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.
-
yuping322 Bundle Undervalued Stock ScreenerScreen and identify undervalued stocks with strong fundamentals using professional equity research methodology. Use when the user asks to find undervalued stocks, screen for cheap or bargain stocks, identify value investing opportunities, perform fundamental stock analysis, find stocks trading below intrinsic value, or requests a stock screener based on financial metrics like P/E ratio, debt-to-equity, free cash flow, or ROIC.
-
yuping322 Bundle Equity Research OrchestratorOrchestrate a full equity research workflow by calling relevant skills/toolkit views and assembling a single coherent deliverable. Use when the user asks to 'analyze this stock end-to-end' or wants a full research pack.
-
vuralserhat86 Skill User Research👥 User Research
-
vuralserhat86 Skill Keyword Research🔑 Keyword Research
-
vuralserhat86 Skill Research Synthesizer📝 Research Synthesizer
-
pa4uslf Skill ClusterUse when the user wants a topic cluster strategy with a pillar page, supporting articles, sequencing, and an internal-linking map. Save the strategy to research/.
-
pa4uslf Skill ResearchUse when the user wants a content research brief, keyword framing, competitor gap analysis, or article outline for this repository. Save the result to research/ and use the project context files as grounding.
-
the-utopia-studio Bundle Evidence LadderWeights a pile of "validation" by what people DID, not what they said. Takes interview quotes, sign-ups, LOIs, pilots, payments and places each on one ladder — money moved 1.0, behaviour observed 0.7, artefact shown 0.5, verbal commitment 0.3, opinion 0.1 — then returns a weighted evidence table, the weight of the load-bearing claim, and for every low signal the cheapest probe that raises it a rung. Fires on "how strong is this signal", "score the interview", "did they actually validate", "weight this evidence", "is this real validation". NOT a build gate on a problem (use problem-quality-scorecard), NOT a picker for which test to run next (use probe-matrix), NOT a transcript summary (use summarize-interview). This is the reference skill the rest of the module cites for the ladder.
-
manusco Skill Market Research<!-- Generated by Resonance Forge. -->
-
manusco Bundle Resonance Research Market ResearchConducts SaaS and B2B market research to identify Existential Data Points (EDPs) that transform solutions from nice-to-have to must-have. Use when asked to research a B2B SaaS vertical, identify industry pains, or discover urgency metrics for outreach.
-
kody-w Bundle Deep ResearchPerforms rigorous, evidence-first deep research using distinct parallel research strategies, primary sources, local artifacts, controlled experiments, adversarial verification, and confidence-rated synthesis. Use when a user asks for deep research, exhaustive investigation, reverse engineering, current landscape analysis, high-stakes comparison, or a defensible implementation recommendation.
-
broomva Bundle ProcurerGrounded procurement research for any real-world need. Turn a problem ("reduce bedroom noise from the avenue", "add air conditioning", "hire an accountant", "buy a TV mount", "replace the kitchen sink") into 3–5 ranked alternatives spanning DIY-retail → mid-retail → specialty → contractor → consultant/turnkey, each with cited price bands (low / typical / high), confidence scores, locale-aware currency, and a final recommendation with budget. Output is decision-shaped (recommendation + budget envelope), not research-shaped (knowledge artifact).
-
broomva Bundle GoodiesIngest, contextualize, and index curated resources (websites, tools, design references, research papers, UI kits) into a public GitHub Pages vault while automatically linking them to the local Knowledge Graph via /checkit and P6 bookkeeping. Dynamically resolves and expands category ontologies, generates client-side search indices, and publishes the updated vault database to a public repository. USE WHEN: /goodies, goodies, goodies add, add to goodies, bookmark this site, save to goodies, bookmark good resource, curate website. NOT FOR: internal-only notes without public vault indexing; general web searches without curating a resource.
-
broomva Bundle Format FirstDecide WHAT SHAPE of content to make, and refuse the platform folklore that circulates as fact. Encodes a claim set traced to primary sources — Meta's own engineering writeup and Transparency Center system cards, Mosseri's actual posts, and the psychology literature behind "hooks" and repetition — separating what is documented, what is hypothesis, and what is unsupported. Ships a linter that GRADES each claim — refuted, contested, unverified, folklore — and errors only on the ones contradicted by a primary source that was actually loaded, because "no source found" is a statement about a search, not about the world. The core move is choosing a FORMAT (visual grammar x script structure) as the invariant and letting topic vary, rather than the reverse. Use when, PRE-PRODUCTION: (1) choosing what shape a piece should take before it is written, (2) deciding how often to repeat a format and when to rotate it, (3) verifying a platform/algorithm claim from a course, thread, or guru, (4) auditing a draft or strategy d
-
broomva Bundle Social IntelligenceAutonomous social engagement + knowledge extraction loop for Moltbook and X/Twitter. Runs the engagement loop (post substantive comments, solve verification challenges, reply to mentions, quote-tweet), extracts knowledge from all interactions into the broomva research vault, and compounds with /blog-post and /content-creation to turn discovered insights into published content. Integrates with knowledge-graph-memory for cross-session persistence. Use when: (1) running the social engagement loop, (2) extracting knowledge from recent interactions, (3) generating content from trending ideas found in social threads, (4) planning X outreach or Moltbook engagement strategy, (5) turning community insights into blog posts or threads. Triggers on: "social loop", "engagement loop", "moltbook", "extract insights", "knowledge from interactions", "what's trending on moltbook", "run the loop", "social intelligence", "outreach strategy".
-
broomva Bundle Deep Dive Research OrchestratorConduct comprehensive multi-dimensional research on any subject using coordinated AI research specialists
-
richard0901 Bundle Sci Research Project InitializerUse when the project reaches 01-SCI研究项目初始化 in the SCI original research dynamic route workflow.
-
richard0901 Bundle Sci Clinical 15Use when the project reaches 15-SCI临床统计分析器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Clinical 03Use when the project reaches 03-SCI临床研究路线生成器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Experiment 03Use when the project reaches 03-SCI实验研究路线生成器 in the SCI original research dynamic route workflow.
-
richard0901 Bundle Sci Bioinformatics 03Use when the project reaches 03-SCI生信研究路线生成器 in the SCI original bioinformatics research workflow.
-
richard0901 Bundle Sci Clinical 07Use when the project reaches 07-SCI临床研究空白识别器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Experiment Gap IdentifierUse when the project reaches 08-SCI实验研究空白识别器 in the SCI original research dynamic route workflow.
-
richard0901 Bundle Sci Bioinformatics 09Use when the project reaches 09-SCI生信研究空白识别器 in the SCI original bioinformatics research workflow.
-
richard0901 Bundle Sci Bioinformatics 10Use when the project reaches 10-SCI生信分析流程设计器 in the SCI original bioinformatics research workflow.
-
richard0901 Bundle Sci Experiment Figure MakerUse when the project reaches 15-SCI实验结果图表制作器 in the SCI original research dynamic route workflow.
-
richard0901 Bundle Sci Clinical 16Use when the project reaches 16-SCI临床结果图表制作器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Bioinformatics 16Use when the project reaches 16-SCI生信结果图表制作器 in the SCI original bioinformatics research workflow.
-
richard0901 Bundle Sci Clinical 17Use when the project reaches 17-SCI临床报告规范核查器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Experiment Result StorylineUse when the project reaches 17-SCI实验结果主线提炼器 in the SCI original research dynamic route workflow.
-
richard0901 Bundle Sci Clinical 18Use when the project reaches 18-SCI临床结果主线提炼器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Bioinformatics 18Use when the project reaches 18-SCI生信结果主线提炼器 in the SCI original bioinformatics research workflow.
-
richard0901 Bundle Sci Experiment 24 Target Journal SelectorUse when the experimental research route needs target journal selection after implementation results and result storyline are clear.
-
richard0901 Bundle Sci Clinical 25Use when the project reaches 25-SCI临床目标期刊选择器 in the SCI original clinical research workflow.
-
richard0901 Bundle Sci Bioinformatics 25Use when the project reaches 25-SCI生信目标期刊选择器 in the SCI original bioinformatics research workflow.
-
richard0901 Bundle Sci Original General 25Retained legacy compatibility skill; do not use as the main target-journal deep-learning route when a dedicated research route exists. 仅在用户明确要求公共通用尾段时使用。
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 undervalued-stock-screener, equity-research-orchestrator, user_research. 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.