{ "schemaVersion": "1.0", "item": { "slug": "repomix-explorer", "name": "Repomix Explorer", "source": "tencent", "type": "skill", "category": "数据分析", "sourceUrl": "https://clawhub.ai/kongyo2/repomix-explorer", "canonicalUrl": "https://clawhub.ai/kongyo2/repomix-explorer", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/repomix-explorer", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=repomix-explorer", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/repomix-explorer" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/repomix-explorer", "agentPageUrl": "https://openagent3.xyz/skills/repomix-explorer/agent", "manifestUrl": "https://openagent3.xyz/skills/repomix-explorer/agent.json", "briefUrl": "https://openagent3.xyz/skills/repomix-explorer/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "User Intent Examples", "body": "The user might ask in various ways:" }, { "title": "Remote Repository Analysis", "body": "\"Analyze the yamadashy/repomix repository\"\n\"What's the structure of facebook/react?\"\n\"Explore https://github.com/microsoft/vscode\"\n\"Find all TypeScript files in the Next.js repo\"\n\"Show me the main components of vercel/next.js\"" }, { "title": "Local Repository Analysis", "body": "\"Analyze this codebase\"\n\"Explore the ./src directory\"\n\"What's in this project?\"\n\"Find all configuration files in the current directory\"\n\"Show me the structure of ~/projects/my-app\"" }, { "title": "Pattern Discovery", "body": "\"Find all authentication-related code\"\n\"Show me all React components\"\n\"Where are the API endpoints defined?\"\n\"Find all database models\"\n\"Show me error handling code\"" }, { "title": "Metrics and Statistics", "body": "\"How many files are in this project?\"\n\"What's the token count?\"\n\"Show me the largest files\"\n\"How much TypeScript vs JavaScript?\"" }, { "title": "Your Responsibilities", "body": "Understand the user's intent from natural language\nDetermine the appropriate repomix command:\n\nRemote repository: npx repomix@latest --remote \nLocal directory: npx repomix@latest [directory]\nChoose output format (xml is default and recommended)\nDecide if compression is needed (for repos >100k lines)\n\n\nExecute the repomix command via shell\nAnalyze the generated output using pattern search and file reading\nProvide clear insights with actionable recommendations" }, { "title": "Step 1: Pack the Repository", "body": "For Remote Repositories:\n\nnpx repomix@latest --remote --output /tmp/-analysis.xml\n\nIMPORTANT: Always output to /tmp for remote repositories to avoid polluting the user's current project directory.\n\nFor Local Directories:\n\nnpx repomix@latest [directory] [options]\n\nCommon Options:\n\n--style : Output format (xml, markdown, json, plain) - xml is default and recommended\n--compress: Enable Tree-sitter compression (~70% token reduction) - use for large repos\n--include : Include only matching patterns (e.g., \"src//*.ts,/*.md\")\n--ignore : Additional ignore patterns\n--output : Custom output path (default: repomix-output.xml)\n--remote-branch : Specific branch, tag, or commit to use (for remote repos)\n\nCommand Examples:\n\n# Basic remote pack (always use /tmp)\nnpx repomix@latest --remote yamadashy/repomix --output /tmp/repomix-analysis.xml\n\n# Basic local pack\nnpx repomix@latest\n\n# Pack specific directory\nnpx repomix@latest ./src\n\n# Large repo with compression (use /tmp)\nnpx repomix@latest --remote facebook/react --compress --output /tmp/react-analysis.xml\n\n# Include only specific file types\nnpx repomix@latest --include \"**/*.{ts,tsx,js,jsx}\"" }, { "title": "Step 2: Check Command Output", "body": "The repomix command will display:\n\nFiles processed: Number of files included\nTotal characters: Size of content\nTotal tokens: Estimated AI tokens\nOutput file location: Where the file was saved (default: ./repomix-output.xml)\n\nAlways note the output file location for the next steps." }, { "title": "Step 3: Analyze the Output File", "body": "Start with structure overview:\n\nSearch for file tree section (usually near the beginning)\nCheck metrics summary for overall statistics\n\nSearch for patterns:\n\n# Pattern search (preferred for large files)\ngrep -iE \"export.*function|export.*class\" repomix-output.xml\n\n# Search with context\ngrep -iE -A 5 -B 5 \"authentication|auth\" repomix-output.xml\n\nRead specific sections:\nRead files with offset/limit for large outputs, or read entire file if small." }, { "title": "Step 4: Provide Insights", "body": "Report metrics: Files, tokens, size from command output\nDescribe structure: From file tree analysis\nHighlight findings: Based on grep results\nSuggest next steps: Areas to explore further" }, { "title": "Efficiency", "body": "Always use --compress for large repos (>100k lines)\nUse pattern search (grep) first before reading entire files\nUse custom output paths when analyzing multiple repos to avoid overwriting\nClean up output files after analysis if they're very large" }, { "title": "Output Format", "body": "XML (default): Best for structured analysis, clear file boundaries\nPlain: Simpler to grep, but less structured\nMarkdown: Human-readable, good for documentation\nJSON: Machine-readable, good for programmatic analysis\n\nRecommendation: Stick with XML unless user requests otherwise." }, { "title": "Search Patterns", "body": "Common useful patterns:\n\n# Functions and classes\ngrep -iE \"export.*function|export.*class|function |class \" file.xml\n\n# Imports and dependencies\ngrep -iE \"import.*from|require\\\\(\" file.xml\n\n# Configuration\ngrep -iE \"config|Config|configuration\" file.xml\n\n# Authentication/Authorization\ngrep -iE \"auth|login|password|token|jwt\" file.xml\n\n# API endpoints\ngrep -iE \"router|route|endpoint|api\" file.xml\n\n# Database/Models\ngrep -iE \"model|schema|database|query\" file.xml\n\n# Error handling\ngrep -iE \"error|exception|try.*catch\" file.xml" }, { "title": "File Management", "body": "Default output: ./repomix-output.xml\nUse --output flag for custom paths\nClean up large files after analysis: rm repomix-output.xml\nOr keep for future reference if space allows" }, { "title": "Communication Style", "body": "Be concise but comprehensive: Summarize findings clearly\nUse clear technical language: Code, file paths, commands should be precise\nCite sources: Reference file paths and line numbers\nSuggest next steps: Guide further exploration" }, { "title": "Example 1: Basic Remote Repository Analysis", "body": "User: \"Analyze the yamadashy/repomix repository\"\n\nYour workflow:\n1. Run: npx repomix@latest --remote yamadashy/repomix --output /tmp/repomix-analysis.xml\n2. Note the metrics from command output (files, tokens)\n3. Grep: grep -i \"export\" /tmp/repomix-analysis.xml (find main exports)\n4. Read file tree section to understand structure\n5. Summarize:\n \"This repository contains [number] files.\n Main components include: [list].\n Total tokens: approximately [number].\"" }, { "title": "Example 2: Finding Specific Patterns", "body": "User: \"Find authentication code in this repository\"\n\nYour workflow:\n1. Run: npx repomix@latest (or --remote if specified)\n2. Grep: grep -iE -A 5 -B 5 \"auth|authentication|login|password\" repomix-output.xml\n3. Analyze matches and categorize by file\n4. Read the file to get more context if needed\n5. Report:\n \"Authentication-related code found in the following files:\n - [file1]: [description]\n - [file2]: [description]\"" }, { "title": "Example 3: Structure Analysis", "body": "User: \"Explain the structure of this project\"\n\nYour workflow:\n1. Run: npx repomix@latest ./\n2. Read file tree from output (use limit if file is large)\n3. Grep for main entry points: grep -iE \"index|main|app\" repomix-output.xml\n4. Grep for exports: grep \"export\" repomix-output.xml | head -20\n5. Provide structural overview with ASCII diagram if helpful" }, { "title": "Example 4: Large Repository with Compression", "body": "User: \"Analyze facebook/react - it's a large repository\"\n\nYour workflow:\n1. Run: npx repomix@latest --remote facebook/react --compress --output /tmp/react-analysis.xml\n2. Note compression reduced token count (~70% reduction)\n3. Check metrics and file tree\n4. Grep for main components\n5. Report findings with note about compression used" }, { "title": "Example 5: Specific File Types Only", "body": "User: \"I want to see only TypeScript files\"\n\nYour workflow:\n1. Run: npx repomix@latest --include \"**/*.{ts,tsx}\"\n2. Analyze TypeScript-specific patterns\n3. Report findings focused on TS code" }, { "title": "Error Handling", "body": "If you encounter issues:\n\nCommand fails:\n\nCheck error message\nVerify repository URL/path\nCheck permissions\nSuggest appropriate solutions\n\n\n\nLarge output file:\n\nUse --compress flag\nUse --include to narrow scope\nRead file in chunks with offset/limit\n\n\n\nPattern not found:\n\nTry alternative patterns\nCheck file tree to verify files exist\nSuggest broader search\n\n\n\nNetwork issues (for remote):\n\nVerify connection\nTry again\nSuggest using local clone instead" }, { "title": "Help and Documentation", "body": "If you need more information:\n\nRun npx repomix@latest --help to see all available options\nCheck the official documentation at https://github.com/yamadashy/repomix\nRepomix automatically excludes sensitive files based on security checks" }, { "title": "Important Notes", "body": "Output file management: Track where files are created, clean up if needed\nToken efficiency: Use --compress for large repos to reduce token usage\nIncremental analysis: Don't read entire files at once; use grep first\nSecurity: Repomix automatically excludes sensitive files; trust its security checks" }, { "title": "Self-Verification Checklist", "body": "Before completing your analysis:\n\nDid you run the repomix command successfully?\nDid you note the metrics from command output?\nDid you use pattern search (grep) efficiently before reading large sections?\nAre your insights based on actual data from the output?\nHave you provided file paths and line numbers for references?\nDid you suggest logical next steps for deeper exploration?\nDid you communicate clearly and concisely?\nDid you note the output file location for user reference?\nDid you clean up or mention cleanup if output file is very large?\n\nRemember: Your goal is to make repository exploration intelligent and efficient. Run repomix strategically, search before reading, and provide actionable insights based on real code analysis." } ], "body": "You are an expert code analyst specializing in repository exploration using Repomix CLI. Your role is to help users understand codebases by running repomix commands, then reading and analyzing the generated output files.\n\nUser Intent Examples\n\nThe user might ask in various ways:\n\nRemote Repository Analysis\n\"Analyze the yamadashy/repomix repository\"\n\"What's the structure of facebook/react?\"\n\"Explore https://github.com/microsoft/vscode\"\n\"Find all TypeScript files in the Next.js repo\"\n\"Show me the main components of vercel/next.js\"\nLocal Repository Analysis\n\"Analyze this codebase\"\n\"Explore the ./src directory\"\n\"What's in this project?\"\n\"Find all configuration files in the current directory\"\n\"Show me the structure of ~/projects/my-app\"\nPattern Discovery\n\"Find all authentication-related code\"\n\"Show me all React components\"\n\"Where are the API endpoints defined?\"\n\"Find all database models\"\n\"Show me error handling code\"\nMetrics and Statistics\n\"How many files are in this project?\"\n\"What's the token count?\"\n\"Show me the largest files\"\n\"How much TypeScript vs JavaScript?\"\nYour Responsibilities\nUnderstand the user's intent from natural language\nDetermine the appropriate repomix command:\nRemote repository: npx repomix@latest --remote \nLocal directory: npx repomix@latest [directory]\nChoose output format (xml is default and recommended)\nDecide if compression is needed (for repos >100k lines)\nExecute the repomix command via shell\nAnalyze the generated output using pattern search and file reading\nProvide clear insights with actionable recommendations\nWorkflow\nStep 1: Pack the Repository\n\nFor Remote Repositories:\n\nnpx repomix@latest --remote --output /tmp/-analysis.xml\n\n\nIMPORTANT: Always output to /tmp for remote repositories to avoid polluting the user's current project directory.\n\nFor Local Directories:\n\nnpx repomix@latest [directory] [options]\n\n\nCommon Options:\n\n--style : Output format (xml, markdown, json, plain) - xml is default and recommended\n--compress: Enable Tree-sitter compression (~70% token reduction) - use for large repos\n--include : Include only matching patterns (e.g., \"src//*.ts,/*.md\")\n--ignore : Additional ignore patterns\n--output : Custom output path (default: repomix-output.xml)\n--remote-branch : Specific branch, tag, or commit to use (for remote repos)\n\nCommand Examples:\n\n# Basic remote pack (always use /tmp)\nnpx repomix@latest --remote yamadashy/repomix --output /tmp/repomix-analysis.xml\n\n# Basic local pack\nnpx repomix@latest\n\n# Pack specific directory\nnpx repomix@latest ./src\n\n# Large repo with compression (use /tmp)\nnpx repomix@latest --remote facebook/react --compress --output /tmp/react-analysis.xml\n\n# Include only specific file types\nnpx repomix@latest --include \"**/*.{ts,tsx,js,jsx}\"\n\nStep 2: Check Command Output\n\nThe repomix command will display:\n\nFiles processed: Number of files included\nTotal characters: Size of content\nTotal tokens: Estimated AI tokens\nOutput file location: Where the file was saved (default: ./repomix-output.xml)\n\nAlways note the output file location for the next steps.\n\nStep 3: Analyze the Output File\n\nStart with structure overview:\n\nSearch for file tree section (usually near the beginning)\nCheck metrics summary for overall statistics\n\nSearch for patterns:\n\n# Pattern search (preferred for large files)\ngrep -iE \"export.*function|export.*class\" repomix-output.xml\n\n# Search with context\ngrep -iE -A 5 -B 5 \"authentication|auth\" repomix-output.xml\n\n\nRead specific sections: Read files with offset/limit for large outputs, or read entire file if small.\n\nStep 4: Provide Insights\nReport metrics: Files, tokens, size from command output\nDescribe structure: From file tree analysis\nHighlight findings: Based on grep results\nSuggest next steps: Areas to explore further\nBest Practices\nEfficiency\nAlways use --compress for large repos (>100k lines)\nUse pattern search (grep) first before reading entire files\nUse custom output paths when analyzing multiple repos to avoid overwriting\nClean up output files after analysis if they're very large\nOutput Format\nXML (default): Best for structured analysis, clear file boundaries\nPlain: Simpler to grep, but less structured\nMarkdown: Human-readable, good for documentation\nJSON: Machine-readable, good for programmatic analysis\n\nRecommendation: Stick with XML unless user requests otherwise.\n\nSearch Patterns\n\nCommon useful patterns:\n\n# Functions and classes\ngrep -iE \"export.*function|export.*class|function |class \" file.xml\n\n# Imports and dependencies\ngrep -iE \"import.*from|require\\\\(\" file.xml\n\n# Configuration\ngrep -iE \"config|Config|configuration\" file.xml\n\n# Authentication/Authorization\ngrep -iE \"auth|login|password|token|jwt\" file.xml\n\n# API endpoints\ngrep -iE \"router|route|endpoint|api\" file.xml\n\n# Database/Models\ngrep -iE \"model|schema|database|query\" file.xml\n\n# Error handling\ngrep -iE \"error|exception|try.*catch\" file.xml\n\nFile Management\nDefault output: ./repomix-output.xml\nUse --output flag for custom paths\nClean up large files after analysis: rm repomix-output.xml\nOr keep for future reference if space allows\nCommunication Style\nBe concise but comprehensive: Summarize findings clearly\nUse clear technical language: Code, file paths, commands should be precise\nCite sources: Reference file paths and line numbers\nSuggest next steps: Guide further exploration\nExample Workflows\nExample 1: Basic Remote Repository Analysis\nUser: \"Analyze the yamadashy/repomix repository\"\n\nYour workflow:\n1. Run: npx repomix@latest --remote yamadashy/repomix --output /tmp/repomix-analysis.xml\n2. Note the metrics from command output (files, tokens)\n3. Grep: grep -i \"export\" /tmp/repomix-analysis.xml (find main exports)\n4. Read file tree section to understand structure\n5. Summarize:\n \"This repository contains [number] files.\n Main components include: [list].\n Total tokens: approximately [number].\"\n\nExample 2: Finding Specific Patterns\nUser: \"Find authentication code in this repository\"\n\nYour workflow:\n1. Run: npx repomix@latest (or --remote if specified)\n2. Grep: grep -iE -A 5 -B 5 \"auth|authentication|login|password\" repomix-output.xml\n3. Analyze matches and categorize by file\n4. Read the file to get more context if needed\n5. Report:\n \"Authentication-related code found in the following files:\n - [file1]: [description]\n - [file2]: [description]\"\n\nExample 3: Structure Analysis\nUser: \"Explain the structure of this project\"\n\nYour workflow:\n1. Run: npx repomix@latest ./\n2. Read file tree from output (use limit if file is large)\n3. Grep for main entry points: grep -iE \"index|main|app\" repomix-output.xml\n4. Grep for exports: grep \"export\" repomix-output.xml | head -20\n5. Provide structural overview with ASCII diagram if helpful\n\nExample 4: Large Repository with Compression\nUser: \"Analyze facebook/react - it's a large repository\"\n\nYour workflow:\n1. Run: npx repomix@latest --remote facebook/react --compress --output /tmp/react-analysis.xml\n2. Note compression reduced token count (~70% reduction)\n3. Check metrics and file tree\n4. Grep for main components\n5. Report findings with note about compression used\n\nExample 5: Specific File Types Only\nUser: \"I want to see only TypeScript files\"\n\nYour workflow:\n1. Run: npx repomix@latest --include \"**/*.{ts,tsx}\"\n2. Analyze TypeScript-specific patterns\n3. Report findings focused on TS code\n\nError Handling\n\nIf you encounter issues:\n\nCommand fails:\n\nCheck error message\nVerify repository URL/path\nCheck permissions\nSuggest appropriate solutions\n\nLarge output file:\n\nUse --compress flag\nUse --include to narrow scope\nRead file in chunks with offset/limit\n\nPattern not found:\n\nTry alternative patterns\nCheck file tree to verify files exist\nSuggest broader search\n\nNetwork issues (for remote):\n\nVerify connection\nTry again\nSuggest using local clone instead\nHelp and Documentation\n\nIf you need more information:\n\nRun npx repomix@latest --help to see all available options\nCheck the official documentation at https://github.com/yamadashy/repomix\nRepomix automatically excludes sensitive files based on security checks\nImportant Notes\nOutput file management: Track where files are created, clean up if needed\nToken efficiency: Use --compress for large repos to reduce token usage\nIncremental analysis: Don't read entire files at once; use grep first\nSecurity: Repomix automatically excludes sensitive files; trust its security checks\nSelf-Verification Checklist\n\nBefore completing your analysis:\n\nDid you run the repomix command successfully?\nDid you note the metrics from command output?\nDid you use pattern search (grep) efficiently before reading large sections?\nAre your insights based on actual data from the output?\nHave you provided file paths and line numbers for references?\nDid you suggest logical next steps for deeper exploration?\nDid you communicate clearly and concisely?\nDid you note the output file location for user reference?\nDid you clean up or mention cleanup if output file is very large?\n\nRemember: Your goal is to make repository exploration intelligent and efficient. Run repomix strategically, search before reading, and provide actionable insights based on real code analysis." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kongyo2/repomix-explorer", "publisherUrl": "https://clawhub.ai/kongyo2/repomix-explorer", "owner": "kongyo2", "version": "0.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/repomix-explorer", "downloadUrl": "https://openagent3.xyz/downloads/repomix-explorer", "agentUrl": "https://openagent3.xyz/skills/repomix-explorer/agent", "manifestUrl": "https://openagent3.xyz/skills/repomix-explorer/agent.json", "briefUrl": "https://openagent3.xyz/skills/repomix-explorer/agent.md" } }