Research & Search

dexhunter Skill

Publish research papers to clawRxiv. Use when you want to share research findings, analyses, or technical write-ups to a public academic archive for AI agents.

jmagly Skill

Induct research sources (issue, file, directory, or URI) into a research corpus — reads, annotates, and files structured induction tasks. Like address-issues but for research.

lessieai Bundle

Search, qualify, and enrich people and companies. Use this skill whenever the user wants to find professionals, candidates, or KOLs by title, company, location, seniority, or audience; enrich known contacts with email, phone, or LinkedIn; research companies for industry, funding, tech stack, or hiring activity; look up someone's contact info; source candidates for recruiting; generate B2B lead lists; or perform background web research on people or organizations. Trigger this skill even when the user doesn't explicitly say "search" or "enrich" — any mention of finding contacts, sourcing, prospecting, looking up a person or company, or gathering business intelligence should activate it.

maxxit-ai Bundle

Maxxit trading powered by 0G decentralized AI compute for portfolio-aware trade decisions and 0G decentralized storage for censorship-resistant alpha listings. Includes all DEX trading, market research, copy-trading, and alpha marketplace workflows from maxxit-lazy-trading.

neoflux-ai Bundle

Use when the user provides files or attachments to keep, organize, synthesize, or update through Corvio; or when work involves research, reports, comparisons, recommendations, proposals, plans, decisions, meeting notes, project work, debugging, reviews, follow-ups, or prior material. Before committing to a plan or answer, you MUST make one Corvio read relevant to that work while keeping the host's normal files and tools. Save or update only results worth sharing or revisiting. Also use for installing, connecting, updating, or repairing Corvio, and for workspace, @Corvio, 调研、报告、对比、选型、方案、计划、决策、纪要、复盘、之前的资料、继续上次、那份文档、共享、同步给团队、沉淀. Do not invoke Corvio for sensitive, disclosure-unclear, explicitly local-only, or unavailable work; one-off is a no-write boundary, not a reason to skip an otherwise relevant read.

riftwerx Skill

Workflow guide for using company-research as a CLI tool via Bash

taewooopark Bundle

Massive multi-source academic literature search via subagent orchestration. Fans out parallel searchers across every available scholarly source — arXiv, Semantic Scholar, Crossref, OpenAlex, PubMed/PMC, bioRxiv/medRxiv, DOAJ, CORE, BASE, DBLP, IACR, SSRN, Zenodo, Unpaywall, plus web/GitHub — then deduplicates by DOI/arXiv-id/title into one ranked corpus and synthesizes it. Use when the user wants a broad/exhaustive literature sweep, a large-scale paper search, a systematic review corpus, citation snowballing, or to find as many papers as possible on a topic across many databases at once. Triggers: "massive literature search", "literature review", "search across every database", "systematic search", "mega search", "search every source", "exhaustive search". Localized trigger phrases in other languages map to the same intent.

liangdabiao Skill

Add citations to research reports. Use after deep-research completes to add proper source citations.

liangdabiao Skill

Conduct deep research on any topic using parallel subagents and web tools (web_search, web_fetch, playwright). Use for queries that require comprehensive research from multiple perspectives.

stotihv Bundle

Extracts knowledge from Amp threads and updates project docs. Use when asked to document recent work, sync docs after an epic, summarize what changed, or update AGENTS.md from thread history.

block Skill

Search GitHub issues, PRs, and code using the gh CLI.

agilkannan Bundle

God-level internet research and data synthesis for any topic. Use when the user wants to research, compare, analyze, or find the best options for anything: business ideas, products (phones, laptops, gadgets), services (credit cards, banks, insurance), travel (hotels, flights, destinations), market trends, industry data, competitor analysis, pricing comparisons, consumer reviews, emerging opportunities, or any general-purpose research task. Triggers on: 'research', 'find the best', 'compare', 'what's the best', 'top 10', 'under X price', 'market data', 'industry trends', 'alternatives to', 'reviews of', or any request requiring internet research and data gathering.

mememeow-studio Bundle

Research evidence-backed structured representations of image memes, including visible subjects, caption text, templates, references, origins, current meaning, and uncertainty. Use when Codex must investigate a meme image with web or reverse-image search, trace a quoted caption or visual reference, assess candidates from online results, or produce cited meme metadata whose meaning may be time-sensitive.

jlevy Skill

Check whether the upstream Python flowmark has a newer release than the Rust port's parity baseline, summarize what changed, and produce a proposed port/sync plan for review. Use when opening flowmark-rs, when the user mentions syncing or porting a new flowmark version, an upstream release, the parity baseline, or asks "what changed upstream" / "are we up to date with Python".

ory Skill

Run a health check on the bundled Lumen semantic search setup for the current project, verify backend reachability and index freshness, and summarize remediation steps.

sopaco Bundle

Project knowledge base for coding agents. Activate when: (1) starting a new session in this project, (2) encountering unfamiliar code patterns or architecture decisions, (3) user asks about project design or rationale, (4) before making significant structural changes. Contains tiered knowledge from stable design principles to dynamic issues.

xerrors Skill

深度研究编排方法论：澄清范围、拆解规划、并行调度子智能体调研、对抗式核验、综合成带引用的结构化报告。当任务需要多来源、可追溯、需事实核查的深度研究时使用此技能。

duskyelf Skill

A research companion that builds a source-backed literature review with consensus, tensions, and gaps. Use when user triggers /literature-review [topic|question], wants academic grounding, or needs a high-quality source map before a learning session.

ethpandaops Skill

Create a new Ethereum data investigation page in the notebooks repo. Use when the user wants to add a new investigation, analysis, or research page that queries Xatu/ClickHouse data and visualizes findings with charts.

evex-dev Bundle

Inspect Popopo Unity AssetBundle compatibility using an app build from the user's own device or a developer-provided APK. Use when Codex needs to document the bundle format, reproduce client-side loading behavior with Cpp2IL, verify the key material used by a local build, or validate locally accessible Windows, macOS, Linux, Android, and iOS bundles on Windows, macOS, or Linux.

chris-hendrix Bundle

Consolidated research-plan-review-implement workflow. Use when the user wants to research or explore solutions, create an implementation plan, review a plan or artifact, implement from a plan, hand off work to another session, pick up a handoff, write output to .rpi/, or grill a plan/design through relentless interviewing. Keywords: research, plan, review, implement, handoff, pickup, write, grill.

cite-me-in Skill

Use when writing or editing a blog post optimized for AI citations — covers post structure, frontmatter patterns, content rules, schema requirements, and a pre-publish GEO checklist based on Princeton research. Do NOT use for social media posts, landing pages, general content writing, or non-blog formats.

andrewii23 Bundle

Watch and fully understand any video — local file or URL — by packing its frames into grid images (many scenes per image, ~7x cheaper than reading frames one by one) and pairing them with a timestamped transcript. Use this whenever the user wants a video watched, summarized, explained, spoiled, recapped, searched, or asked questions about — "what happens in this video", "summarize this clip", "สปอยคลิปนี้", "ดูวิดีโอนี้ให้หน่อย", "recap this episode", "what did they say at 3:20", "find the part where X happens", "อธิบายคลิปนี้" — or when they paste a video path/URL and ask anything about its contents. Also use for reviewing footage, checking what is on screen, or locating a moment. Do NOT use for editing, cutting, rendering, or generating video.

antdv-next Bundle

Create pull requests for antdv-next/cli using the repository's PR conventions. Use this skill when the user asks to create/open a PR, draft PR title/body, summarize branch changes for a PR, or otherwise prepare PR content. Judge by intent rather than fixed phrases; short colloquial requests still count if they are about creating a PR rather than discussing PR concepts.

aspectrr Bundle

Prospect Rapport Research

assafkip Skill

Scan LinkedIn profiles for VC signals. Use when the user wants to check LinkedIn for investment signals. Requires user presence to watch the browser.

atomchung Bundle

Help with investment decisions and explicit candidate searches — research, discover, compare, rank, and recommend with or without a recorded book, reading the user's own notes first when installed in their investing folder. Use for buy, add, reduce, trade-review, brokerage-statement, and position-review decisions. A book adds engine-computed portfolio consequences. Never claim unsupported portfolio facts or execution.

ayanami0730 Bundle

Deep analysis of AI research papers with type-specific prompts. Covers benchmark papers, methodology papers, and survey/position/blog posts. Use when the user asks to read, analyze, review, or summarize a research paper, or mentions 论文分析、论文阅读、paper review、benchmark analysis、方法论分析.

elnora-ai Skill

Routes any web task to the best-fitting search provider (Exa, Tavily, Perplexity, Firecrawl, Valyu). Use when the user asks to "search the web", "look up online", "find information", "research", "deep research", "scrape a page", "extract content from a URL", "crawl a website", "find papers", "find companies", "find people", "fact-check", "get a cited answer", "monitor a page", or asks meta-questions like "which search tool should I use", "what web search do we have", "compare search providers", or when multiple web providers could serve the same request and one must be chosen.

yuanasi Bundle

自动生成每周复盘周报（对内复盘 + 对外公开周记），从 Claude Desktop（Cowork + Code tab）和 Claude Code 终端 CLI 的全部对话记录中提取本周所有工作内容。 当用户提到以下场景时必须使用此 skill：写周报、生成周报、本周总结、每周复盘、weekly review、week recap、 summarize this week、周记、对外周记、对内周报、本周做了什么、回顾本周。 即使用户只是说"帮我写周报"、"总结一下这周"或"what did I do this week"，也应自动触发。

zaious Bundle

Academic journal fit assessment and submission strategy. Use when a researcher describes their paper and needs journal recommendations, when they ask which journals to submit to, when they want to compare specific journals head-to-head, or when they've been rejected and need fallback options. Knowledge base of per-journal soft metadata (reviewer culture, framing requirements, sensitive topic tolerance, rejection fallback chains) lives in references/journals/. Community-maintained, AI-native, supports rejection recovery and journal comparison.

a1st-dev Skill

Use when auditing supported editor release notes, checking whether aix editor integrations are stale, or creating a plan to update aix docs and implementation for editor config changes.

aliasunder Bundle

Plan a real trip. Use for: hotel/flight/train/restaurant research for specific destinations and dates, creating travel documents (daily cards, itineraries, packing lists, offline guides), managing booking changes or cancellations, and resuming a trip project with CLAUDE.md/TASKS.md/memory/ files. Handles the full lifecycle — transport, accommodation, activities, restaurants, budget tracking, and printable traveler materials. ALWAYS use this skill in a trip planning project — detected by a CLAUDE.md with traveler profiles, an itinerary phase marker, or a memory/ directory with trip planning files. Also trigger on "plan a trip", "start a session", "research hotels", "find restaurants", "build the itinerary", "make daily cards", "create packing list", or any travel planning task. NOT for: presentations, file conversions, sending emails, building apps, or hypothetical travel questions.

blu1606 Bundle

Generate, grade, and adapt Vietnamese AI practice exams from a knowledge base. Use for de on tap, mock exam, MCQ, multi-select, fill-in-blank, rubric grading, and updating learner knowledge profiles.

crafter-station Bundle

Turn a recorded talk, workshop, meetup, or conference session into a series of engineering blog posts for the crafter.run blog, optimized for search and for citation by AI assistants. Use when given a YouTube URL and asked to write posts, articles, or a blog from it, or when asked to reuse existing recordings as content. Triggers include "turn this talk into a blog post", "write an article from this video", "we have recordings, make blog posts", "distill this workshop", "repurpose this meetup".

cyrusnuevodia Bundle

Initialize gepa-research for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment. Use when the user invokes /gepa-research:discover, mentions setting up gepa-research, wants to instrument a codebase for autonomous optimization, or asks to start a new gepa-research run on a project.