Research & Learning skills

Reach for this skill whenever Claude encounters situations involving supply chain innovation, B2B customer respect, community revitalization, vocational education, or navigating massive business crises. Apply the mental models of Diane Hendricks, co-founder of ABC Supply and building supplies billionaire, when users face decisions about strategic acquisitions, counter-cyclical expansion, or treating blue-collar workers as respected entrepreneurs. Use this skill to channel her 'fight or fold' resilience, her strict financial responsibility hierarchy, and her focus on solving the exact pain points you faced as a customer.

The English summary is being prepared. Showing the original description.

銘柄・業界・マーケット・ビジネスモデルの深掘りリサーチ。Grok API (X/Web検索) と yfinance を統合して多角的な分析レポートを生成する。

The English summary is being prepared. Showing the original description.

知識グラフへの自然言語クエリ。過去のレポート・スクリーニング・取引・リサーチ・市況を検索。

The English summary is being prepared. Showing the original description.

Extract reusable patterns from non-trivial work in the is-kit repository and store them as project knowledge. Use after meaningful API design, type-system work, debugging, or compatibility discoveries.

The English summary is being prepared. Showing the original description.

Analyze selected sources: Viktor or MotionSites.

The English summary is being prepared. Showing the original description.

Research with scoped depth and counterevidence.

The English summary is being prepared. Showing the original description.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

The English summary is being prepared. Showing the original description.

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems.

The English summary is being prepared. Showing the original description.

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

The English summary is being prepared. Showing the original description.

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

The English summary is being prepared. Showing the original description.

仕事・学習・家事・個人制作などで止まった場面を責めずに省察し、5ステップを手がかりに、見えていなかった前提と次の一歩を見つける対話型Skill。先延ばし、完璧主義、着手や提出への怖さ、試した後の停滞を整理したいときに使う。単純な実行、説明、軽微な修正、網羅的な計画づくりには使わない。

The English summary is being prepared. Showing the original description.

Suede AI pricing and packaging: chooses the value metric (seats, usage, credits, outcomes), structures tiers, compares free trial, freemium, and reverse trial, plans willingness to pay research and price increases with grandfathering, and tears down a pricing page for buyer clarity and for search and AI-assistant readability (text prices, matching schema, quotable FAQ). Returns a Pricing Decision Brief or a scored teardown. Use when deciding what to charge, restructuring tiers, pricing AI features with variable compute cost, raising prices, or fixing a pricing page that buyers or AI answers misread. NOT FOR: in-product upgrade screens (use suede-paywalls), offer bonuses and guarantees (use suede-offers), or executing billing changes.

The English summary is being prepared. Showing the original description.

Suede AI customer-research discipline: interview design, transcript, ticket, survey, and NPS synthesis, review and forum mining with saved captures, VOC quote banks, jobs to be done, evidence-backed personas, and the exact questions buyers type into search and AI assistants. Use when discovering or synthesizing what a defined customer segment actually says, does, needs, and resists. NOT FOR: competitor-only profiling (use suede-competitor-profiling), writing final marketing copy (use suede-copy), or deciding product priorities without product evidence (use suede-product-marketing).

The English summary is being prepared. Showing the original description.

Suede AI competitive-intelligence discipline: evidence-backed profiles of positioning, pricing, messaging, product, proof, reviews, organic search footprint, and AI answer visibility, built from current public URLs with raw captures saved and fact, inference, and unknowns kept separate. Use when researching named competitors or refreshing a structured view of the competitor set. NOT FOR: publishing comparison or alternative pages (use suede-competitors), internal sales battle cards (use suede-sales-enablement), or deciding pricing changes (use suede-pricing).

The English summary is being prepared. Showing the original description.

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper', 'conference paper', 'manuscript', 'thesis', 'APA', 'MLA', 'Chicago', 'IEEE two-column', 'bibliography', 'hanging indent', 'citation style', 'abstract + keywords', 'equation numbering', 'cross-reference', paper with footnotes/endnotes. Output is a single .docx.

The English summary is being prepared. Showing the original description.

Align Python version and repo-declared dependencies (requirements.txt / environment.yml) before installing packages for NLP research code reproduction.

The English summary is being prepared. Showing the original description.

Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets, or inline code. The key signal is the user wants to UNDERSTAND something, not change it. Do NOT trigger for requests to build, fix, plan, review, research, or add/modify code.

The English summary is being prepared. Showing the original description.

Use when writing or changing PyTorch code — model, Dataset/DataLoader, training and evaluation loops, determinism, mixed precision, torch.compile, checkpoints with safetensors, Hugging Face models, ONNX export, and tests that run on CPU

The English summary is being prepared. Showing the original description.

Transform research into Opportunity Solution Tree (Teresa Torres method). Map outcomes, opportunities, solutions, and experiments.

The English summary is being prepared. Showing the original description.

模拟高三语文辅导老师，辅导现代文阅读、古诗文鉴赏、文言文翻译、作文写作等语文问题。重语感培养、文本解读、写作思维。当学生提出语文问题、请求分析课文、讲解古诗词、修改作文时使用。

The English summary is being prepared. Showing the original description.

模拟高三通用技术辅导老师，辅导技术设计、结构分析、流程图、算法、简单编程等通用技术问题。重实践操作、设计思维、问题解决能力培养。当学生提出技术设计、结构优化、流程设计、算法问题时使用。

The English summary is being prepared. Showing the original description.

模拟高三英语辅导老师，辅导英语阅读理解、完形填空、语法填空、写作等问题。重语言能力培养、做题技巧、词汇积累。当学生提出英语问题、请求讲解语法、分析阅读题、修改作文时使用。

The English summary is being prepared. Showing the original description.

模拟中国高三理科辅导老师，用渐进式教学方法辅导数学、物理、化学、生物等理科问题。当学生提出理科问题、请求讲解、说"不懂"、"教我"时使用。适用于高考备考、解题辅导、概念理解。

The English summary is being prepared. Showing the original description.

模拟高三文科辅导老师，用启发式教学方法辅导政治、历史、地理等文科综合问题。侧重理解、记忆、分析能力培养。当学生提出文科问题、请求讲解历史事件、地理现象、政治原理时使用。

The English summary is being prepared. Showing the original description.