Research Subagents
281 research subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1development-workflows-research-agentResearch agent that fetches GitHub repos, counts agents/skills/commands, gets star counts, and analyzes Claude Code workflow repositoriesJul 2026
- 2report_compiler_agentTransforms research findings into polished APA 7.0 academic reports; activated in Phase 4 and Phase 6Jul 2026
- 3research_architect_agentDesigns the methodological blueprint; selects research paradigm, method, data strategy, and analytical frameworkJul 2026
- 4synthesis_agentIntegrates findings across sources, resolves evidence conflicts, and maps knowledge gapsJul 2026
- 5gemini-research-expertUse this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and synthesis of information.Jul 2026
- 6technical-researcherUse this agent when you need to conduct in-depth technical research on complex topics, technologies, or architectural decisions.Jul 2026
- 7trellis-researchCode and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.Jul 2026
- 8web-research-specialistUse this agent when you need to research information on the internet, particularly for debugging issues, finding solutions to technical problems, or gathering comprehensive information from multiple…Jul 2026
- 9research-workerPaid-media research worker for one bounded platform, policy, API, issue, pull-request, or repository slice. Produces source and license evidence without editing canonical guidance.Jul 2026
- 10source-verifierAdversarial source and claim verifier for paid-media facts, thresholds, policies, APIs, benchmarks, and repository evidence. Classifies confidence without repairing claims.Jul 2026
- 11literature-reviewerUse this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research…Jul 2026
- 12rebuttal-writerUse this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic…Jul 2026
- 13slack-archaeologistDeep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident…Jul 2026
- 14fact-checkerChecks the claims in a summary and returns whether they hold. Use after summarizing.Jul 2026
- 15README🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。--…Jul 2026
- 16README🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。--…Jul 2026
- 17aiox-analystAIOX Analyst autônomo. Market research, competitive analysis, brainstorming facilitation, ROI calculations, deep research. Usa task files reais do AIOX.Jul 2026
- 18scoutConfidence-gated exploration that assesses readiness before implementation. Scores 0-100 across five dimensions and gives GO/HOLD verdict.Jul 2026
- 19news-query-agentAnswer news queries with a fixed demo response.Jul 2026
- 20claim-verifierFresh-context verifier for factual claims made by other agents or skills. Implements the Chain-of-Verification (CoVe) independence trick via context forking — the verifier never sees the original…Jun 2026
- 21domain-refereeSubstantive referee for a manuscript. Reviews contribution, literature positioning, substantive argument, external validity, and journal fit. Calibrated to a target journal and primed with a…Jun 2026
- 22domain-reviewerSubstantive domain review for lecture slides. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory…Jun 2026
- 23editorJournal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from `.claude/references/journal-profiles.md`, and…Jun 2026
- 24methods-refereeMethodology referee for a manuscript. Paper-type-aware (reduced-form / structural / theory+empirics / descriptive / formal-theory / survey-experiment), each with its own dimension weights and…Jun 2026
- 25pedagogy-reviewerHolistic pedagogical review for academic slides. Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use after content is drafted.Jun 2026
- 26explainerCode explanation and architecture walkthroughs. Helps developers understand complex code and systems.Jul 2026
- 27worker-researcherWeb research agent. Searches, fetches URLs, extracts facts and evidence. No synthesis — just structured findings.Jul 2026
- 28researcherRead-only web and registry lookup. Use for Agent Skill / MCP discovery (npx skills find, MCP search), current-usage doc-checks, and scope source verification. Returns only a compact summary, never…Jul 2026
- 29scope-discovererDiscovers functional scope from existing codebase for reverse documentation. Identifies targets through multi-source discovery combining user-value and technical perspectives. Use when "reverse…Jul 2026
- 30competitive-intelInvoke for any competitor work — one-off competitive teardowns (content, SEO, paid ads, social, AI visibility, pricing, positioning) OR ongoing competitive monitoring (change detection, share of…Jul 2026
- 31intelligence-curatorUse when the task requires interpreting, synthesizing, or distributing marketing learnings across agents — compound intelligence, pattern recognition, confidence scoring, playbook generation,…Jul 2026
- 32research-expanderTask-specific research subagent for the prd-taskmaster expand-tasks skill. Takes a TaskMaster task (title, description, dependencies) and runs 3-5 targeted queries via available research tools…Jul 2026
- 33researcherMarket research and competitive analysis specialist. Use for conducting market research, analyzing competitors, gathering audience insights, exploring industry trends, and finding marketing best…Jul 2026
- 34online-researcherHarnessFlow worker subagent — spawn only from a HarnessFlow workflow step, never by autonomous delegation. Searches online for resources, tools, packages, patterns, and solutions needed by the…Jul 2026
- 35phoenix-project-analyzerCONTRIBUTOR TOOL - Analyzes Phoenix projects to discover patterns, pain points, and plugin improvement opportunities. Use this agent when gathering insights from real codebases to identify gaps in…Jul 2026
- 36workflow-external-researcherExternal research agent using Exa MCP for API details, design patterns, and technology evaluationJul 2026
- 37workflow-phase-researcherResearches implementation approach for a specific roadmap phaseJul 2026
- 38workflow-project-researcherDomain research for project initialization, spawned with different focus anglesJul 2026
- 39workflow-research-synthesizerMerges multiple researcher outputs into a unified research summaryJul 2026
- 40review-methodologyChecks empirical claims, causal language, identification strategy, and robustness discussionJun 2026
- 41researcherDeep codebase exploration and analysis. Use for understanding code architecture, finding patterns, and gathering context before making changes.Jul 2026
- 42researcher-agent**Type**: `researcher-agent` **Role**: Codebase exploration and prior art research **Spawned By**: Issue Orchestrator **Tools**: Codebase read, web search, Context7, BEADS CLIJun 2026
- 43research-expert微观伤疤打捞器 (原调研专家)。深度挖掘主题背后的极度微观细节、生活伤疤与行业隐秘代价，并同步建立事实证据账本。由工作流导演在 Stage 2 显式调用。Jul 2026
- 44topic-research选题调研专家。验证选题是否值得写，提供热点扫描、爆款拆解、痛点验证和选题打分。由工作流导演在 Stage 0b 显式调用。Jul 2026
- 45researcherUse this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering…Mar 2026
- 46nyc-zoning-expertNYC property and zoning specialist. Orchestrates due-diligence lookups (landmarks, DOB permits and violations, ACRIS, HPD, BSA), zoning envelope analysis from PLUTO, and 3D envelope visualization.…Jul 2026
- 47product-and-materials-researcherFF&E research specialist. Finds products from a design brief, extracts specs from URLs and PDF catalogs, tags and classifies, and finds alternatives. Use for product search, materials palettes, spec…Jul 2026
- 48paxSenior Researcher. Use proactively for any task that needs cross-source verification before action — hire research briefs (mandatory step in SOP-001), unfamiliar tool/format research before WS-002…Jul 2026
- 49web-researcherTechnical documentation researcher. Looks up API specs, official docs, error codes, version differences, and library usage. Search-only — never writes code, never modifies files. Use whenever the…Apr 2026
- 50sibyl-heavyFully Autonomous AI Research System with Self-Evolution, built natively on Claude CodeMar 2026
- 51sibyl-lightFully Autonomous AI Research System with Self-Evolution, built natively on Claude CodeMar 2026
- 52sibyl-standardFully Autonomous AI Research System with Self-Evolution, built natively on Claude CodeMar 2026
- 53archaeologistKod geçmişi araştırmacısı. Git blame, commit geçmişi ve diff analizi yaparak kodun neden böyle yazıldığını ortaya çıkarır. Kullanıcı bir kodun geçmişini, bir değişikliğin güvenli olup olmadığını veya…Apr 2026
- 54design-scoutUse this agent for competitive UX analysis, design benchmarking, user insight synthesis, design pattern research, accessibility audits of competitors, trend analysis, and inclusion-aware research…Jun 2026
- 55brahma-analyzerCross-artifact consistency and coverage analysis specialist with Anthropic think protocol. Validates alignment between specifications, plans, tasks, and implementation. Use before implementation to…Nov 2025
- 56docs-researcherUse BEFORE writing code that uses an external API, library, or tool not already documented in `.meridian/api-docs/`. Researches via web scraping and builds comprehensive knowledge docs with current…Mar 2026
- 57exploreUse for broad codebase research when you don't know where to look, need to understand "how does X work?", or want comprehensive findings across many files. Returns file paths, line numbers, code…Mar 2026
- 58research-thompson公司调研分析师（Ben Thompson 思维模型）。当需要市场调研、竞品分析、行业趋势判断、商业模式解构、用户需求验证时使用。为战略决策提供深度信息支撑。Feb 2026
- 59outline-explorerFast agent specialized for exploring Outline knowledge bases. Use this when you need to search for documents by keywords, browse collection structures, find specific information across the wiki, or…Jul 2026
- 60researcherResearch analyst for gathering, evaluating, and synthesizing information from multiple sources into evidence-based research briefs.Jul 2026
- 61biostat-assessorClosed-book assessor for the learnbiostats studio. Probes mastery of a module's claims through Socratic, no-notes questioning across Bloom levels, detects misconceptions, bands the result on the…Jul 2026
- 62conf-enrichment-researcherIsolated web-research worker for the conference-scheduling pipeline. Thickens ONE thin or missing session abstract (or a small batch) via targeted web search, gated so already-rich abstracts are left…Jul 2026
- 63literature-scan-coachSearch worker for one keyword query across bioRxiv, medRxiv, PubMed, and arXiv. Spawned by an orchestrator that's running a fan-out (one coach per expanded query).Jul 2026
- 64superforecasterAn elite forecasting agent that orchestrates reference class forecasting, Fermi decomposition, Bayesian updating, premortems, and bias checking. Adheres to the "Outside View First" principle and…Jul 2026
- 65trend-scoutWeekly ML/systems signal radar for substacker. Scans ~30-50 curated intuition-first sources (Olah, Weng, Karpathy, Jay Alammar, Raschka, Willison, Transformer Circuits, Interconnects, arXiv cs.LG,…Jul 2026
- 66domain-reviewerSubstantive domain review for biomedical epidemiology replication scripts and reports. Acts as a senior epidemiology journal referee (NEJM/Lancet/IJE standard).May 2026
- 67codebase-online-researcherDo you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the…Feb 2026
- 68codebase-research-analyzerThe research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise.Feb 2026
- 69thoughts-analyzerThe research equivalent of codebase-analyzer. Use this subagent_type when wanting to deep dive on a research topic. Not commonly needed otherwise.Feb 2026
- 70web-search-researcherDo you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher…Feb 2026
- 71artifact-coherence-auditorAudits coherence between paper prose and replication outputs — catches\Jul 2026
- 72blindspotPeripheral vision audit for empirical output. Finds what the author\Jul 2026
- 73claim-verifyVerify that cited claims in a paper accurately represent what the source\Jul 2026
- 74domain-reviewerResearch-focused substantive correctness agent. Checks mathematical\Jul 2026
- 75gemini-researchWeb research agent that delegates to Gemini CLI in headless mode. Use\Jul 2026
- 76peer-reviewerUse this agent when you need to review someone else's paper — as a\Jul 2026
- 77proposal-reviewerUse this agent when you need to review a research proposal, extended\Jul 2026
- 78referee2-reviewerRigorous adversarial reviewer for papers, manuscripts, research designs,Jul 2026
- 79explorerRead-only subsystem explorer. Use it to map an unfamiliar service or package BEFORE editing — it explores with its own context window and reports back, so the main agent edits with the full picture…May 2026
- 80by-epitopeDeep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot…May 2026
- 81by-epitope-researcherParallel epitope surface analysis. Identifies druggable sites, hotspot residues, scores epitope accessibility and druggability. Lighter-weight than the full by-epitope agent.May 2026
- 82by-prior-art-researcherParallel prior art research via SAbDab, PubMed, bioRxiv, and literature. Finds existing binders, antibodies, nanobodies against the target. Maps the competitive landscape.May 2026
- 83by-researchTarget analysis, literature review, prior art search, epitope identification using PDB, UniProt, SAbDab, and research MCP tools.May 2026
- 84by-research-synthesizerSynthesizes outputs from 4 parallel research agents into a unified target report. Reads target_structures.json, target_sequence.json, prior_art.json, and epitope_analysis.json. Produces…May 2026
- 85by-sequence-researcherParallel target sequence research via UniProt. Identifies canonical sequence, domains, PTMs, variants, functional regions, and druggability indicators.May 2026
- 86by-structure-researcherParallel target structure research via PDB. Finds best resolution crystal structures, identifies chains, interfaces, binding surfaces, and downloads the optimal structure for design.May 2026
- 87scout-agentRead-only codebase exploration and research agentApr 2026
- 88research-assistantTechnical research and documentation specialistJul 2026
- 89domain-reviewerSubstantive domain review for research manuscripts. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity,…Mar 2026
- 90solana-researcherDeep research specialist for Solana ecosystem. Performs comprehensive investigation of protocols, SDKs, APIs, and blockchain patterns with systematic methodology and evidence-based analysis.\n\nUse…Jun 2026
- 91web-research-specialistResearch technical topics by searching the web — debug errors, compare solutions, find best practices from GitHub issues, Stack Overflow, documentation, and community resources.Jul 2026
- 92finding-extractorExtracts atomic, testable findings from a single research paper. Invoked alongside lite-drafter and metadata-extractor during /paperloom:ingest.Apr 2026
- 93finding-linkerCompares new findings against a shortlist of existing findings in the vault and proposes typed edges (supports / contradicts / extends / uses / similar-to). Invoked by /paperloom:ingest.Apr 2026
- 94metadata-extractorExtracts paper metadata (authors, date, venue, fields, DOI/arxiv ID) and a paper-quality assessment (credibility, experimental rigor, reproducibility) from a paper's plain text. Invoked alongside…Apr 2026
- 95genesis-researcherDeep research agent with full web + code intelligence. Use for any task requiring web fetching, searching, codebase exploration, or multi-source synthesis. Prefer this over generic Explore agents for…Jul 2026
- 96research-scoutAnswers questions about an API, library version, CLI flag, config option, or current best practice by checking the installed environment first and then version-matched official docs — never from…Jul 2026
- 97grainulatorAutonomous research sprint subagent. Executes multi-pass research, adds claims, compiles, and generates output artifacts without user intervention.Apr 2026
- 98gsd-advisor-researcherResearches a single gray area decision and returns a structured comparison table with rationale. Spawned by discuss-phase advisor mode.Jul 2026
- 99gsd-phase-researcherResearches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.Jul 2026
- 100gsd-project-researcherResearches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.Jul 2026
