"Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts."

4.0(0)

3.1K

dbt (data build tool)

dbt-transformation-patterns

by @sickn33

"Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or ..."

4.0(0)

3.0K

MLOps Pipelines

ml-pipeline-workflow

by @sickn33

构建端到端MLOps管道，涵盖数据准备、模型训练、验证和生产部署，实现机器学习全流程。

4.0(0)

2.9K

Microsoft Fabric

fabric-lakehouse

by @github

提供Fabric Lakehouse及其在软件系统和AI功能中的特性上下文，包括Lakehouse数据概念。

4.0(0)

7.0K

Google Model Armor

gws-modelarmor-create-template

by @googleworkspace

"Google Model Armor: Create a new Model Armor template."

4.0(0)

3.5K

Google Gemini

gemini

by @softaworks

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

4.0(0)

3.4K

Prompt Engineering

gws-modelarmor-sanitize-prompt

by @googleworkspace

"Google Model Armor: Sanitize a user prompt through a Model Armor template."

4.0(0)

3.4K

LLM Output Filtering

gws-modelarmor-sanitize-response

by @googleworkspace

"Google Model Armor: Sanitize a model response through a Model Armor template."

4.0(0)

3.4K

Anthropic Claude

claude-api

by @anthropics

"Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks."

4.0(0)

3.3K

Andrej Karpathy

karpathy-guidelines

by @forrestchang

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

4.0(0)

1.9K

Information Retrieval

tooluniverse-sequence-retrieval

by @mims-harvard

从NCBI和ENA检索生物序列（DNA、RNA、蛋白质），支持基因消歧和登录类型处理。

4.0(0)

1.3K

AI News

daily-ai-news

by @yyh211

聚合并总结来自多个来源的最新AI新闻，提供简洁的新闻摘要和直接链接。

4.0(0)

1.1K

Information Retrieval

iterative-retrieval

by @affaan-m

Pattern for progressively refining context retrieval to solve the subagent context problem

4.0(0)

1.0K

PaddleOCR

paddleocr-text-recognition

by @aidenwu0209

从图片、PDF或文档中提取文本，支持URL和本地文件，并返回结构化JSON。

4.0(0)

1.0K

Data Pipeline Architecture

data-engineering-data-pipeline

by @sickn33

"You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing."

3.7(0)

180

fal.ai

fal-image-edit

by @sickn33

"AI-powered image editing with style transfer and object removal"

3.7(0)

416

Hugging Face Hub

hugging-face-cli

by @sickn33

"Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run comput..."

3.7(0)

250

Hugging Face Datasets

hugging-face-datasets

by @sickn33

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

3.7(0)

295

Hugging Face Models

hugging-face-evaluation

by @sickn33

在Hugging Face模型卡中添加和管理评估结果，支持从README提取评估表和导入分数。

3.7(0)

207

Hugging Face Jobs

hugging-face-jobs

by @sickn33

"This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. Covers UV scripts, Docker-based jobs, hardware selection, cost estimation, authentication with tok..."

3.7(0)

182

Hugging Face Models

hugging-face-model-trainer

by @sickn33

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for...

3.7(0)

333

Hugging Face Hub

hugging-face-paper-publisher

by @sickn33

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

3.7(0)

194

Text Summarization

text-summarizer

by @dkyazzentwatwa

从长文本文档生成提取式摘要，可控制摘要长度、提取关键句并处理多个文档。

3.7(0)

312

Deep Learning

deep-learning-pytorch

by @mindrally

Expert guidance for deep learning, transformers, diffusion models, and LLM development with PyTorch, Transformers, Diffusers, and Gradio.

3.7(0)

272

Apache Airflow

airflow-dag-patterns

by @sickn33

遵循最佳实践，构建生产级Apache Airflow DAGs，确保数据工作流的稳定高效运行。

3.3(0)

Context Compression

context-compression

by @sickn33

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions...

0.0(0)

LLM Context Windows

context-window-management

by @sickn33

"Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long..."

0.0(0)

Data Science

data-scientist

by @sickn33

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

0.0(0)

Web Scraping

firecrawl-scraper

by @sickn33

"Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API"

0.0(0)

Scikit-learn

scikit-learn

by @sickn33

Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.

0.0(0)

Tavily API

tavily-search

by @veithly

Tavily AI search API - Optimized search for AI agents. Use when searching the web for current information, news, facts, or any task requiring real-time data.

0.0(0)

OCR

ocr-document-processor

by @dkyazzentwatwa

使用OCR技术从图片和扫描PDF中提取文本，支持多语言、表格检测、结构化输出和批量处理。

0.0(0)

Ontology Engineering

ontology

by @sundial-org

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on

0.0(0)

Apache Spark

parallel-task-spark

by @am-will

Only to be triggered by explicit /parallel-task-spark commands.

0.0(0)

Apache Spark

super-swarm-spark

by @am-will

Only to be triggered by explicit super-swarm-spark commands.

0.0(0)

MLOps

ml-pipeline

by @jeffallan

"Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for training orchestration, builds feature store schemas with Feast, deploys model registries, and automates retraining and validation

0.0(0)

Apache Spark

spark-engineer

by @jeffallan

Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operati

0.0(0)

Data Modeling

data-model-creation

by @tencentcloudbase

Optional advanced tool for complex data modeling. For simple table creation, use relational-database-tool directly with SQL statements.

0.0(0)

Google Gemini

gemini-image

by @johnlindquist

利用Gemini的视觉能力分析图像，进行图像分析、截图文本提取和视觉内容理解。

0.0(0)

Machine Learning

domain-ml

by @zhanghandong

"Use when building ML/AI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理"

0.0(0)

Knowledge Base

mcp-deepwiki

by @aahl

Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.

0.0(0)

Machine Learning Models

model-usage

by @steipete

使用CodexBar CLI总结Codex或Claude的本地模型使用成本，包括当前模型和完整模型细分。

0.0(0)

Generative AI

ai-video-generation

by @inferen-sh

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

0.0(0)

AI Models

nano-banana-2

by @inferen-sh

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

0.0(0)

Qwen Model

qwen-image-2

by @inferen-sh

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

0.0(0)

AI Models

nano-banana

by @inferen-sh

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

0.0(0)

Qwen Model

qwen-image-2-pro

by @inferen-sh

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

0.0(0)

Image Generation

image-generation-mcp

by @supercent-io

该技能通过MCP实现AI图像生成，利用Gemini模型或兼容服务，为营销、UI和演示文稿创建高质量图像。

0.0(0)

Tavily API

tavily-best-practices

by @tavily-ai

该技能提供Tavily集成最佳实践，指导开发者使用编码助手（如Claude Code, Curs）构建生产就绪的Tavily集成。

0.0(0)

Similarity Search

similarity-search-patterns

by @wshobson

Intelligent automation and multi-agent orchestration for Claude Code

0.0(0)

Vector Databases

vector-index-tuning

by @wshobson

Intelligent automation and multi-agent orchestration for Claude Code

0.0(0)

Large Language Models (LLM)

llm-models

by @inferen-sh

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

0.0(0)

Semantic Search

super-search

by @supermemoryai

该技能用于超级搜索，在Supermemory中查找过去的编码会话、决策和已保存信息，支持用户查询和可选范围标志。

0.0(0)

Data Science

senior-data-scientist

by @davila7

此技能是一位世界级高级数据科学家，专注于生产级AI/ML/数据系统，提供核心工具和实验设计能力。

0.0(0)

Skill Taxonomy

skill-lookup

by @f

搜索匹配用户请求的技能，展示标题、描述、作者和文件列表，并支持获取选定技能。

0.0(0)

AI Assistants

personal-assistant

by @ailabs-393

将Claude转变为全面的个人助理，具备持久记忆用户偏好、日程、任务和上下文的能力。

0.0(0)

AI Agents

agent-memory

by @api

管理AI代理的记忆功能，支持存储和检索代理在任务执行过程中的信息。

0.0(0)

Context Management

day2-create-context-sync-skill

by @ai-native-camp

第二天：创建自己的Context Sync技能，遵循STOP PROTOCOL，理解MCP作为Claude与外部服务对话的通道。

0.0(0)

Prompt Engineering

prompt-lookup

by @f

当用户需要AI提示词、模板或改进提示时，使用prompts.chat MCP服务器提供帮助。

0.0(0)

Claude AI

claude-automation-recommender

by @anthropics

推荐Claude自动化方案，帮助用户优化工作流程和提升效率。

0.0(0)

OpenRouter API

openrouter-typescript-sdk

by @openrouterteam

提供OpenRouter统一API的TypeScript SDK，通过类型安全接口访问300+ AI模型。

0.0(0)

Fact Checking

fact-checker

by @shubhamsaboo

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

0.0(0)

Decision Support Systems

decision-helper

by @shubhamsaboo

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

0.0(0)

AI APIs

letzai-api

by @letz-ai

帮助用户集成LetzAI API，实现AI驱动的图像和视频生成、编辑及放大功能。

0.0(0)

Data Pipelines

senior-data-engineer

by @davila7

为生产级AI/ML/数据系统提供世界一流的资深数据工程师技能。

0.0(0)

Jupyter Notebook

jupyter-notebook

by @openai

用于创建清晰、可复现的 Jupyter Notebook，支持实验、探索性分析、教程和教学演示。

0.0(0)

PDF Processing

pdf-ocr

by @yejinlei

从影印版 PDF 和图片文件中提取文字，支持 RapidOCR 本地引擎和 AI 大模型高精度识别。

0.0(0)

Web Scraping

scrapling-official

by @d4vinci

自适应网页抓取框架，能处理从单个请求到大规模爬取，并能从网站变化中学习。

0.0(0)

Knowledge Graph

index-knowledge

by @tursodatabase

生成分层的 AGENTS.md 文件，包含复杂性评分的子目录，支持从头重新生成。

0.0(0)

Document AI

document-processing

by @eyadsibai

处理各种办公文档，包括PDF、Excel、Word和PowerPoint，提供文档格式概览和处理指南，适用于报告和表格等。

0.0(0)

Qdrant

qdrant-vector-search

by @davila7

高性能向量数据库，用Rust编写，用于生产环境的RAG和语义搜索，支持构建推荐系统和智能问答。

0.0(0)

Unbrowse AI

unbrowse

by @unbrowse-ai

为代理提供浏览器替代方案，首次浏览后缓存API，后续可即时重用，提高浏览效率，适用于数据抓取。

0.0(0)

Memory Search

mem-search

by @thedotmack

搜索所有会话中的历史工作记录，提供搜索、过滤和获取的简单工作流，用于回顾过往信息，提升工作效率。

0.0(0)

Working Memory

read-working-memory

by @nowledge-co

在每个会话开始时读取工作记忆，提供从知识库合成的每日简报，用于获取上下文信息，提升会话效率。

0.0(0)

PDF Processing

ai-pdf-filler-cli

by @askyourpdf

使用已安装的simplicity-cli命令执行PDF自动填充工作流，优先直接命令行操作而非手动API调用，提高效率。

0.0(0)

Text Chunking

chunking-strategy

by @giuseppe-trisciuoglio

为检索增强生成（RAG）系统和文档处理管道实施最优的文本分块策略，提升信息检索和生成效果。

0.0(0)

Knowledge Bases

knowledge-management

by @anthropics

专注于创建、组织和维护支持知识库内容，撰写可搜索、易于浏览且能解决问题的文章，提升知识管理效率和用户自助服务能力。

0.0(0)

NotebookLM

anything-to-notebooklm

by @joeseesun

自动从微信公众号、网页链接、YouTube等多种来源获取内容，上传至NotebookLM，并根据自然语言指令生成播客、PPT、思维导图等多种格式。

0.0(0)

Notion

notion-knowledge-capture

by @davila7

将对话和笔记转化为结构化、可链接的Notion页面，便于知识复用，快速捕捉决策、操作指南、常见问题等关键信息。

0.0(0)

Memory Management

distill-memory

by @nowledge-co

专注于提炼和存储在当前会话结束后仍有用的知识，包括带理由的决策、可重复的流程等，确保关键信息持久化。

0.0(0)

Semantic Search

search-memory

by @nowledge-co

利用AI技术在个人知识库中进行智能搜索，适用于用户提及过往工作、修复或决策时，快速检索相关信息。

0.0(0)

Perplexity AI

perplexity-search

by @davila7

通过LiteLLM和OpenRouter，利用Perplexity模型进行AI驱动的网络搜索，提供实时、基于网络的答案及来源，提升信息获取效率。

0.0(0)

GrepAI

grepai-search-basics

by @yoanbernabeu

涵盖GrepAI语义代码搜索的基础知识，指导用户学习和执行基本的代码搜索，理解其工作原理，提升代码检索效率。

0.0(0)

Conversational AI

save-thread

by @nowledge-co

用于保留旧的技能名称，不假定通用技能运行时能导入真实会话记录，此技能名称已弃用，仅为兼容性保留。

0.0(0)

PyTorch Lightning

pytorch-lightning

by @davila7

PyTorch Lightning是一个高级训练框架，旨在组织PyTorch代码，消除样板代码，同时保持灵活性，简化深度学习模型开发。

0.0(0)

Information Retrieval

recall

by @arjunkmrm

通过BM25排名进行全文搜索，检索所有过去的Claude Code和Codex会话记录，帮助用户快速回顾和查找历史信息。

0.0(0)

Knowledge Synthesis

knowledge-synthesis

by @anthropics

将来自多个来源的原始结果进行整合，生成连贯、可信的答案，旨在将分散的信息转化为有价值的综合知识。

0.0(0)

GrepAI

grepai-search-advanced

by @yoanbernabeu

提供GrepAI高级搜索选项，包括JSON输出、紧凑模式以及与AI代理的集成。

0.0(0)

LanceDB

memory-lancedb-pro

by @win4r

OpenClaw的增强型长期记忆插件，替代内置的memory-lancedb，提供更强大的记忆功能。

0.0(0)

GrepAI

grepai-search-tips

by @yoanbernabeu

提供GrepAI语义搜索查询的技巧和最佳实践，旨在提高搜索结果质量。

0.0(0)

Tavily API

tavily-web

by @benedictking

根据用户意图选择Tavily端点，进行网页搜索、信息提取等操作。

0.0(0)

GrepAI

grepai-trace-graph

by @yoanbernabeu

使用GrepAI追踪图构建完整的调用图，递归显示所有依赖关系。

0.0(0)

GrepAI

grepai-trace-callers

by @yoanbernabeu

使用GrepAI追踪调用者，查找调用特定函数或方法的所有代码位置。

0.0(0)

Pinecone

pinecone

by @davila7

托管的向量数据库，适用于生产级AI应用和RAG系统，提供无服务器服务。

0.0(0)

Qdrant

qdrant

by @giuseppe-trisciuoglio

Qdrant向量数据库集成，为语义搜索和相似性检索提供与Java等语言的集成模式。

0.0(0)

Text Summarization

summarization

by @jwynia

根据目的、受众和上下文，创建有效的摘要，识别不同类型的总结需求。

0.0(0)

GrepAI

grepai-search-boosting

by @yoanbernabeu

配置GrepAI搜索分数提升，优先显示相关代码路径，降低测试、文档和供应商代码权重。

0.0(0)

Optical Character Recognition (OCR)

image-ocr

by @fearovex

专家级图像文字识别技能，支持Tesseract、EasyOCR、PaddleOCR、Google Vision等多种OCR工具。

0.0(0)

OCR

ocr-super-surya

by @aktsmm

利用Surya进行GPU优化的OCR，从图像、PDF和多语言文档中提取文本。

0.0(0)

Perplexity AI

perplexity

by @softaworks

Web search and research using Perplexity AI. Use when user says "search", "find", "look up", "ask", "research", or "what's the latest" for generic queries. NOT for library/framework docs (use Context7) or workspace questions.

0.0(0)

MLflow

mlflow

by @davila7

利用MLflow管理机器学习生命周期，包括实验追踪和模型注册。

0.0(0)

GrepAI

grepai-chunking

by @yoanbernabeu

配置GrepAI如何将代码文件分块进行嵌入，并优化分块策略。

0.0(0)

Data Warehousing

warehouse-init

by @astronomer

Initialize warehouse schema discovery. Generates .astro/warehouse.md with all table metadata for instant lookups. Run once per project, refresh when schema changes. Use when user says "/data:warehouse-init" or asks to set up data discovery.

0.0(0)

Crawl4AI

crawl4ai

by @brettdavies

This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.

0.0(0)

PyTorch FSDP

pytorch-fsdp

by @davila7

为PyTorch FSDP开发提供全面支持，基于官方文档，帮助用户处理分布式训练任务。

0.0(0)

GrepAI

grepai-workspaces

by @yoanbernabeu

使用GrepAI工作区管理多个相关项目，提供统一的搜索索引，适用于单体仓库。

0.0(0)

Alibaba Cloud

alicloud-ai-translation-anytrans

by @cinience

使用阿里云OpenAPI管理通义翻译服务资源，支持RPC调用、官方SDK和OpenAPI Explorer。

0.0(0)

Creative AI

creative-intelligence

by @aj-geddes

作为创意智能系统专家，促进结构化头脑风暴和研究，协助解决创意问题。

0.0(0)

AIXYZ

aixyz-on-openclaw

by @agentlyhq

为OpenClaw用户提供使用aixyz构建、部署和盈利AI代理的分步指南，从零开始。

0.0(0)

AI Agents

agent-native-architecture

by @everyinc

专注于代理原生架构的设计与实现，提供复合工程插件，优化AI代理的性能和可扩展性。

0.0(0)

Google Cloud Vertex AI

vertex-ai-api-dev

by @google-gemini

Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, an

0.0(0)

Alibaba Cloud AI

alicloud-ai-audio-asr

by @cinience

提供阿里云模型工作室的Qwen非实时语音识别（ASR）服务，支持音频转文本。

0.0(0)

Ralph Plan Methodology

ralph-plan

by @mastra-ai

作为规划助手，帮助用户创建结构良好的Ralph循环命令，支持交互式命令构建。

0.0(0)

LLM Serving

serving-llms-vllm

by @davila7

提供vLLM高性能LLM服务，通过PagedAttention和连续批处理实现比标准Transformer高24倍的吞吐量。

0.0(0)

Alibaba Cloud AI

alicloud-ai-audio-tts-voice-design

by @cinience

提供阿里云模型工作室的Qwen TTS语音设计服务，通过自然语言描述创建可控的合成语音。

0.0(0)

Hugging Face Accelerate

huggingface-accelerate

by @davila7

HuggingFace Accelerate统一分布式训练，将分布式训练简化为四行代码，易于安装和使用。

0.0(0)

Chroma DB

chroma

by @davila7

开源嵌入数据库Chroma，专为构建具有记忆功能的LLM应用设计，支持RAG等场景。

0.0(0)

LLaMA Models

llama-cpp

by @davila7

提供纯C/C++ LLM推理，依赖极少，针对CPU和非NVIDIA硬件优化，适用于本地部署。

0.0(0)

Multimodal AI

ai-multimodal

by @mrgoonie

使用Google Gemini多模态API处理音频、图像、视频、文档并生成图像，提供统一的多媒体接口。

0.0(0)

OpenAI DALL-E

openai-image-gen

by @steipete

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

0.0(0)

Speech Recognition

speech-recognition

by @dpearson2699

"Transcribe speech to text using the Speech framework. Use when implementing live microphone transcription with AVAudioEngine, recognizing pre-recorded audio files, configuring on-device vs server-based recognition, handling authorization flows, or adopting the new SpeechAnalyzer API (iOS 26+) for m

0.0(0)

Alibaba Cloud AI Search

alicloud-ai-search-opensearch

by @cinience

提供OpenSearch向量搜索版服务，使用ha3engine SDK进行文档推送和HA/SQL搜索。

0.0(0)

Google Gemini

gemini-peer-review

by @jezweb

Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.

0.0(0)

GrepAI

grepai-mcp-claude

by @yoanbernabeu

涵盖GrepAI与Claude Code通过模型上下文协议（MCP）的集成，用于在Claude中设置GrepAI。

0.0(0)

Alibaba Cloud AI

alicloud-ai-chatbot

by @cinience

使用阿里云OpenAPI管理Beebot聊天机器人服务资源，支持RPC调用、官方SDK和OpenAPI Explorer。

0.0(0)

Alibaba Cloud AI

alicloud-ai-audio-tts-realtime

by @cinience

提供阿里云模型工作室的Qwen实时文本转语音（TTS）服务，用于低延迟流式语音输出。

0.0(0)

Alibaba Cloud AI Search

alicloud-ai-search-milvus

by @cinience

通过PyMilvus连接阿里云Milvus（Serverless），使用标准API执行向量搜索。

0.0(0)

DingTalk

dingtalk-ai-table

by @aliramw

钉钉AI表格操作技能，基于新版MCP schema，支持对表格的Base、Table、Field和Record进行管理，不再使用旧版标识符。

0.0(0)

OpenAI Whisper

openai-whisper-api

by @steipete

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

0.0(0)

Screenshot to Code

screenshot-to-code

by @onewave-ai

Convert UI screenshots into working HTML/CSS/React/Vue code. Detects design patterns, components, and generates responsive layouts. Use this when users provide screenshots of websites, apps, or UI designs and want code implementation.

0.0(0)

Alibaba Cloud AI

alicloud-ai-entry-modelstudio

by @cinience

阿里云模型工作室入口技能，负责将请求路由到现有的本地技能，避免重复模型或参数细节，简化操作流程。

0.0(0)

Sentence Transformers

sentence-transformers

by @davila7

Sentence Transformers技能，提供基于Transformer的Python框架，用于生成高质量的句子和文本嵌入，适用于需要高效语义表示的场景。

0.0(0)

DeepSpeed

deepspeed

by @davila7

DeepSpeed开发辅助技能，根据官方文档提供全面的帮助，适用于处理大规模深度学习模型训练和优化。

0.0(0)

Alibaba Cloud AI Content

alicloud-ai-content-aicontent

by @cinience

阿里云AIContent服务，通过OpenAPI管理AIContent资源，支持使用官方SDK或OpenAPI Explorer进行操作。

0.0(0)

Alibaba Cloud AI Image

alicloud-ai-image-zimage-turbo

by @cinience

阿里云模型工作室Z-Image Turbo技能，通过DashScope多模态生成API，实现快速的文本到图像生成。

0.0(0)

Google Gemini

gemini-image-gen

by @jezweb

Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.

0.0(0)

Alibaba Cloud AI

alicloud-ai-audio-tts-voice-clone-test

by @cinience

阿里云语音克隆TTS最小可行性测试技能，用于验证该技能的最小请求路径，并在失败时记录详细错误信息。

0.0(0)

LLM Evaluation

evaluating-llms-harness

by @davila7

LLM评估工具lm-evaluation-harness技能，用于通过标准化提示和指标，在60多个学术基准上评估大型语言模型。

0.0(0)

Alibaba Cloud AI Search

alicloud-ai-search-dashvector

by @cinience

阿里云DashVector向量搜索服务，用于管理向量集合，并执行带可选过滤和稀疏向量的相似性搜索。

0.0(0)

data-ai

alicloud-ai-entry-modelstudio-matrix-test

by @cinience

阿里云模型工作室矩阵测试技能，用于验证该技能的最小请求路径，并在失败时记录详细错误信息。

0.0(0)

Alibaba Cloud

alicloud-ai-entry-modelstudio-test

by @cinience

阿里云模型工作室技能最小测试，用于对当前可用的模型工作室技能进行最小化验证并记录结果。

0.0(0)

DSPy

dspy

by @davila7

DSPy技能，提供声明式语言模型编程框架，用于构建包含多个组件和工作流的复杂AI系统。

0.0(0)

Alibaba Cloud

alicloud-ai-text-document-mind

by @cinience

阿里云文档智能DocMind技能，通过Node.js SDK异步提取文档结构、文本和布局信息。

0.0(0)

OCR

smart-ocr

by @claude-office-skills

smart ocr — AI Agent Skill

0.0(0)

Alibaba Cloud

alicloud-ai-cloud-call-center

by @cinience

阿里云云呼叫中心服务，通过OpenAPI管理云呼叫中心资源，支持使用官方SDK或OpenAPI Explorer。

0.0(0)

Marimo

add-molab-badge

by @marimo-team

Add "Open in molab" badge(s) linking to marimo notebooks. Works with READMEs, docs, websites, or any markdown/HTML target.

0.0(0)

Model Pruning

model-pruning

by @davila7

通过模型剪枝技术压缩大型语言模型，在保持准确率的同时显著减小模型大小和加速推理。

0.0(0)

Transformers (AI)

transformers

by @davila7

提供Hugging Face Transformers库的概述，访问数千个预训练模型，用于NLP、CV、音频等多模态任务。

0.0(0)

AI Reasoning

recall-reasoning

by @parcadei

搜索过往会话，回顾相关决策、成功和失败的方法，从历史工作中学习。

0.0(0)

AI Content Outlining

outlines

by @davila7

用于生成结构化文本，确保输出符合JSON/XML/代码等格式，并支持Pydantic模型进行类型安全验证。

0.0(0)

BLIP-2

blip-2-vision-language

by @davila7

提供Salesforce BLIP-2的全面指南，用于视觉-语言预训练任务，结合冻结图像编码器和大型语言模型。

0.0(0)

AI Research Agent

research-agent

by @parcadei

作为研究代理，负责收集外部文档和最佳实践，参考2024-2025年的最新信息。

0.0(0)

Hypothesis Generation

hypothesis-generation

by @davila7

系统性地生成科学假设，从观察中提出可测试的、基于证据的解释。

0.0(0)

Compound Learning (AI)

compound-learnings

by @parcadei

将短暂的会话学习转化为持久、可累积的能力，优化设置和知识积累。

0.0(0)

Code Model Evaluation

evaluating-code-models

by @davila7

利用BigCode评估工具，对代码生成模型进行基准测试，涵盖HumanEval、MBPP等15+基准。

0.0(0)

AI Hooks

hooks

by @parcadei

强制执行Hook开发规则，指导用户通过Shell包装器和TypeScript创建和管理钩子文件。

0.0(0)

GrepAI

grepai-mcp-cursor

by @yoanbernabeu

涵盖GrepAI与Cursor IDE的MCP集成，指导用户在Cursor中设置GrepAI。

0.0(0)

Instructor (AI)

instructor

by @davila7

用于从LLM响应中可靠地提取结构化数据，并根据Pydantic模式验证输出。

0.0(0)

AI Planning Agent

planning-agent

by @parcadei

作为规划代理，负责创建实施计划，并参考2024-2025年的最新最佳实践。

0.0(0)

Seedance

seedance

by @songguoxs

作为专业的AI视频提示词工程师，为字节跳动即梦平台的Seedance 2.0模型生成高质量中文视频提示词。

0.0(0)

AI Agent Memory

do

by @thedotmack

作为协调者，负责部署子代理执行所有任务，协调上下文、路由信息并验证子代理工作完成情况，自身不直接执行具体工作。

0.0(0)

Unsloth

unsloth

by @davila7

基于官方文档，为unsloth开发提供全面协助。当处理unsloth相关任务或提问时，可触发此技能以获取专业指导和支持。

0.0(0)

Alibaba Cloud AI

alicloud-ai-audio-asr-test

by @cinience

测试技能，旨在验证阿里云AI语音ASR（非实时）的最小请求链路可用性，失败时记录详细错误信息，确保基础功能正常。

0.0(0)

AI Agent Monitoring

heal-skill

by @boshu2

'Automated skill maintenance. Detects and fixes common skill issues: missing frontmatter, name mismatches, unlinked references, empty directories, dead references, and Codex parity drift triage. Triggers: "heal-skill", "heal skill", "fix skills", "skill maintenance", "repair skills".'

0.0(0)

AI Agent Improvement

skill-upgrader

by @parcadei

元技能，利用四个并行代理将任何SKILL.md文件升级为决策理论v5混合格式，实现技能文档的标准化和优化。

0.0(0)

Firebase Genkit

developing-genkit-dart

by @firebase

Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.

0.0(0)

NVIDIA NeMo

nemo-curator

by @davila7

NVIDIA的GPU加速数据整理工具，用于为大型语言模型（LLMs）准备高质量训练数据，优化数据预处理流程。

0.0(0)

Meme Generation

four-meme-ai

by @four-meme-community

首次使用时，代理必须向用户展示用户协议和安全通知，确保用户了解并同意相关条款，保障信息安全。

0.0(0)

Weights & Biases

weights-and-biases

by @davila7

用于机器学习实验跟踪和MLOps，自动记录指标、可视化结果，帮助用户高效管理、比较和优化ML模型开发过程。

0.0(0)

Knowledge Graphs

sag

by @steipete

ElevenLabs text-to-speech with mac-style say UX.

0.0(0)

NVIDIA TensorRT

tensorrt-llm

by @davila7

NVIDIA的开源库，用于优化大型语言模型（LLM）推理，在NVIDIA GPU上实现最先进的性能，加速模型部署。

0.0(0)

AI Best Practices

obviously-awesome

by @wondelai

'Define product positioning by mapping competitive alternatives, unique attributes, and best-fit customers to the right market category. Use when the user mentions "positioning", "competitive alternatives", "how to position", "market category", or "why customers don''t get it". Covers positioning ca

0.0(0)

AI Debugging

debug-hooks

by @parcadei

提供调试Claude Code钩子的系统化工作流程，解决钩子未触发、输出错误或会话结束等问题，确保代码正常运行。

0.0(0)

AI Agent Orchestration

complete-skill

by @parcadei

用于测试整个持久化管道，确保数据存储和检索机制的完整性与可靠性，遵循特定指令完成测试流程。

0.0(0)

Image Analysis

tooluniverse-image-analysis

by @mims-harvard

Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ/CellProfiler output (area, circularity, intensity, cell counts), performs Dunn

0.0(0)

Knowledge Retrieval

oracle

by @steipete

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

0.0(0)

Task Management

things-mac

by @steipete

通过macOS上的`things`命令行工具管理Things 3，支持添加/更新项目和待办事项，并从本地数据库读取、搜索和列出数据。

0.0(0)

AI Assistant

help

by @parcadei

提供帮助信息和使用指南，解答用户疑问，引导用户更好地理解和利用相关功能或技能。

0.0(0)

Goal-Oriented AI

goals

by @boshu2

'Maintain GOALS.yaml and GOALS.md fitness specifications. Measure fitness, manage directives, track drift, add/prune goals. Triggers: "goals", "goal status", "show goals", "add goals", "prune goals", "clean goals", "goal drift", "goal history", "export goals", "meta goals", "migrate goals".'

0.0(0)

AI Agent Initialization