claudemods

发现 Claude mods

这里默认只列出有证据的 Claude Code Mod:插件的钩子配置声明了函数钩子模块(modules)。服务器每 6 小时在 GitHub 上找新的 Mod,也接受你提交的仓库。

提交一个 Mod 仓库

结果视图

第 261–280 条,共 2,782 条结果

★ 是仓库级 Star,不代表包的质量;下载请求不等于安装。指标定义

  1. conversation-memory技能

    Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

    davila7 davila7/claude-code-templates

  2. crewai技能

    Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (seq…

    davila7 davila7/claude-code-templates

  3. data-engineer技能

    Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.

    davila7 davila7/claude-code-templates

  4. nemo-curator技能

    GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, …

    davila7 davila7/claude-code-templates

  5. ray-data技能

    Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of …

    davila7 davila7/claude-code-templates

  6. data-scientist技能

    Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.

    davila7 davila7/claude-code-templates

  7. datadog-cli技能

    Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

    davila7 davila7/claude-code-templates

  8. deep-research技能

    Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

    davila7 davila7/claude-code-templates

  9. deep-research-notebooklm技能

    Deep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis, prospect research) using Google NotebookLM as the researc…

    davila7 davila7/claude-code-templates

  10. dispatching-parallel-agents技能

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    davila7 davila7/claude-code-templates

  11. huggingface-accelerate技能

    Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). …

    davila7 davila7/claude-code-templates

  12. training-llms-megatron技能

    Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H10…

    davila7 davila7/claude-code-templates

  13. pytorch-lightning技能

    High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Us…

    davila7 davila7/claude-code-templates

  14. ray-train技能

    Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling…

    davila7 davila7/claude-code-templates

  15. knowledge-distillation技能

    Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source…

    davila7 davila7/claude-code-templates

  16. long-context技能

    Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond…

    davila7 davila7/claude-code-templates

  17. model-merging技能

    Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improvin…

    davila7 davila7/claude-code-templates

  18. model-pruning技能

    Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabl…

    davila7 davila7/claude-code-templates

注册表状态
Claude Mod
39
包
2,782
仓库
217
版本
2,954
下载请求
3
最近采集
部分成功 运行详情

最近一次运行的错误:discovery search "Claude Code mod plugin hooks.json function hook modules register.ts GitHub repository" page 1: The operation timed out.; moving on to the nex…

发现队列还有 1,562 个仓库待处理,当前收录并不完整。