stevesolun/ctx

• highreadme#1

  Clarify the project's core identity as an LLM recommendation engine in the README's opening

  原因：

  当前

  The README starts with `# ctx — Skill, Agent, MCP & Harness Recommendations` followed by links and then 'ctx watches what you are building...'.

  复制粘贴的修复

  复制

  Add the following sentence immediately after the H1: 'ctx is an AI-powered recommendation engine that helps developers integrate relevant skills, agents, and harnesses into their custom LLM applications by leveraging a massive knowledge graph.'

  待办完成忽略
• mediumtopics#2

  Add more specific topics to reinforce the project's role as an LLM skill discovery and orchestration tool

  原因：

  当前

  agents, ai-agents, anthropic, automation, claude, claude-code, context-management, developer-tools, harness, knowledge-graph, llm, llm-wiki, mcp, micro-skills, obsidian, real-time, recommendation-engine, skill-management, skills, wiki

  复制粘贴的修复

  复制

  agents, ai-agents, anthropic, automation, claude, claude-code, context-management, developer-tools, harness, knowledge-graph, llm, llm-wiki, mcp, micro-skills, obsidian, real-time, recommendation-engine, skill-management, skills, wiki, llm-skill-discovery, ai-skill-discovery, llm-orchestration, ai-recommendation-system

  待办完成忽略
• lowabout#3

  Rephrase the repository description to lead with its core function as a recommendation engine

  原因：

  当前

  Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,928-node LLM-wiki graph, 91,464 skills, 467 agents, 10,790 MCPs, 207 harnesses, and capped execution recommendations.

  复制粘贴的修复

  复制

  ctx is an AI-powered recommendation engine providing skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs, leveraging a 102,928-node LLM-wiki knowledge graph with 91,464 skills, 467 agents, 10,790 MCPs, and 207 harnesses.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How can I find and integrate relevant AI skills and agents for my custom LLM applications?

  你：未被推荐
  AI 推荐顺序：

  1. LangChain
  2. LlamaIndex
  3. Microsoft Semantic Kernel
  4. OpenAI Assistants API
  5. Haystack
  6. CrewAI

  AI 推荐了 6 个替代方案，却始终没点名 stevesolun/ctx。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What are the best tools for leveraging a knowledge graph to manage LLM context and recommendations?

  你：未被推荐
  AI 推荐顺序：

  1. Neo4j (neo4j/neo4j)
  2. Graph Data Science Library (neo4j/graph-data-science)
  3. LangChain (langchain-ai/langchain)
  4. TypeDB (vaticle/typedb)
  5. Amazon Neptune
  6. Ontotext GraphDB (Ontotext-AD/graphdb)
  7. ArangoDB (arangodb/arangodb)
  8. TigerGraph (tigergraph/tigergraph)

  AI 推荐了 8 个替代方案，却始终没点名 stevesolun/ctx。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of stevesolun/ctx?

  pass
  ✓AI 明确点名了 stevesolun/ctx

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts stevesolun/ctx in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 stevesolun/ctx

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo stevesolun/ctx solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 stevesolun/ctx

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？