Bundle Proposal Lit SearchFind relevant academic literature for a topic or proposal — keyword search across public scholarly databases, plus citation snowballing from existing references. Writes CSL-YAML entries into the proposal. Use when the user needs sources or papers, says their bibliography or reference list is thin, wants the literature base broadened, or asks whether their idea is already published or whether anyone has worked on it before.
-
ilkaydemiralay Bundle Creator Production DesignerBuild the film's world — locations, sets, props, period atmosphere, color and material language, and reusable visual continuity anchors for long-form AI film production. Use when the user needs world design, set documents, prop lists, period research, or AI location prompts.
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 research, wick-tldr, wick-catalog. 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.