[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-langgenius-dify-.agents-skills-frontend-code-review":3},{"error":4,"detail":5,"metadata":41,"markdownContent":42,"rawMarkdown":38},false,{"repo_full_name":6,"owner":7,"repo_name":8,"repo_forks":9,"skill_path":10,"repo_stars":11,"name":12,"category_id":13,"description":14,"file_tree":15,"skill_md_content":38,"skill_id":39,"skill_key":40},"langgenius/dify","langgenius","dify",20868,".agents/skills/frontend-code-review",134028,"frontend-code-review",2,"Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.",[16,21],{"name":17,"path":18,"size":19,"type":20},"SKILL.md",".agents/skills/frontend-code-review/SKILL.md",2848,"file",{"name":22,"path":23,"type":24,"children":25},"references",".agents/skills/frontend-code-review/references","folder",[26,30,34],{"name":27,"path":28,"size":29,"type":20},"business-logic.md",".agents/skills/frontend-code-review/references/business-logic.md",619,{"name":31,"path":32,"size":33,"type":20},"code-quality.md",".agents/skills/frontend-code-review/references/code-quality.md",1409,{"name":35,"path":36,"size":37,"type":20},"performance.md",".agents/skills/frontend-code-review/references/performance.md",928,"---\nname: frontend-code-review\ndescription: \"Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.\"\n---\n\n# Frontend Code Review\n\n## Intent\nUse this skill whenever the user asks to review frontend code (especially `.tsx`, `.ts`, or `.js` files). Support two review modes:\n\n1. **Pending-change review** – inspect staged/working-tree files slated for commit and flag checklist violations before submission.\n2. **File-targeted review** – review the specific file(s) the user names and report the relevant checklist findings.\n\nStick to the checklist below for every applicable file and mode.\n\n## Checklist\nSee [references/code-quality.md](references/code-quality.md), [references/performance.md](references/performance.md), [references/business-logic.md](references/business-logic.md) for the living checklist split by category—treat it as the canonical set of rules to follow.\n\nFlag each rule violation with urgency metadata so future reviewers can prioritize fixes.\n\n## Review Process\n1. Open the relevant component/module. Gather lines that relate to class names, React Flow hooks, prop memoization, and styling.\n2. For each rule in the review point, note where the code deviates and capture a representative snippet.\n3. Compose the review section per the template below. Group violations first by **Urgent** flag, then by category order (Code Quality, Performance, Business Logic).\n\n## Required output\nWhen invoked, the response must exactly follow one of the two templates:\n\n### Template A (any findings)\n```\n# Code review\nFound \u003CN> urgent issues need to be fixed:\n\n## 1 \u003Cbrief description of bug>\nFilePath: \u003Cpath> line \u003Cline>\n\u003Crelevant code snippet or pointer>\n\n\n### Suggested fix\n\u003Cbrief description of suggested fix>\n\n---\n... (repeat for each urgent issue) ...\n\nFound \u003CM> suggestions for improvement:\n\n## 1 \u003Cbrief description of suggestion>\nFilePath: \u003Cpath> line \u003Cline>\n\u003Crelevant code snippet or pointer>\n\n\n### Suggested fix\n\u003Cbrief description of suggested fix>\n\n---\n\n... (repeat for each suggestion) ...\n```\n\nIf there are no urgent issues, omit that section. If there are no suggestions, omit that section.\n\nIf the issue number is more than 10, summarize as \"10+ urgent issues\" or \"10+ suggestions\" and just output the first 10 issues.\n\nDon't compress the blank lines between sections; keep them as-is for readability.\n\nIf you use Template A (i.e., there are issues to fix) and at least one issue requires code changes, append a brief follow-up question after the structured output asking whether the user wants you to apply the suggested fix(es). For example: \"Would you like me to use the Suggested fix section to address these issues?\"\n\n### Template B (no issues)\n```\n## Code review\nNo issues found.\n```\n\n","993a61be-b2eb-51f5-8050-8bb5eaadd4db","langgenius-dify-.agents-skills-frontend-code-review",{"name":12,"description":14},"\u003Ch1>Frontend Code Review\u003C/h1>\n\u003Ch2>Intent\u003C/h2>\n\u003Cp>Use this skill whenever the user asks to review frontend code (especially \u003Ccode>.tsx\u003C/code>, \u003Ccode>.ts\u003C/code>, or \u003Ccode>.js\u003C/code> files). Support two review modes:\u003C/p>\n\u003Col>\n\u003Cli>\u003Cstrong>Pending-change review\u003C/strong> – inspect staged/working-tree files slated for commit and flag checklist violations before submission.\u003C/li>\n\u003Cli>\u003Cstrong>File-targeted review\u003C/strong> – review the specific file(s) the user names and report the relevant checklist findings.\u003C/li>\n\u003C/ol>\n\u003Cp>Stick to the checklist below for every applicable file and mode.\u003C/p>\n\u003Ch2>Checklist\u003C/h2>\n\u003Cp>See \u003Ca href=\"references/code-quality.md\">references/code-quality.md\u003C/a>, \u003Ca href=\"references/performance.md\">references/performance.md\u003C/a>, \u003Ca href=\"references/business-logic.md\">references/business-logic.md\u003C/a> for the living checklist split by category—treat it as the canonical set of rules to follow.\u003C/p>\n\u003Cp>Flag each rule violation with urgency metadata so future reviewers can prioritize fixes.\u003C/p>\n\u003Ch2>Review Process\u003C/h2>\n\u003Col>\n\u003Cli>Open the relevant component/module. Gather lines that relate to class names, React Flow hooks, prop memoization, and styling.\u003C/li>\n\u003Cli>For each rule in the review point, note where the code deviates and capture a representative snippet.\u003C/li>\n\u003Cli>Compose the review section per the template below. Group violations first by \u003Cstrong>Urgent\u003C/strong> flag, then by category order (Code Quality, Performance, Business Logic).\u003C/li>\n\u003C/ol>\n\u003Ch2>Required output\u003C/h2>\n\u003Cp>When invoked, the response must exactly follow one of the two templates:\u003C/p>\n\u003Ch3>Template A (any findings)\u003C/h3>\n\u003Cdiv class=\"md-code-block\">\u003Cpre>\u003Ccode class=\"hljs language-plaintext\"># Code review\nFound <N> urgent issues need to be fixed:\n\n## 1 <brief description of bug>\nFilePath: <path> line <line>\n<relevant code snippet or pointer>\n\n\n### Suggested fix\n<brief description of suggested fix>\n\n---\n... (repeat for each urgent issue) ...\n\nFound <M> suggestions for improvement:\n\n## 1 <brief description of suggestion>\nFilePath: <path> line <line>\n<relevant code snippet or pointer>\n\n\n### Suggested fix\n<brief description of suggested fix>\n\n---\n\n... (repeat for each suggestion) ...\u003C/code>\u003C/pre>\u003C/div>\u003Cp>If there are no urgent issues, omit that section. If there are no suggestions, omit that section.\u003C/p>\n\u003Cp>If the issue number is more than 10, summarize as "10+ urgent issues" or "10+ suggestions" and just output the first 10 issues.\u003C/p>\n\u003Cp>Don't compress the blank lines between sections; keep them as-is for readability.\u003C/p>\n\u003Cp>If you use Template A (i.e., there are issues to fix) and at least one issue requires code changes, append a brief follow-up question after the structured output asking whether the user wants you to apply the suggested fix(es). For example: "Would you like me to use the Suggested fix section to address these issues?"\u003C/p>\n\u003Ch3>Template B (no issues)\u003C/h3>\n\u003Cdiv class=\"md-code-block\">\u003Cpre>\u003Ccode class=\"hljs language-plaintext\">## Code review\nNo issues found.\u003C/code>\u003C/pre>\u003C/div>"]