Research Claude Skills
2 269 research skills from 396 authors. They find sources and get you up to speed on unfamiliar ground. Half of them fit into 2 278 tokens or less — that is what one costs your context window when the agent loads it. 663 ship runnable scripts rather than instructions alone. 4 of them cannot work without an MCP server, most often rube. We also found 291 copies of these same skills sitting in other people's repositories — counted once here, not 291 times.
2 269 unique 396 authors 3 updated this month 93 from vendors
四源同级：Brave (`web_search`) + Exa + Tavily + Grok。按意图自动选策略、调权重、做合成。 DEFAULT search tool for ALL search/lookup needs. Multi-source search and deduplication layer with intent-aware scoring. Integrates Brave Search (web_search), Exa, Tavily, and Grok to provide high-coverage, high-quality results. Automatically classifies query intent and adjusts search strategy, scoring weights, and result synthesis. Use for ANY query that requires web search — factual lookups, research, news, comparisons, resource finding, "what is X", status checks, etc. Do NOT use raw web_search directly; always route through this skill.
Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.
Analyze Google SERP (Search Engine Results Pages) — featured snippets, PAA (People Also Ask), AI Overview, knowledge panels, local packs. Detect AI Overview trigger conditions and optimize content to be cited by AI. Use when user asks to 'analyze SERP', 'check search results', 'AI Overview analysis', 'featured snippet optimization', 'PAA research', or 'how to get cited by Google AI'.
You are an expert market researcher who uses LLM-generated synthetic survey responses and Semantic Similarity Rating (SSR) to produce fast, cheap, dir Fast, cheap market research using LLM-generated synthetic survey responses with Semantic Similarity Rating (SSR). Runs purchase intent, concept tests, and pricing research in minutes instead of weeks, at $0 per respondent. Based on PyMC Labs' validated methodology (90% correlation with real humans purchase intent, concept test, consumer research, SSR, synthetic survey, product validation, pricing research, Likert scale.
Use when the user wants to research, compare, or evaluate a technology, framework, platform, or engineering tool for product R&D decision-making, such as "调研 FastAPI", "技术选型", "compare Spring Boot vs NestJS", "写 ADR", "评估是否适合", "PoC 方案", or "technology radar".
蒸馏David Ogilvy思维模式的实用框架——广告教父、调研驱动、大创意、品牌形象
Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth. Use when writing documentation, generating wiki pages, creating tech...
| Delegate tasks to AI agents via Box0. Use when the user asks to review code, check security, run tests, compare tools, get multiple perspectives, research a topic, analyze data, write docs, or any task that could benefit from specialized or parallel execution. Also use when the user mentions agent names or says "ask", "delegate", "get opinions from", or "have someone".
Analyze HitKeep AI visibility data. Use for AI crawler fetches, AI-referred visits, assistant names or families, citation yield, resource types, top paths, fetch failures, Search Console context, GPTBot, ClaudeBot, ChatGPT, Claude, Perplexity, AI search, or whether assistants are discovering and sending traffic to a site.
CRE Legal review suite — 6 specialist skills for PSA review, title & survey analysis, estoppel tracking, loan document review, insurance coordination, and transfer document preparation for multifamily acquisitions.
Creates and edits Dark Sky Conservation policy documentation for Maharashtra government officials and academics. Handles audience-appropriate tone, section-specific content rules (Research/Policy/Pilots), and orchestrates technical validation passes. Use when working on docs/content/ markdown files.
>- Rigorous multi-agent deep-dive analysis for complex investigative tasks — auditing codebases, evaluating strategies or systems, validating designs, doing open-ended research. Deploys 4–6 specialist agents in parallel across distinct lanes, then synthesis, then adversarial red-team review, then optional patching — producing structured markdown research files plus a plain-English executive briefing with honest 1–10 confidence ratings. ALWAYS invoke when the user says any of "deep dive", "thorough audit", "rigorous analysis", "comprehensive review", "audit this codebase", "analyze the strategy", "evaluate this design", "review this thoroughly", or "research deep dive". Also invoke proactively for any open-ended investigative task involving a codebase, strategy, system design, or research question that warrants 30+ minutes of structured analysis — even when the user doesn't use these exact phrases.
Use when the user is considering applying to, interviewing with, or accepting an offer from a company and wants due diligence on the company and optionally a specific role. Requires a company name, optionally a job title, then researches current public data, employee reviews, salary signals, product/tech quality, and red flags before giving a grounded recommendation. NOT for generic career coaching or resume editing.
Classify academic papers and documents into subject categories using keyword-based text analysis.
Implements the SimPO (Simple Preference Optimization) loss function from the paper "SimPO: Simple Preference Optimization with a Reference-Free Reward". Use this when implementing or understanding SimPO training objectives.
Look up arxiv paper metadata (title, abstract, subject) from arxiv IDs to classify papers by topic without reading full PDFs.
Guidelines for implementing the SimPO loss function as per the SimPO paper.
Complete SimPO loss implementation with exact formula derivation from the paper.
Classify academic papers into subject categories using weighted keyword matching with regex word boundaries and case-insensitive search.
Complete setup guide for reproducing NLP paper results with HuggingFace TRL/transformers on Python 3.12 - use when setting up environments for preference optimization experiments.
Identify major attractions, points of interest, and notable sites across three Ohio cities that appeal to general travelers. Use this when building activities for a multi-city itinerary.
How to implement the SimPO (Simple Preference Optimization) loss function based on the SimPO paper. Use this when implementing the simpo_loss method in SimPOTrainer.
Use this skill to implement the simpo_loss function in SimPOTrainer based on the SimPO paper. The loss combines a length-normalized reward with a margin gamma and uses BCE loss without a reference model.
Implements the SimPO (Simple Preference Optimization) loss function with length normalization and reward margin as specified in the research paper.
Classifies PDF academic papers by subject area using text extraction from first pages. Use this skill whenever you need to categorize, sort, or organize PDF papers by topic, research field, or subject matter.
Organizes PDF, PPTX, and DOCX academic files into subject folders by extracting and analyzing their title/abstract text. Use this skill whenever the user needs to sort or categorize a batch of research papers or documents into topic-based folders (e.g., LLM, quantum computing, biology, physics, music). Handles arXiv papers and other academic documents automatically.
Procedures for setting up the environment for research projects involving Python, PyTorch, and NLP models. Use whenever environment requirements (environment.yml) are present.
How to reproduce Deep Learning papers. Use this skill whenever the user asks to implement an algorithm, loss function, architecture, or technique based on an academic paper (PDF, Arxiv, etc).
Align Python version and repo-declared dependencies (requirements.txt / environment.yml) before installing packages for NLP research code reproduction.
Create beautifully designed travel guidebook PDFs from trip itineraries. End-to-end workflow from deep research to Playwright PDF export, featuring zero AI-generated images, Tabler Icons, inline SVG decorations, and Claude's warm parchment aesthetic. Use this skill whenever the user mentions 路书, 旅行指南, travel guidebook, 行程手册, trip planner, 自驾游攻略, itinerary book, 攻略, 出行指南, 旅行计划, 行程规划, or wants to turn trip notes into a printable guide. Also triggers for multi-day travel planning, route guides, road trip planners, 旅行攻略制作, 旅行PDF, or converting travel research into a professionally designed document.
Guide for working with Vaultr, an AI-native personal note-taking system. Use this skill whenever the user wants to search, find, read, write, save, create, modify, delete, or capture notes — including journal entries, research notes, quick thoughts, knowledge retrieval, or any note-taking task. Trigger when the user says things like 'save this as a note', 'find my notes about X', 'create a note', 'look up my notes on X', 'read my note about Y', 'delete a note', 'quick note', 'short note', 'what do I know about X', or any variation of managing notes in Vaultr.
Use when a user needs通用中文参考文献、GB/T 7714-style bibliography entries, Chinese academic reference formatting, or BibTeX completion from Chinese or English literature titles, including 根据文献名补全参考文献、生成中文论文参考文献格式、format Chinese academic references.
Quick-understanding doc for ML/DL, AI4Science, and research codebases — task type, stack, architecture, and figure-worthy innovations. Use when the user wants repo analysis, 仓库分析, or to understand a codebase before figure planning.
Plan figures for an academic paper or document — map sections to figure types, count, priority, and aspect ratios. Use this skill whenever the user provides paper text, a PDF, an outline, section drafts, or asks what figures their paper needs, including "论文需要哪些图", "论文配图规划", "paper figure planning", "which figures should my paper have", "帮我规划配图". Produces a Figure Plan with must/strong/nice priorities and per-figure visual elements.
Generate publication-ready figure prompts in the modern pastel/airy ICLR/NeurIPS style with soft panels, tokens, pills, and rounded type. Use this skill whenever the user wants a pastel, airy, soft, or modern ML figure — including "pastel风格", "ICLR那种", "现代柔彩", "airy figure prompt", "token flow diagram", "2024-2025 conference style". Produces a layered English image prompt with P1/P2/P3 color schemes. For classic box-border CVPR/Nature diagrams, route to academic-figure-prompt instead.
Generate publication-ready figure prompts for image models (GPT-Image-2, Gemini NanoBanana, etc.) in the classic academic style. Use this skill whenever the user wants a box-border architecture diagram, framework/network/module figure, or JSON figure spec — including "生成框架图", "画架构图", "JSON配图规范", "academic figure prompt", "框架图JSON". Produces a structured JSON spec AND a 200-400 word English image prompt with icons, dimension labels, and panel grouping. For pastel/airy ICLR-style figures, route to academic-figure-prompt-pastel instead.
Make palette decisions for academic figures — choose between classic and pastel style families, then recommend a colorblind-safe scheme with exact hex values based on venue, domain, figure type, and module count. Use this skill whenever the user asks about colors, palettes, style for a figure, including "用什么配色", "推荐配色", "what palette for NeurIPS", "Nature Blue", "classic vs pastel", "色盲友好配色", or any color-related question about academic diagrams.
Extract and analyze architecture diagrams from academic PDFs or existing figure images. Use this skill whenever the user provides a PDF or image containing an architecture diagram and wants to extract, analyze, or redraw it — including "从PDF提取架构图", "架构图分析", "extract figures from pdf", "architecture diagram extraction", "analyze this diagram". Runs a local PDF extraction script and produces structured redraw parameters for downstream prompt skills.
Entry-point assistant for academic figure generation. Use this skill whenever the user wants to generate academic figures, paper diagrams, or architecture visualizations — including "帮我画图", "从仓库到配图走一遍", "完整论文配图工作流", "帮我分析这个仓库然后出图", or any end-to-end request from code/paper to figure. The assistant analyzes the input, presents a Figure Plan for user confirmation, then generates colors, prompts, and (when an image model is available) the final image. Routes repo-first (code) or paper-first (document/PDF) inputs.
Turn governed source evidence into a citation-bound reader-facing draft, channel package, and provider-neutral publication handoff.
Produce a decision-ready deep-research brief from bounded governed evidence and preserve every material source binding.
Inspect bounded local repository and Runx catalog evidence before a design, draft, or operator decision, then produce citation-bound findings and a reuse, amendment, new-work, or stop recommendation. Use when existing tools, skills, standards, or project patterns must constrain downstream work; use research or web-fetch first for external sources.
Produce bounded, source-backed research packets for product, ecosystem, and operator decisions.
Internal evidence-index analysis and verification stage for the canonical research skill.
Use when the user wants web research: gathering cited, multi-angle evidence on a specific question. Triggers on: \"research X for me\", \"do web research on\", \"look up sources for\", \"find citations for\", \"gather evidence on\", \"what does the web say about X\". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups (\"find this function\", \"search the repo\"), local file search, LLM-as-judge evaluation, or paywalled/auth-gated scraping. Produces a written plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.
面向 Agent 的百度 API 搜索 Skill。用于中文“查一下/搜索/联网查/最近/最新/热点”等场景，调用百度百科和百度 AI Search API，保留原始结果、去重并生成 research pack。