docs: skills - fix broken reference links

assets/skills/ccxt/Manual.md

@@ -0,0 +1,7 @@
+# CCXT Manual（外链）
+
+本仓库未内置 CCXT 的完整 Manual 原文；请使用官方文档：
+
+- Docs（推荐）：https://docs.ccxt.com/
+- GitHub Wiki Manual：https://github.com/ccxt/ccxt/wiki/Manual
+

assets/skills/ccxt/references/Manual.md

@@ -0,0 +1,7 @@
+# CCXT Manual（外链）
+
+本仓库未在 `assets/skills/ccxt/references/` 内维护 CCXT Manual 的镜像文件；请使用官方文档：
+
+- Docs（推荐）：https://docs.ccxt.com/
+- GitHub Wiki Manual：https://github.com/ccxt/ccxt/wiki/Manual
+

assets/skills/claude-cookbooks/references/capabilities.md

@@ -4,15 +4,15 @@ Welcome to the Capabilities section of the Claude Cookbooks! This directory cont
 
 ## Guides
 
-- **[Classification with Claude](./classification/guide.ipynb)**: Discover how Claude can revolutionize classification tasks, especially in scenarios with complex business rules and limited training data. This guide walks you through data preparation, prompt engineering with retrieval-augmented generation (RAG), testing, and evaluation.
+- **[Classification with Claude](https://github.com/anthropics/claude-cookbooks/tree/main/capabilities/classification)**: Discover how Claude can revolutionize classification tasks, especially in scenarios with complex business rules and limited training data. This guide walks you through data preparation, prompt engineering with retrieval-augmented generation (RAG), testing, and evaluation.
 
-- **[Retrieval Augmented Generation with Claude](./retrieval_augmented_generation/guide.ipynb)**: Learn how to enhance Claude's capabilities with domain-specific knowledge using RAG. This guide demonstrates how to build a RAG system from scratch, optimize its performance, and create an evaluation suite. You'll learn how techniques like summary indexing and re-ranking can significantly improve precision, recall, and overall accuracy in question-answering tasks.
+- **[Retrieval Augmented Generation with Claude](https://github.com/anthropics/claude-cookbooks/tree/main/capabilities/retrieval_augmented_generation)**: Learn how to enhance Claude's capabilities with domain-specific knowledge using RAG. This guide demonstrates how to build a RAG system from scratch, optimize its performance, and create an evaluation suite. You'll learn how techniques like summary indexing and re-ranking can significantly improve precision, recall, and overall accuracy in question-answering tasks.
 
-- **[Retrieval Augmented Generation with Contextual Embeddings](./contextual-embeddings/guide.ipynb)**: Learn how to use a new technique to improve the performance of your RAG system. In traditional RAG, documents are typically split into smaller chunks for efficient retrieval. While this approach works well for many applications, it can lead to problems when individual chunks lack sufficient context. Contextual Embeddings solve this problem by adding relevant context to each chunk before embedding. You'll learn how to use contextual embeddings with semantic search, BM25 search, and reranking to improve performance.
+- **[Retrieval Augmented Generation with Contextual Embeddings](https://github.com/anthropics/claude-cookbooks/tree/main/capabilities/contextual-embeddings)**: Learn how to use a new technique to improve the performance of your RAG system. In traditional RAG, documents are typically split into smaller chunks for efficient retrieval. While this approach works well for many applications, it can lead to problems when individual chunks lack sufficient context. Contextual Embeddings solve this problem by adding relevant context to each chunk before embedding. You'll learn how to use contextual embeddings with semantic search, BM25 search, and reranking to improve performance.
 
-- **[Summarization with Claude](./summarization/guide.ipynb)**: Explore Claude's ability to summarize and synthesize information from multiple sources. This guide covers a variety of summarization techniques, including multi-shot, domain-based, and chunking methods, as well as strategies for handling long-form content and multiple documents. We also explore evaluating summaries, which can be a balance of art, subjectivity, and the right approach!
+- **[Summarization with Claude](https://github.com/anthropics/claude-cookbooks/tree/main/capabilities/summarization)**: Explore Claude's ability to summarize and synthesize information from multiple sources. This guide covers a variety of summarization techniques, including multi-shot, domain-based, and chunking methods, as well as strategies for handling long-form content and multiple documents. We also explore evaluating summaries, which can be a balance of art, subjectivity, and the right approach!
 
-- **[Text-to-SQL with Claude](./text_to_sql/guide.ipynb)**: This guide covers how to generate complex SQL queries from natural language using prompting techniques, self-improvement, and RAG. We'll also explore how to evaluate and improve the accuracy of generated SQL queries, with evals that test for syntax, data correctness, row count, and more.
+- **[Text-to-SQL with Claude](https://github.com/anthropics/claude-cookbooks/tree/main/capabilities/text_to_sql)**: This guide covers how to generate complex SQL queries from natural language using prompting techniques, self-improvement, and RAG. We'll also explore how to evaluate and improve the accuracy of generated SQL queries, with evals that test for syntax, data correctness, row count, and more.
 
 ## Getting Started
 

assets/skills/claude-cookbooks/references/patterns.md

@@ -15,6 +15,6 @@ This repository contains example minimal implementations of common agent workflo
 ## Getting Started
 See the Jupyter notebooks for detailed examples:
 
-- [Basic Workflows](basic_workflows.ipynb)
-- [Evaluator-Optimizer Workflow](evaluator_optimizer.ipynb) 
-- [Orchestrator-Workers Workflow](orchestrator_workers.ipynb)
+- [Basic Workflows](https://github.com/anthropics/claude-cookbooks/blob/main/patterns/agents/basic_workflows.ipynb)
+- [Evaluator-Optimizer Workflow](https://github.com/anthropics/claude-cookbooks/blob/main/patterns/agents/evaluator_optimizer.ipynb)
+- [Orchestrator-Workers Workflow](https://github.com/anthropics/claude-cookbooks/blob/main/patterns/agents/orchestrator_workers.ipynb)

assets/skills/cryptofeed/references/README.md

@@ -1,5 +1,5 @@
 # Cryptocurrency Exchange Feed Handler
-[![License](https://img.shields.io/badge/license-XFree86-blue.svg)](LICENSE)
+[![License](https://img.shields.io/badge/license-XFree86-blue.svg)](https://github.com/bmoscon/cryptofeed/blob/master/LICENSE)
 ![Python](https://img.shields.io/badge/Python-3.8+-green.svg)
 [![PyPi](https://img.shields.io/badge/PyPi-cryptofeed-brightgreen.svg)](https://pypi.python.org/pypi/cryptofeed)
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/efa4e0d6e10b41d0b51454d08f7b33b1)](https://www.codacy.com/app/bmoscon/cryptofeed?utm_source=github.com&utm_medium=referral&utm_content=bmoscon/cryptofeed&utm_campaign=Badge_Grade)
@@ -82,7 +82,7 @@ For an example of a containerized application using cryptofeed to store data to
 
 ## National Best Bid/Offer (NBBO)
 
-Cryptofeed also provides a synthetic [NBBO](examples/demo_nbbo.py) (National Best Bid/Offer) feed that aggregates the best bids and asks from the user specified feeds.
+Cryptofeed also provides a synthetic [NBBO](https://github.com/bmoscon/cryptofeed/blob/master/examples/demo_nbbo.py) (National Best Bid/Offer) feed that aggregates the best bids and asks from the user specified feeds.
 
 ```python
 from cryptofeed import FeedHandler
@@ -171,7 +171,7 @@ See more discussion of package installation in [INSTALL.md](https://github.com/b
 
 ## Rest API
 
-Cryptofeed supports some REST interfaces for retrieving real-time and historical data, as well as order placement and account management. These are integrated into the exchange classes directly. You can view the supported methods by calling the `info()` method on any exchange. The methods for interacting with the exchange RET endpoints exist in two flavors, the synchronous methods (suffixed with `_sync`) as well as the asynchronous which can be utilized with asyncio. For more information see the [documentation](docs/rest.md).
+Cryptofeed supports some REST interfaces for retrieving real-time and historical data, as well as order placement and account management. These are integrated into the exchange classes directly. You can view the supported methods by calling the `info()` method on any exchange. The methods for interacting with the exchange RET endpoints exist in two flavors, the synchronous methods (suffixed with `_sync`) as well as the asynchronous which can be utilized with asyncio. For more information see the [documentation](https://github.com/bmoscon/cryptofeed/blob/master/docs/rest.md).
 
 
 ## Future Work
@@ -182,7 +182,7 @@ There are a lot of planned features, new exchanges, etc planned! If you'd like t
 
 Issues and PRs are welcomed!
 
-Cryptofeed wouldn't be possible without the help of many [contributors](AUTHORS.md)! I owe them and all other contributors my thanks!
+Cryptofeed wouldn't be possible without the help of many [contributors](https://github.com/bmoscon/cryptofeed/blob/master/AUTHORS.md)! I owe them and all other contributors my thanks!
 
 ## Donations / Support
 

assets/skills/twscrape/references/account_management.md

@@ -0,0 +1,14 @@
+# twscrape：账号管理（参考）
+
+本文件为 `twscrape` 的账号管理参考页。
+
+## 推荐阅读顺序
+
+1. `assets/skills/twscrape/references/installation.md`
+2. `assets/skills/twscrape/SKILL.md`（包含账号池、登录、轮换等完整示例）
+3. `assets/skills/twscrape/references/examples.md`
+
+## 入口
+
+- 账号添加/登录的核心示例：`assets/skills/twscrape/SKILL.md`
+

assets/skills/twscrape/references/api_methods.md

@@ -0,0 +1,8 @@
+# twscrape：API 方法（参考）
+
+本文件为 `twscrape` 的 API 方法参考页（仓库内精简版）。
+
+## 入口
+
+- 完整方法速查与示例：`assets/skills/twscrape/SKILL.md`
+

assets/skills/twscrape/references/cli_usage.md

@@ -0,0 +1,8 @@
+# twscrape：CLI 用法（参考）
+
+本文件为 `twscrape` 的命令行使用参考页。
+
+## 入口
+
+- CLI 相关命令示例：`assets/skills/twscrape/SKILL.md`
+

assets/skills/twscrape/references/proxy_config.md

@@ -0,0 +1,8 @@
+# twscrape：代理配置（参考）
+
+本文件为 `twscrape` 的代理配置参考页。
+
+## 入口
+
+- 代理参数示例：`assets/skills/twscrape/SKILL.md`
+