学术
学术写作、研究与引用
Paper Super Reviewer — 论文超审 v3.0
TheeTarnished
Paper Super Reviewer - peer review system
help
cadrianmae
This skill should be used when the user asks for help with tracking, how to use the track plugin, tracking documentation, what tracking commands are available, how hooks-based tracking works, track plugin overview, or explanation of verbosity settings. Displays comprehensive documentation covering commands, file formats, verbosity settings, academic workflow examples, v2.0 architecture, and migration from v1.x.
strategic-analysis
samChang72
麥肯錫等級的商業戰略分析師。提供市場規模（TAM）、競爭格局、客戶畫像、 行業趨勢、SWOT/波特五力、定價策略、GTM 計劃、客戶旅程、財務建模、 風險評估、市場准入與執行戰略綜合等 12 項專業分析框架。 當需要進行商業分析、市場研究、競爭情報或戰略規劃時使用。
ask-many-models
HartreeWorks
This skill should be used when the user asks to "ask many models", "query multiple AI models", "get opinions from different AIs", "compare AI responses", "ask GPT and Gemini", "ask several models", or mentions wanting to send the same prompt to multiple AI models and synthesise the results.
research-spike
gpu-cli
"Conducts time-boxed technical investigations, competitive research, or feasibility analysis. Asks clarifying questions upfront and produces a structured markdown report with executive summary. Use for technical spikes, architecture decisions, or evaluating new technologies."
research
LukasStrickler
"Conduct comprehensive academic research using OpenAlex, PDF extraction, paper search MCPs, and web search. Always produces comprehensive reports with 5+ evidence cards covering conflicting ideas and best approaches. Integrates academic papers (high weight) and non-academic sources (blogs, docs - lower weight but valuable for SOTA). Use when: (1) Researching software architecture patterns, (2) Finding academic papers on technical topics, (3) Conducting literature reviews, (4) Analyzing research papers for evidence-based decisions, (5) Building evidence cards from papers, (6) Finding related works and citations, or (7) When you need grounded, paper-backed technical recommendations. Triggers: research, find papers, literature review, evidence-based, academic research, compare approaches, what does research say, find studies on, search for papers about."
spec
doodledood
"Build requirements specification through structured discovery interview. Use when defining scope, gathering requirements, or specifying WHAT work should accomplish - features, bugs, refactors, infrastructure, migrations, performance, documentation, or any other work type. Triggers: spec, requirements, define scope, what to build."
content-research
atalovesyou
Research-first content creation optimized for both human readers and AI search engines (Claude, ChatGPT, Perplexity, Gemini). Creates authentic, authoritative content that becomes the go-to citation source for AI models answering user questions. Use this skill when: - Creating content that should appear in AI search results (Perplexity, ChatGPT, Claude) - Building topical authority to become THE source AI cites for a topic - Launching a new product and need compelling, citable content - Creating blog posts, articles, social media, or press releases - Need content that references real trends, people, and recent events - Want AI-assisted content that doesn't sound AI-generated - Creating thought leadership content in any industry Triggers: "create content for", "write about", "research and write", "find experts for", "content for launch", "blog post about", "article on", "press release for", "AI search", "show up in AI", "Perplexity", "be cited by AI"
research-web
doodledood
"Comprehensive multi-wave web research with strategic source selection. Gathers information from official docs, community resources, and advanced sources. Use for deep technical research, API documentation, best practices. Triggers: research web, deep research, comprehensive research, find documentation."
web-research
doodledood
"Conduct structured web research with hypothesis tracking. Synthesizes information from multiple sources into actionable findings. Use for technical research, API docs, best practices. Triggers: web research, look up, search for, find documentation."
dialectical-reasoning
kimasplund
Thesis-antithesis-synthesis reasoning for navigating genuine trade-offs and conflicting requirements. Use when opposing forces are both valid, binary choices are false, or stakeholder conflicts need resolution. Unlike ToT (picks winner), DR synthesizes opposites. Example: "Centralized vs decentralized architecture" → Neither is "right"; find synthesis that captures benefits of both.
plan
doodledood
"Create implementation plans from spec via iterative codebase research and strategic questions. Produces mini-PR plans optimized for iterative development. Use after $spec or when you have clear requirements. Triggers: plan, implementation plan, how to build."
gemini-research
otrebu
Web research via Gemini CLI with Google Search grounding. Generates markdown report. Claude MUST append analysis section after. Use for real-time data: news, docs, code examples, fact verification.
refero-design
bbssppllvv
Research-First design methodology using Refero MCP. Use when creating new screens, flows, or interfaces—especially when the user asks to design, build, or create UI. Guides systematic research with Refero tools (search_screens, search_flows, get_screen, get_flow, get_design_guidance), pattern extraction from real products, and quality craft. Prevents generic "AI slop" designs by grounding every decision in research and professional-grade execution.
book-distillation-v6
XCDaHuiGe
"AI Native Research OS / Cognitive Research Engine V6.3。核心升级：(1) Insight Delta Tracking 反伪深度机制；(2) Dynamic Tension Graph 认知张力系统；(3) Uncertainty Engine 不确定性管理；(4) Hypothesis Evolution 观点动态演化；(5) World State Simulation 世界状态模拟。真正的深度来自认知增量的积累，不是页数的堆积。"
validate-bib
clearsmog
Validate bibliography entries against citations in all document files (.tex, .qmd, .typ). Find missing entries and unused references.
index-deep-research-analysis-skills
aierwiki
'基于唐氏深度研究法的 A 股指数天气预报研究 skill。用于在指数研究场景下定义输入要求、首轮研究维度、证据标准、时效纪律、技术验证要求和最终报告格式。唐氏深度研究法的具体流程、轮次设计与发散-收敛执行方式，不在本 skill 中展开，Agent 应先加载 deep-research skill 了解并遵循其随机应变、轮次串行推进、最终兼顾广度与深度的研究方法。触发词：指数深度研究、指数天气预报、唐氏深度研究指数、上证指数研判、沪深300未来走势。'
chaos-seize
Oncorporation
Use when analyzing revolutionary tactics that create or exploit societal disorder to seize power. Draws on Marx, Alinsky, Lenin, Mao, and historical case studies to explain how out-of-power actors disorganize, agitate, and consolidate during instability.
kanban
lambda610
"异步任务管理系统。用于：(1) 添加任务到 inbox，(2) 查看任务进度，(3) 处理 backlog。触发方式：用户说'添加任务'/'task add'/'kanban'或类似表达。注意：只写 inbox，不立即执行任务。Not for: 需要立即执行的任务。"
tech-research
psylch
Comprehensive technical research by combining multiple intelligence sources — Grok (X/Twitter developer discussions via browser automation), DeepWiki (AI-powered GitHub repository analysis), and WebSearch. Dispatches parallel subagents for each source and synthesizes findings into a unified report. This skill should be used when evaluating technologies, comparing libraries/frameworks, researching GitHub repos, gauging developer sentiment, or investigating technical architecture decisions. Trigger phrases include "tech research", "research this technology", "技术调研", "调研一下", "compare libraries", "evaluate framework", "investigate repo".
consulting-gauntlet
sarajanenonchristian388
Full-stack consulting engagement simulator. Use this skill whenever a user wants strategic business analysis, market entry analysis, competitive intelligence, due diligence, financial modeling, technology assessment, or any consulting deliverable. Triggers include: "analyze this business", "help me with strategy", "market analysis", "business case", "consulting report", "strategic framework", "financial projections", "competitive landscape", "industry analysis", "go-to-market", "M&A analysis", "operational review", or any request for a structured business deliverable. Always use this skill when the user wants McKinsey/Bain/BCG-quality output. Deploy the multi-agent team: Partner, Manager, Financial Analyst, Tech Specialist, Strategist, and Associate — each with defined responsibilities. Never produce consulting-grade output without this skill.
brainstorm
101mare
Structured brainstorming through divergent-then-convergent thinking. Generates multiple approaches using research-validated techniques (Reverse Brainstorming, SCAMPER, Perspective Shifts, Analogies) before converging on a recommended design. Works for any domain: software features, architecture, thesis structure, process design, concepts, strategies. Recognizes: "brainstorm", "brainstorming", "ideation", "ideas for", "let's think about", "explore options", "what are approaches for", "how could we", "alternatives for" Does NOT handle: implementation planning (use plan-review), prompt writing (use prompt-builder), code writing (use frontend-design/tdd), team coordination (use team-builder).
research
costa-marcello
"Researches any topic by dispatching 6-10 parallel sub-agents across community discussions and official sources. Use when user wants to research something, asks 'what's new with X', needs recommendations, wants community opinions, or mentions analysing trends, news, or sentiment about any topic."
deep-research
101mare
Structured research workflow: Question → Sources (web + codebase) → Analyze → Synthesize → Document. Does NOT handle: planning (use plan-review), code review (use pr-review), brainstorming (use brainstorm), architecture (use architecture-builder). Use before technical decisions, when evaluating libraries/tools, or investigating unknowns. Recognizes: "deep-research", "research this", "evaluate options", "which library", "compare approaches", "investigate", "technical decision", "what are the trade-offs", "recherchiere", "welche Library", "Optionen vergleichen", "pros and cons"