{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreia2eidqa67j2oc7luosoao7ctegfq33xkhh5c4hrhfs6qh6izlklu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mpl4ywxjw4k2"
  },
  "path": "/t/how-to-achieve-greater-code-refactoring-automation/1385318#post_6",
  "publishedAt": "2026-07-01T08:25:21.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "github.com",
    "GitHub - TechSpokes/skill-ide-phpstorm-mcp: IDE PHPStorm MCP server best practices. Helps AI...",
    "GitHub - TechSpokes/agency-specifications-files-agents-md: AGENTS.md file guidelines",
    "GitHub - TechSpokes/agency-specifications-files-readme-md: Readme.md Specification",
    "gist.github.com",
    "https://gist.github.com/sergeliatko/2e3f2a165797db81337c598e9f5f2c53",
    "show original"
  ],
  "textContent": "Great thread here.\n\nPersonally for refactoring I heavily rely on IDE (PHP storm) calling agents from the console inside the IDE\n\nAlso I have released this PHP storm skill which might help your agent to work with IDE:\n\ngithub.com\n\n### GitHub - TechSpokes/skill-ide-phpstorm-mcp: IDE PHPStorm MCP server best practices. Helps AI...\n\nIDE PHPStorm MCP server best practices. Helps AI agents to leverage your IDE tools for better efficiency.\n\nAlso what helps a lot is having the architecture overview document created by the agent after the analysis of your code base with weak spots flagged during the analysis.\n\nAnd some alignment on the documentation is also good to help agent produce better code.\n\nHere are some examples I put in the repository as adopted conventions:\n\ngithub.com\n\n### GitHub - TechSpokes/agency-specifications-files-agents-md: AGENTS.md file guidelines\n\nAGENTS.md file guidelines\n\ngithub.com\n\n### GitHub - TechSpokes/agency-specifications-files-readme-md: Readme.md Specification\n\nReadme.md Specification\n\ngist.github.com\n\n#### https://gist.github.com/sergeliatko/2e3f2a165797db81337c598e9f5f2c53\n\n##### code-commenting-specification-v2.md\n\n\n    # Code Commenting Specification\n\n    Version 2.0.0\n\n    A specification for code commenting in multi-entity codebases where humans, AI agents, and automated tools collaborate.\n\n    ## 1. Abstract\n\n    This specification defines principles, a tag vocabulary, requirement levels, and guidelines for code comments in software projects. It treats code comments as a form of cross-intelligence context transfer: persistent, asynchronous messages embedded in source code that carry information not available from the code itself.\n\n\nThis file has been truncated. show original\n\nHope that helps.",
  "title": "How to achieve greater code refactoring automation?"
}