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.
-
tomevault-io Bundle ObsidianUse the official Obsidian CLI (v1.12+) to manage vaults, notes, daily notes, search, tasks, tags, properties, links, templates, sync, publish, and workspaces. Use when the user mentions Obsidian, vaults, notes, or wants to automate note-taking and knowledge base workflows. Use when this capability is needed.
-
tomevault-io Bundle BipUnified guidance for using the bipartite reference library CLI. Use when searching for papers, managing the library, or exploring literature via S2/ASTA. Use when this capability is needed.
-
tomevault-io Bundle Mcouthon Agents AgentsSummarize Task to Architectural Decision Record
-
tomevault-io Bundle Generate ChangelogGenerate a changelog from conventional commits in this repository. Use when asked to generate, create, or update a changelog, release notes, or summarize changes between versions/tags/refs. Handles both top-level conventional commit prefixes and conventional commits embedded in squash merge commit bodies. Use when this capability is needed.
-
tomevault-io Bundle Workspace DigestSummarize the files saved in this assistant's shared workspace. Use when the user asks what is in their workspace, for a file inventory, or a digest of saved work. Use when this capability is needed.
-
tomevault-io Bundle IssueRead a GitHub issue, summarize it, and create a branch for it Use when this capability is needed.
-
tomevault-io Bundle ResearchArchaeological rescue skill for abandoned projects. Reconstructs lost context through git archaeology, timeline analysis, and mission extraction. Use when this capability is needed.
-
tomevault-io Bundle Agtx ResearchExplore the codebase to understand a task before planning. Write findings to .agtx/research.md and stop. This is a read-only exploration — do not modify any files. Use when this capability is needed.
-
tomevault-io Bundle Aide LabUse when documenting environment acquisition, lab state, bootability, blockers, or snapshot-oriented research records.
-
tomevault-io Bundle Huntly Knowledge BaseThis skill should be used when the user asks about their saved content, bookmarks, starred articles, highlights, reading history, tweets, or knowledge base in Huntly sqlite database. Triggers include "我的收藏", "知识库", "我保存了什么", "my bookmarks", "my library", "what did I save". Use when this capability is needed.
-
tomevault-io Bundle CitationsAutomatically adds user-provided links and citations to docs/research/references.md. Use this skill whenever the user shares a URL, paper, blog post, or external reference that should be recorded. Use when this capability is needed.
-
tomevault-io Bundle Integration Hazard ResearchProtocol Type Trigger NAMED_EXTERNAL_PROTOCOL (detected when recon finds import/interface for an identifiable external protocol — not standard libraries). Researches known integration hazards of the target protocol. Use when this capability is needed.
-
tomevault-io Bundle Open PrReview current-branch changes and open a GitHub pull request using gh. Use when the user asks to open/create a PR, prepare a PR title/body, or summarize changes for review. Use when this capability is needed.
-
tomevault-io Bundle Implement Paper AutoImplement a research paper in a marimo notebook fully automatically without extra user input. Use when this capability is needed.
-
tomevault-io Bundle UX ResearcherExpert in user research, usability testing, feedback analysis, and user-centered design Use when this capability is needed.
-
tomevault-io Bundle Ito ResearchConduct structured research for feature development, technology evaluation, or problem investigation. Use when the user needs to explore options, analyze trade-offs, or investigate technical approaches. Use when this capability is needed.
-
tomevault-io Bundle SuperplanUse when starting significant features, epics, or complex tasks. Creates multi-phase implementation plans with parallelizable phases, poker estimates, TDD-first acceptance criteria, and quality gates. Detects tech stack from CLAUDE.md/AGENTS.md (bypassing internet research if complete) or via codebase scan.
-
tomevault-io Bundle Brd Researchresearch phase for a BRD design issue — explores the codebase and documents findings before proposing solutions Use when this capability is needed.
-
tomevault-io Bundle Planning With FilesImplements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session recovery after /clear. Use when this capability is needed.
-
tomevault-io Bundle Pi CrewMUST be read before using crew_list, crew_spawn, crew_respond, crew_done, or crew_abort. Use to delegate bounded research, review, coding, or testing to non-blocking background subagents that run in isolated sessions while your session stays interactive; you own decomposition, scope, result vetting, and final synthesis. Use when this capability is needed.
-
tomevault-io Bundle Jira DailyGenerate smart standup reports from Jira activity and git history. This skill should be used when users want to prepare for daily standups, generate activity reports, or summarize recent work across Jira tickets and git commits. Use when this capability is needed.
-
tomevault-io Bundle Project ManagerManage GitHub issues and the GitHub Project board for the current repository, while keeping the local tracker in sync. Use when the user wants to capture freeform requirements as issues, flesh out issue descriptions from repo or upstream research, triage Priority/Size/Workflow/Status, add issues or PRs to the repo's configured project board, or reconcile GitHub state with `.local/work-items.yaml`. Use when this capability is needed.
-
tomevault-io Bundle Cc WikiDistill the user's `~/.claude` history into a Quartz knowledge base. Runs preprocess.py, dispatches parallel project-digest agents, then parallel cross-cutting synthesis agents (people / companies / projects / concepts / workflows / tools / playbooks), writes the spine, installs Quartz, and starts the dev server. Single command, no flags required. Use when this capability is needed.
-
tomevault-io Bundle ResearcherResearch analyst in a multi-bot group chat — synthesizes background information, fact-checks claims, identifies knowledge gaps, and suggests next steps. Use when the conversation needs context, a factual claim needs verification, someone asks for background research, or a discussion lacks supporting evidence. Use when this capability is needed.
-
tomevault-io Bundle Web BrowseWeb browsing capability for agents to research and find information. Allows fetching web pages with JavaScript rendering, capturing screenshots, and extracting text content. All browsing is sandboxed and internal network access is blocked. Use when this capability is needed.
-
tomevault-io Bundle Omics Target Evidence MapperAggregate public target-level evidence across omics and translational sources for research triage. Use when this capability is needed.
-
tomevault-io Bundle Q IntroDraft or refine introduction sections for academic manuscripts from phenomenon to theory to contribution. Use for writing introductions, literature framing, or research question development. Use when this capability is needed.
-
tomevault-io Bundle Knowledge Priming RefinerFacilitate a structured conversation to create a project-specific knowledge base document. Produces a knowledge-base.md that primes AI with the project's tech stack, architecture, trusted sources, and project structure. Use when the user says 'set up knowledge base', 'prime the project', 'onboard AI', 'create knowledge base', 'set up project context', or 'configure AI context'. Use when this capability is needed.
-
tomevault-io Bundle Nexus MapperGenerate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling reliable cold-start AI sessions across a team. Produces INDEX.md, systems.md, concept_model.json, git_forensics.md and more. Requires shell execution and Python 3.10+. For ad-hoc file queries or instant impact analysis during active development, use nexus-query instead. Use when this capability is needed.
-
tomevault-io Bundle SummarizeSummarize content from files, URLs, or clipboard text into concise structured notes Use when this capability is needed.
-
tomevault-io Bundle Web Research Expert你的目标是利用 `web_search` 和 `web_extract` 这两个工具,以**最少的 Token 消耗、最精准的方式**为用户获取高质量信息 Use when this capability is needed.
-
tomevault-io Bundle Todo GithubCreate, update, and access task lists as GitHub issues for this repo using GH CLI; use when asked to research repo context and turn a checklist into issues. Use when this capability is needed.
-
tomevault-io Bundle Research SynthesizerOwnPilot official general skill for turning mixed research material into concise, sourced briefs, comparisons, decisions, and next steps. Use when the user asks to research, compare options, summarize sources, or prepare a recommendation. Use when this capability is needed.
-
tomevault-io Bundle Depth SearchDeep multi-source research combining academic MCPs (arxiv, semantic-scholar, paper-search, deepwiki), Exa semantic search, and local ~/.topos knowledge base. Use for comprehensive research requiring multiple sources. NEVER fall back to web_search - ask user for help instead. Use when this capability is needed.
-
tomevault-io Bundle Rjroy Vibe Garden Research---
-
tomevault-io Bundle High Impact Journal PublishingGuidance and workflow for planning, writing, submitting, revising, and publishing scientific manuscripts in high-impact journals. Use when Claude needs to advise on research quality, study design, manuscript structure, journal selection, peer review responses, or publication strategy. Use when this capability is needed.
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 obsidian, bip, mcouthon--agents--agents. 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.