Research & Search

zjunlp Bundle

Induce an instruction-derived scientific goal skeleton from a research task before reading literature, web sources, data details, code, or prior results. Use at the start of AutoSciRub when Codex needs atomic, traceable goals that state what the task should address without prescribing methods or metrics.

abijith-suresh Bundle

Clones canonical source and reads the actual API before implementing against a framework or library. Use when implementing against unfamiliar APIs or libraries.

alexvtejeda Bundle

Use when the user wants to research or learn a topic before forming a firm opinion — "I want to learn about X", "help me research Y", "gather a reading list / resources / a study path on Z", "I'm new to X and want to understand it deeply", "convene a research council on X". The research/study front end over the elenchus-council engine. NOT for stress-testing a concrete build/architecture premise the user already intends to construct (that's elenchus-build), and NOT for a one-shot factual lookup (a single search answers those).

wjgoarxiv Skill

Systematic multi-database literature survey. 3 researchers cover non-overlapping sources (databases, time periods, or methodologies) with citation-chain knowledge transfer. TRIGGER when: user wants a literature survey, systematic review, paper survey, wants to cover multiple databases or time periods. DO NOT TRIGGER when: user wants to optimize a metric (use autoconference) or read a single paper (use scientific-reading).

youkistudios Skill

Close an existing source-attributed Session Save record with a human summary and technical resume state. Use when the user asks to summarize, close out, or preserve a finished session. Not a mid-session checkpoint.

yuque Skill

Summarize a Yuque document or knowledge base at one-line, key-point, or detailed granularity. Use when the user wants a quick overview of a document or repo; trigger phrases include “帮我总结一下这篇文档”, “这个知识库讲了什么”, and “summarize this doc”.

yuque Skill

Scan a Yuque knowledge base for stale or outdated documents and recommend updates or archiving. Use when the user is cleaning up, maintaining, or periodically reviewing a knowledge base; trigger phrases include “帮我检查哪些文档过期了”, “知识库体检”, and “find stale docs”.

nbsp1221 Bundle

Use when a founder has a rough product idea and wants autonomous deep validation, market and competitor research, and an evidence-based MVP decision with minimal back-and-forth.

nbsp1221 Bundle

Use when investigating a repository that is not already available locally and the user needs repository-specific understanding of its structure, implementation, maintenance, or relevant files.

oimiragieo Bundle

Call this before reading any file path, URL, or document that could be large. This is the preferred tool instead of the Read tool whenever the target is a file or URL — not a short inline snippet. Use for every request phrased as "read /path/to/file", "summarize this document", "what does X say about Y", "give me the key points of /path/X", "help me understand this file", "explain the content at URL", "find section X in document Y". Compresses source by 60-90% via gotcontext.ai's PageRank semantic compression, then feeds only the compressed skeleton into Claude's context. The Read tool still fits active-editing workflows on files you already know are short; for everything else with a path or URL target, this skill is the right call.

qjhwc Bundle

引文缺口识别技能。用于在当前 draft 中找到最需要补的一条 citation 缺口，并产出 query。

qjhwc Bundle

文献候选筛选技能。用于从候选搜索结果中选择最适合写入当前论文的一组引用。

qjhwc Bundle

Writes ML/AI review and survey papers for arXiv using the IEEEtran LaTeX template with verified BibTeX citations. Triggers when the deliverable is a review paper, literature survey, or when an existing LaTeX project needs citation validation or repair.

skills-router Bundle

Convert articles, papers, GitHub repositories, and various content sources into professional videos. Use when users want to transform text content (URLs, documents, code repositories) into video format. Handles research, scriptwriting, scene planning, and Remotion-based video generation. Triggers on requests like "convert this article to video", "create a video from this paper", or "make a video about this GitHub project".

adamos486 Bundle

Use 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.

posthog Skill

Summarize what needs attention in one GitHub repository: open pull requests, the review queue, failing checks, stale work, and what merged recently. Use at the start of a work session to decide what to pick up next.

priority3 Bundle

Read Gemini shared conversation links and extract the rendered chat into structured text. Use when users provide `https://gemini.google.com/share/*` or `https://g.co/gemini/share/*` and ask to read, summarize, archive, migrate, or analyze the shared conversation content. Triggers: Gemini/分享链接/对话内容/gemini share.

agents-on-rails Skill

Search your evidence-graded knowledge base (personal or work) and get back only trustworthy claims, each stamped with its trust label. Thin wrapper over the OKF-E kb_query CLI. USE PROACTIVELY, not only on request — BEFORE designing, debugging, or deciding in a domain past sessions may already have paid for (build and release tooling, environment quirks that keep recurring, dependency pinning, past incidents, and per-repo topics named after the repo), query first and re-derive second; the live topic list is kb/index.md. Also fires on "what do we know about X", prior lessons, past findings.

daisybastioned440 Bundle

Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.

daisybastioned440 Skill

Core research principles that govern all project decisions. Load this skill for every research project. Every idea, method, and artifact must be evaluated against these principles before proceeding.

daisybastioned440 Skill

Defines the structure and requirements for a research proposal.

derivativelabs Skill

Generate and maintain research-driven brand artifact library. Coach personas are always derived from real forum research — never invented. Living docs that evolve as research and performance data come in.

felixgraeber Skill

Route or run comprehensive App Store Optimization work for iOS and Android. Use for full listing audits, multi-area ASO requests, or when the user does not name a more specific ASO task. Covers keyword research, metadata, visuals, reviews, competitors, localization, testing, technical health, compliance, conversion, launch planning, and seasonal optimization.

felixgraeber Skill

Research and improve app-store keywords, metadata, localization, and seasonal listing changes for Apple App Store and Google Play.

fireredteam Skill

【META SKILL】分析当前剪辑逻辑与风格，总结并生成一个新的可复用 Skill 文件，存入剪辑技能库。Analyze the current editing logic and style, summarize and generate a new reusable Skill file, and store it in the editing skill library.

halukerenozlu Skill

Summarize text content files documents

agent-sh Skill

Research any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning guide', 'build knowledge base', or 'study subject'.

alphamao1 Bundle

把 X/Twitter 博主、YouTube 博主、newsletter、播客或类似个人信息源的持续更新转成 progressive-investment-research 研究工作区的可审计增量。适用于：跟踪博主更新、生成每日报告、通过 Chrome 登录态或本地 browser bridge 抓 X、用 yt-dlp 抓 YouTube 字幕、把观点拆成 source leads、公司页、行业模块、open questions 和后续研究任务。Serenity 和 RihardJarc 是内置信息源案例，不依赖 PaiWork 专有工具。

dcramer Skill

Deep research across multiple sources with synthesis and citations

dcramer Bundle

Manage Gmail and Google Calendar with capability-backed auth and operations. Use when asked to check inbox, summarize emails, give a day at a glance, send an email, review calendar events, or schedule meetings.

simplevaad-debug Skill

This skill should be used when the user needs deep, multi-step research using native web tools (WebSearch/WebFetch) without external API keys.

percival-labs Bundle

General-purpose web research with configurable depth. USE WHEN research OR look up OR find out OR what is OR deep dive OR compare options OR investigate. Supports quick lookups, deep dives, and comparative analysis.

rivo2026 Bundle

组织西方社会学、哲学、传播学、心理学与消费研究人物的模拟圆桌，通过独立研究、交叉质询和主持人审议共同研究问题，并支持追问、知识地图与持续学习。用户想让多位思想家讨论、比较理论解释、深入研究问题或继续研究圆桌时使用。简单释义和用户明确要求的单人讲解可直接回答。

searchcans Bundle

使用 SearchCans SERP API 和 Reader API 执行有界、证据驱动、账户感知的中文深度研究。适用于需要当前、地域化、可引用网页证据的市场、竞品、技术、政策、公司或产品问题；先规划 3–5 个子问题，设置来源预算，读取来源、处理冲突，并交付可追溯 URL 的研究简报。

searchcans Bundle

Conduct bounded, evidence-led, account-aware web research with SearchCans SERP API and Reader API. Use for cited-source research that needs current localized web evidence, such as market, competitor, technology, policy, company, or product research; plan 3–5 subquestions, set a source budget, read selected pages, reconcile conflicting claims, and deliver a claim-ready brief with traceable URLs.

skillmedev Skill

Prepares a candidate for a specific job interview - company research checklist, a STAR story bank mined from their resume and mapped to common competencies, a questions-to-ask bank, salary-question deflection lines, and a mock-interview loop. Use when a user says "I have an interview next week, help me prepare", "help me practice answers for this interview", "what should I ask the interviewer", "build me STAR stories from my resume", or "they're going to ask about salary, what do I say". Do NOT use for negotiating after an offer arrives - use salary-negotiation instead - and do NOT use for fixing the resume itself - use resume-reviewer instead.