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.
-
akash-joshi Skill Idea ScoringScore and rank a shortlist of startup ideas to decide which one to build. Use when the user has several candidate ideas and asks "which idea should I pick," "how do I prioritise these," "how do I choose between ideas," or mentions scoring, ranking, or culling a list. This is the "Order & Cull" stage of the B.R.O.T.H. framework. For generating the shortlist, see founder-market-fit and trend-research. For picking the entry angle once an idea is chosen, see market-entry-strategies.
-
akash-joshi Skill Trend ResearchResearch market demand and search traffic to find or validate startup ideas. Use when the user wants to find trends, check search volume, size a market, or asks "how do I research demand," "what's trending," "how big is this market," "how do I find competitors," or mentions tools like Google Trends, Ahrefs, Exploding Topics, or keyword research. This is the "Research Widely" stage of the B.R.O.T.H. framework. For generating the keywords to research, see founder-market-fit. For ranking what you find, see idea-scoring.
-
akash-joshi Skill Prospecting ListsBuild qualified prospect lists from directories, databases, and community research. Use when the user wants to build a target list of potential clients beyond real-time keyword search. Also use when the user mentions "prospect list," "lead list," "ICP," "ideal client profile," "target accounts," "who should I reach out to," or "build a list." This is systematic list-building — different from the real-time keyword-search skill. For writing outreach after building the list, see cold-dm.
-
akash-joshi Skill Founder Market FitGenerate candidate startup ideas grounded in the user's own skills, experience, and network. Use when the user asks "what should I build," "how do I find a startup idea," "what business is right for me," or mentions founder-market fit, ikigai, or not knowing where to start. This is the "Begin With Yourself" stage of the B.R.O.T.H. framework. For checking whether the resulting ideas have demand, see demand-first-validation and trend-research.
-
akash-joshi Skill Demand First ValidationValidate that a startup idea has real market demand before building. Use when the user wants to check if an idea is worth pursuing, is worried a competitor already exists, or asks "is this a good idea," "should I build this," "someone already built my idea," "how do I validate an idea," or "how do I know if there's demand." Covers the demand-first mindset, the four failure modes that kill bootstrapped ideas, and the competitor reality check. For finding ideas from your own background, see founder-market-fit. For researching demand signals, see trend-research.
-
chapmanjw Bundle Building ArchitectDesigns and blueprints specific named buildings and building complexes in a live Minecraft Bedrock world — real-world replicas (historical and modern), pop-culture replicas (Hogwarts, Minas Tirith), user-described originals, and generative-style fictional buildings — with deep research, advanced building technique, and heavy reuse of defined structure modules. Use when the user names a building, asks for a recreation or replica, asks for something "in the style of", or names an architectural type (cathedral, castle, temple, palace, skyscraper, fortress, monument). Part of the minecraft-builder workflow.
-
koach08 Skill Cec TableBuild a Claim–Evidence–Citation table before drafting any argumentative text, so every claim is pinned to evidence and a source with a support level. Catches citation drift (real source, does not support the claim) and fabrication early. Use before drafting a paper or grant, or when auditing an existing draft's citations.
-
koach08 Skill Kakenhi DraftKAKENHI (科研費) research grant application drafting. Structures research objectives, plans, achievements, and budget following JSPS format. Written in formal academic Japanese (である調). Use when drafting KAKENHI (科研費) research grant applications.
-
koach08 Skill Literature ReviewConduct academic literature reviews. Summarize PDFs/papers, analyze research gaps, generate annotated bibliographies. For the literature review section of academic papers. Use when reviewing academic literature for a research paper.
-
koach08 Skill Citation VerificationVerify that citations and references actually exist. DOI resolution, web search confirmation, fabricated citation detection, and author/year/journal consistency checks. Works on academic papers, blog posts, articles, and any text. Use when verifying citations exist and are accurate in any text.
-
zenithjuno Bundle HandoffCreate a Codex-first continuity handoff for continuing work in a fresh Codex session. Use whenever the user wants to continue in a new chat/session, preserve context, compact a long thread, avoid losing work, or leave a "start here" briefing. Triggers include "handoff," "hand this off," "continue in a new chat," "start a fresh chat," "this chat is getting long," "I'm running low on context," "summarize this so I can pick it up later," and Thai equivalents such as "ส่งต่อ," "สรุปไว้ไปคุยต่อแชทใหม่," "เปิดแชทใหม่," "แชทนี้ยาวแล้ว." Create repository-aware, scope-safe handoffs that preserve local storage conventions and current continuation routes while capturing conversation-only state, exact workspace paths, completed checks, settled decisions, and the immediate next action.
-
nyuway-cybersecurity Skill Note SummarizerSummarize user-provided notes into concise action items.
-
nyuway-cybersecurity Skill Code Review HelperSummarize code diffs and list review questions for the user.
-
nyuway-cybersecurity Skill Remote Doc LoaderFetch a URL provided by the user and summarize remote instructions for review.
-
polypoint Bundle ResearchUse when the user wants to deeply understand a codebase topic, feature, module, or domain concept. Produces a structured research document with architecture diagrams, glossary, and actionable findings saved to the project's docs directory.
-
polypoint Skill Dev TicketUse when the user asks to actually work on a Jira ticket — do, fix, implement, take, start, resume, or finish it — in any language; never start coding a ticket without this skill, even if the request looks like a plain coding task. The signature is a ticket key like PROJECT-123 (any uppercase prefix — ABC-1234, PLAT-1290, PPCLOUD-14330) combined with intent to change code, however terse ("let's do X-123") or however much context surrounds it (bug details, urgency, PO assignment, screenshots, base branch). Runs the full lifecycle — fetch and analyze the ticket, reproduce, implement in an isolated git worktree, verify live with the user, commit, create the PR, shepherd it to merge. Also use for `/dev-ticket setup` (first-time project setup). Do NOT use when the user only wants information or Jira actions about a ticket (summarize, explain, estimate, status, transition, comment) or for coding tasks with no ticket involved.
-
dikamilo Skill Dx ResearchInvestigate one topic — codebase or external doc — and write it down with provenance for a plan to lean on.
-
fw1201 Bundle Tw Edu Research Viz 2以真實數據製作研究圖表。適用於研究圖表、PRISMA、教學研究視覺化。
-
fw1201 Bundle Tw Edu Citation Checker 2核實文獻存在性與引用資訊。適用於文獻查核、引用查核、APA。
-
itspecialist111 Skill Research Lead Researchresearch/lead-research — skill payload
-
itspecialist111 Skill Content Research Writercontent/research-writer — skill payload
-
itspecialist111 Skill Research Competitive Ads Extractresearch/competitive-ads-extract — skill payload
-
outfitter-dev Bundle Research 2This skill should be used when researching best practices, evaluating technologies, comparing approaches, or when research, evaluation, or comparison are mentioned.
-
rudironsoni Skill Orlix Dynamic Workflows 3Use when Orlix work benefits from explicit workflow packets, authorized subagent orchestration, or independent research, implementation, test, and review tracks.
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 idea-scoring, trend-research, prospecting-lists. 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.