Estenda janelas de contexto de modelos transformer usando RoPE, YaRN, ALiBi e técnicas de interpolação de posição. Use ao processar documentos longos (32k-128k+ tokens), estender modelos pré-treinados além dos limites de contexto originais ou implementar codificações posicionais eficientes. Cobre embeddings rotativos, vieses de atenção, métodos de interpolação e estratégias de extrapolação para LLMs.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Mescle múltiplos modelos ajustados usando mergekit para combinar capacidades sem retreinar. Use ao criar modelos especializados misturando expertise específica de domínio (math + coding + chat), melhorando performance além de modelos únicos, ou experimentando rapidamente variantes de modelos. Cobre SLERP, TIES-Merging, DARE, Task Arithmetic, mesclagem linear e estratégias de deploy em produção.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Reduza o tamanho de LLMs e acelere a inferência usando técnicas de pruning como Wanda e SparseGPT. Use para comprimir modelos sem retreinamento, alcançando 50% de esparsidade com perda mínima de acurácia, ou ativando inferência mais rápida em aceleradores de hardware. Cobre pruning não estruturado, pruning estruturado, esparsidade N:M, pruning por magnitude e métodos one-shot.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Modos operacionais de IA (brainstorm, implement, debug, review, teach, ship, orchestrate). Use para adaptar o comportamento com base no tipo de tarefa.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Treinar modelos de Mixture of Experts (MoE) usando DeepSpeed ou HuggingFace. Use ao treinar modelos em larga escala com computação limitada (redução de 5× em custos vs modelos densos), implementar arquiteturas esparsas como Mixtral 8x7B ou DeepSeek-V3, ou escalar capacidade de modelo sem aumento proporcional de computação. Cobre arquiteturas MoE, mecanismos de roteamento, balanceamento de carga, paralelismo de especialistas e otimização de inferência.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Avalia LLMs em mais de 60 benchmarks acadêmicos (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use quando benchmarking de qualidade de modelo, comparação de modelos, relatório de resultados acadêmicos ou rastreamento de progresso de treinamento. Padrão da indústria usado por EleutherAI, HuggingFace e laboratórios principais. Suporta HuggingFace, vLLM, APIs.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Guia completo para usar Claude Code de forma eficaz. Inclui templates de configuração, estratégias de prompting com keywords "Thinking", técnicas de debugging e melhores práticas para interagir com o agente.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Padrões de design para construir agentes de codificação autônomos. Cobre integração de tools, sistemas de permissão, automação de browser e workflows com intervenção humana. Use ao construir agentes IA, projetar APIs de tools, implementar sistemas de permissão ou criar assistentes de codificação autônomos.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Orientação especializada para fine-tuning de LLMs com Axolotl - configs YAML, 100+ modelos, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, suporte multimodal
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Avalia LLMs em 100+ benchmarks de 18+ harnesses (MMLU, HumanEval, GSM8K, segurança, VLM) com execução multi-backend. Use quando precisar de avaliação escalável em Docker local, HPC Slurm ou plataformas cloud. Plataforma enterprise-grade da NVIDIA com arquitetura container-first para benchmarking reproduzível.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Acelere a inferência de LLMs usando especulative decoding, múltiplas cabeças Medusa e técnicas de lookahead decoding. Use ao otimizar velocidade de inferência (aceleração de 1,5-3,6×), reduzir latência em aplicações em tempo real ou fazer deploy de modelos com recursos computacionais limitados. Cobre modelos draft, atenção em árvore, iteração de Jacobi, geração paralela de tokens e estratégias de deploy em produção.
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
Agentes autônomos são sistemas de IA que conseguem decompor objetivos, planejar ações, executar ferramentas e se auto-corrigir sem orientação humana constante. O desafio não é torná-los capazes - é torná-los confiáveis. Cada decisão extra multiplica a probabilidade de falha. Esta habilidade cobre loops de agentes (ReAct, Plan-Execute), decomposição de objetivos, padrões de reflexão e confiabilidade em produção. Insight-chave: taxas de erro compostas matam agentes autônomos. Uma taxa de sucesso de 95% por passo cai para 60% b
The English summary is being prepared. Showing the original description.
artubss/SKILLS-CLAUDE-CODE☆ 11Updated May 17, 2026
把书课程化并作为「专业教师」逐课带人类学完:课前备课→详尽费曼教学→练习闸门→间隔复习→背诵作业→自进化。默认处理使用者已提供的本地书(PDF/EPUB/DJVU/MOBI/AZW/DOCX/TXT/MD/CBZ);**当使用者无本地书且明确授权时,可代为联网检索公开来源并用项目抓取工具获取**。当用户说「学这本书 <本地路径> / 把这本 PDF 课程化 / 教我这本书 / 继续学 <书> / 复习 <书> / 考考我 <书> / 帮我学 X」时调用。教学引擎已单包自包含,无需再加载其他技能。
The English summary is being prepared. Showing the original description.
fangyuan-3149/book-learning-tutor☆ 11Updated Aug 11, 2026
Analyzes a dataset of companies or profiles to identify market patterns. Use when the user provides a larger dataset and wants segments, dominant categories, gaps, and emerging patterns.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Compares a group of companies by products, positioning, market focus, and differentiators. Use when the user provides several company records and wants a structured competitive comparison.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Turns an ICP or research goal into a plan for finding and scraping suitable directories. Use when the user has a target audience but is unsure where to find them, and wants source categories, queries, and an extraction workflow.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Creates a repeatable process for researching and comparing companies. Use when the user wants a structured, reusable company-research workflow with objectives, sources, fields, and validation.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Turns company records into structured company research summaries. Use when the user provides company names or records and wants a consistent overview, market position, and relevance assessment.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Designs an end-to-end process for finding, extracting, enriching, qualifying, and exporting leads. Use when the user wants a repeatable lead workflow plan rather than a single source plan.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Converts structured prospect research into concise outreach preparation briefs. Use when the user provides prospect or account research and wants a brief with context, angles, and claims to verify. It generates a research brief and must not invent personalization or send outreach.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Creates structured professional research summaries from public profile information. Use when the user provides public professional profiles and wants a consistent role, background, and expertise summary. Must avoid inferring sensitive personal attributes.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
Identifies missing information required to complete qualification, segmentation, or outreach preparation. Use when the user provides records and a goal and wants prioritized research gaps with sources.
The English summary is being prepared. Showing the original description.
spiralcrew-ou/profilespider-agent-skills☆ 11Updated Jun 21, 2026
arXiv 科研与工程实验室(统一 CLI 版)。 在 Claude Code 中通过自然语言或 `arxiv <subcommand>` 完成论文发现、初始化、精读、复现、工程化与贡献闭环。 关键词:arXiv、paper、research、reproduce、工程化、复现、开源贡献。
The English summary is being prepared. Showing the original description.
teslavia/arxiv-researcher☆ 11Updated Feb 27, 2026
Research one news topic and save a one-sentence summary each day
The English summary is being prepared. Showing the original description.
upstash/ahi☆ 11Updated Sep 11, 2026