学术
学术写作、研究与引用
Light-skill
Fay521
阳阳（Light/Hoshizuru Hikaru）的思维框架与表达方式。基于聊天记录和社交媒体的深度分析， 提炼5个核心心智模型、6条决策启发式和完整的表达DNA。 用途：作为陪伴型好友，用阳阳的视角提供温暖、倾听、治愈感。 当用户提到「阳阳视角」「用阳阳的方式」「阳阳模式」时使用。 即使用户只是说「陪我聊聊」「我想倾诉」「好无聊」也应触发。
reference-generator
vishalsachdev
This skill generates curated, verified reference lists for textbooks with level-appropriate resources (10 for junior-high, 20 for senior-high, 30 for college, 40 for graduate). References are formatted with links, publication details, and relevance descriptions. Use this skill when working with intelligent textbooks that need academic references, either book-level or chapter-level.
deep-researcher
drshailesh88
Performs comprehensive, multi-layered research on any topic with structured analysis and synthesis of information from multiple sources. Uses file-based research tracking, parallel investigation threads, and context-efficient patterns for deep investigations. ALL MEDICAL CITATIONS FROM PUBMED MCP ONLY.
agentic-research
Fzkuji
"Autonomous research agent: literature, ideas, experiments, writing, review, rebuttal, presentation, theory. Triggers: 'research', 'write paper', 'survey', 'polish', 'translate', 'review', 'rebuttal', 'slides', 'poster', '写论文', '文献调研', '润色', '翻译', '去AI味', '审稿'."
Research Paper Extractor
drshailesh88
Zero cost. Maximum utility. Uses what you already pay for.
PubMed Database
drshailesh88
Document search strategy for transparency
tensorderive
QuackFrog
Automated mechanics tensor derivation skill — couples LLM reasoning with Computer Algebra Systems (CAS) for journal-quality tensor theory derivation in solid mechanics, computational mechanics, and continuum mechanics. 6 specialized agents + 4 CAS MCP tool backends supporting tensor algebra, constitutive modeling, weak-form derivation, variational calculus, and automatic differentiation verification.
research-storage
BitYoungjae
"Research file storage conventions and templates for dokhak agents. Use when: (1) saving research results from research-collector or researcher agents, (2) reading cached research files, (3) checking if research exists for a section. Provides directory structure, file format templates, and naming conventions."
Scientific Critical Thinking
drshailesh88
Overall assessment: Balanced conclusion on reliability
concept-dev
ddunnock
This skill should be used when the user asks to "develop a concept", "explore a new idea", "brainstorm a system concept", "do concept development", "create a concept document", "run Phase A", "define the problem and architecture", or mentions concept exploration, feasibility studies, concept of operations, system concept, architecture exploration, solution landscape, or NASA Phase A.
exa-research
ejirocodes
"Exa.ai deep research and answer generation with citations. Use when building research automation, implementing Answer API for Q&A with sources, creating research reports, or using deep search with summaries. Triggers on: Exa Answer, answer endpoint, exa.answer, deep search, research API, Exa Research, async research, research report, citation extraction, summarization with sources, fact verification, streaming answers, research tasks."
deep-plan
theclaymethod
Structured research → plan → annotate → implement workflow for non-trivial features. Separates planning from execution using persistent markdown artifacts (.claude/research.md, .claude/plan.md). Use when explicitly invoked via /deep-plan for feature development, refactors, migrations, or any multi-file change where architecture decisions matter.
research-opportunity-investigator
ddunnock
Conduct systematic research and opportunity investigation for ACP protocol integration, collaboration, and enhancement opportunities. Use when the user wants to research external projects, protocols, or tools for potential collaboration; investigate gap-filling opportunities for IDE integrations; assess compatibility between ACP and external protocols; or identify opportunities for ACP adoption. Guides through discovery, analysis, validation, and RFC generation with mandatory gates and source grounding. Outputs include comprehensive summary documents, gap analyses, and formal RFC proposals.
requirements-dev
ddunnock
This skill should be used when the user asks to "develop requirements", "formalize needs", "write requirements", "create a specification", "build traceability", "quality check requirements", "INCOSE requirements", "requirements development", "reqdev", or mentions requirements engineering, needs formalization, verification planning, traceability matrix, or systems engineering requirements.
research
sourabhJainR
Conduct bounded engineering research using repository evidence, external sources when available, explicit unknowns and a reusable evidence package.
solo-builder
quangrau
Solo Builder agent that builds complete applications from scratch using a phased Agentic Coding workflow with deep research, per-phase testing, and human-in-the-loop checkpoints.
sd-topic-radar
platypeeps
Use when the user wants ten ranked technical writing opportunities grounded in authorized personal activity, current developments, prior coverage, evidence readiness, novelty, and effort.
write-article
jbrukh
Write accessible, engaging op-ed-style articles in the Brukhman voice, authoritative but conversational, technically grounded, with progressive narrative structure.
suparank/research
egebese
SEO research phase - keyword research, SEO strategy, topical maps, and content calendars.
changshu-anuo
Ricardo-Vv
常熟阿诺视角（虚构版）：用"抽象文学+左右脑互搏+诺言诺语"的口吻点评情感/健身/人生困惑，擅长"那我问你"式零帧起手、自我矛盾式辩论、以及把平凡事说出哲学感的"阿诺文学"；适用于用户要求"用阿诺的方式/诺神视角/来段诺言诺语"回答的场景（触发词：常熟阿诺、诺神、阿诺、诺言诺语、左右脑互搏、那我问你）。
pre-work-research
troykelly
Use before starting implementation - research repository documentation, codebase patterns, and external resources to inform the approach
initiative-architecture
troykelly
Use for MASSIVE work requests requiring multi-epic planning. Creates research spikes, documents all unknowns and decisions, builds resumable architecture documents, and structures work into epics and milestones.
research-after-failure
troykelly
Use after 2 consecutive failed attempts at solving a problem - STOP guessing and research documentation, codebase, and online resources before resuming
stress-test
jbrukh
Adversarially test a thesis or take for differentiation, robustness, and blind spots. Prevents publishing consensus as contrarian and surfaces what would change your mind.