Àmbit acadèmic
Redacció acadèmica, recerca i citacions
ai-dev-research
swannysec
World-expert deep technical research agent for AI-enabled software development. Use PROACTIVELY when users need: (1) Deep research on AI/ML development topics (RAG, agents, LLMs, embeddings, vector DBs, prompt engineering, fine-tuning) (2) Technical consultation on AI architectures, tool selection, or implementation approaches (3) Implementation guidance with production-ready patterns and best practices (4) Comparative analysis of AI frameworks, models, or services (5) Current state-of-the-art analysis with authoritative citations Triggers: "research AI", "compare LLMs", "RAG architecture", "agentic workflow", "AI coding tools", "which model should I use", "how does X work in AI", "best practices for AI development", "production AI systems", "AI implementation guidance"
academic-vi
mxuanvan02
Think through, structure, write, translate, revise, and audit Vietnamese academic discourse in any deliverable. Automatically use whenever Vietnamese content serves an academic, scientific, research, higher-education, or scholarly purpose, including prose, manuscripts, reports, slides, teaching content, course materials, speaker notes, assessment items, and English-to-Vietnamese translation. Do not use to invent evidence, search literature, validate methods, discover citations, or manipulate document layout.
hypothesis-testing-engine
gked2121
Take any claim and design + execute a complete research protocol to test it. Apply scientific method automatically: design study, gather data, run analysis, provide verdict with confidence level.
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.
session-retrospective
swannysec
Iterative reflection, research, and improvement skill for extracting actionable learnings from any Claude Code session. Use after longer sessions to capture process improvements, project improvements, or both. Produces agent-ready context documents for future implementation.
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.
literature-verify
BasileChretien
Retrieve a source, extract a value with its verbatim quote, and record it so the chain from manuscript to published sentence can be verified. Use when adding a number from the literature, when check reports literature-source-missing or quote-not-in-source, or when a citation needs a stored source.
claim-evidence-graph
xngg1021
确定性科学论断-证据图 (Claim-Evidence Graph v1)，连接学术论断、证据记录与计算过程追溯.
follow-USTC
nbznb
USTC and technology digest — tracks USTC official information, academic notices, selected tech news, and research papers, then remixes them into a readable digest.
book-manuscript-development
Oceanswave
Build long-form book manuscripts from outline through revision. Use when users ask for chapter-by-chapter outlines, chapter drafts, illustrative stories, research integration, exercises, transitions, case studies, conclusions, or chapter quality reviews.
research-reproducibility
xngg1021
论文可复现性核对流水线：身份、代码、版本、依赖、构建与指标四态判定.
academic-source-verification
xngg1021
核查文献真实性:交叉核对被引数、撤稿状态、开放获取全文与原文内容.
browser-research
molotroka123-cell
Navigate and inspect websites efficiently using DOM-first browser automation, screenshots only when visual understanding is needed, and strict approval gates for sensitive actions.
notebooklm
alfredang
Deep research and slide presentation generator using NotebookLM MCP. Performs deep research on topics, then generates professional slide presentations with white background and Arial font based on research sources.
research
joaomj
Investigate external facts, unfamiliar tools, APIs, libraries, or deployed behavior with primary sources and explicit evidence. Use only when the answer depends on information outside the current codebase.
compilar-tese
anavvanzin
Compile thesis chapters to DOCX or PDF via Pandoc. Use when the user says "compilar", "make tese", "gerar PDF", "gerar DOCX", or wants to build the thesis.
research
krishagel
Multi-LLM parallel research with query decomposition and synthesis
tracer-research
scottwater
Investigate a focused question against high-trust primary sources and capture cited findings as one Markdown note. Use for documentation, API, specification, or local knowledge-base research, including AFK Wayfinder research tickets.
agent-evaluation
eyadsibai
Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmarks"
writing-crypto
dbosk
Write cryptography prose and notation using the project's bibsp.sty + preamble.tex conventions (acro + biblatex footnote citations and standardized math macros). Use proactively when: (1) writing/editing cryptography sections in .tex files, (2) introducing or using crypto acronyms such as IND-CPA, IND-CCA, AE, MAC, PRF, ZK, and DH, (3) defining schemes/algorithms/variables in math notation, (4) adding citations for security notions or standard primitives, (5) writing security proofs or reductions, (6) user mentions biblatex, crypto notation, or security proof in cryptographic context.
web-research
Tempuss
Use when researching markets, analyzing competitors, comparing technologies, or finding case studies. Ensures all findings include credible sources and URLs.
pandoc-fix
anavvanzin
Use when Pandoc compile of the ICONOCRACIA thesis fails — undefined citation keys, LaTeX package errors, Markdown→LaTeX escape issues (underscores, ampersands, unicode), YAML frontmatter errors, missing .csl/.bib, or broken cross-references. Diagnoses the error, applies minimal fix, re-runs compile.
rule-research
artyhoo
Use when a consumer wants to bootstrap stack-aware ESLint rules from LIVE documentation rather than ship pre-baked recipes. Triggers: rule research, research stack practices, generate eslint rule from docs, bootstrap rules for my stack, rules-research, rule-bootstrapping, no-head-element, исследовать практики стека, сгенерировать правило из документации.
eli5
srobroek
Explain a topic at five depth levels from metaphor to frontier. Use when asked "ELI5", "explain X", "what is X", or "how does X work".