[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AGK8VC5VGZVZNMGM2KBZA2":3,"skill-same:01M7AGK8VC5VGZVZNMGM2KBZA2":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":29,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7AGK8VC5VGZVZNMGM2KBZA2","ck:repomix",null,"Pack repositories into AI-friendly files with Repomix (XML, Markdown, plain text). Use for codebase snapshots, LLM context preparation, security audits, third-party library analysis.","manhvann\u002Fcodexkit","manhvann","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108862213?v=4","01M7AGBGXSB8Z8HXXR27QKX035","Manh Nguyen Van","01M7AGBGYDJPBR2EYEWJ0G1K8J",88,"MIT","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ck:repomix\ndescription: Pack repositories into AI-friendly files with Repomix (XML, Markdown, plain text). Use for codebase snapshots, LLM context preparation, security audits, third-party library analysis.\nargument-hint: \"[path] [--style xml|markdown|plain|json]\"\n---\n\n# Repomix Skill\n\nRepomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like Codex, ChatGPT, and Gemini.\n\n## When to Use\n\nUse when:\n- Packaging codebases for AI analysis\n- Creating repository snapshots for LLM context\n- Analyzing third-party libraries\n- Preparing for security audits\n- Generating documentation context\n- Investigating bugs across large codebases\n- Creating AI-friendly code representations\n\n## Quick Start\n\n### Check Installation\n```bash\nrepomix --version\n```\n\n### Install\n```bash\n# npm\nnpm install -g repomix\n\n# Homebrew (macOS\u002FLinux)\nbrew install repomix\n```\n\n### Basic Usage\n```bash\n# Package current directory (generates repomix-output.xml)\nrepomix\n\n# Specify output format\nrepomix --style markdown\nrepomix --style json\n\n# Package remote repository\nnpx repomix --remote owner\u002Frepo\n\n# Custom output with filters\nrepomix --include \"src\u002F**\u002F*.ts\" --remove-comments -o output.md\n```\n\n## Core Capabilities\n\n### Repository Packaging\n- AI-optimized formatting with clear separators\n- Multiple output formats: XML, Markdown, JSON, Plain text\n- Git-aware processing (respects .gitignore)\n- Token counting for LLM context management\n- Security checks for sensitive information\n\n### Remote Repository Support\nProcess remote repositories without cloning:\n```bash\n# Shorthand\nnpx repomix --remote yamadashy\u002Frepomix\n\n# Full URL\nnpx repomix --remote https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\n\n# Specific commit\nnpx repomix --remote https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\u002Fcommit\u002Fhash\n```\n\n### Comment Removal\nStrip comments from supported languages (HTML, CSS, JavaScript, TypeScript, Vue, Svelte, Python, PHP, Ruby, C, C#, Java, Go, Rust, Swift, Kotlin, Dart, Shell, YAML):\n```bash\nrepomix --remove-comments\n```\n\n## Common Use Cases\n\n### Code Review Preparation\n```bash\n# Package feature branch for AI review\nrepomix --include \"src\u002F**\u002F*.ts\" --remove-comments -o review.md --style markdown\n```\n\n### Security Audit\n```bash\n# Package third-party library\nnpx repomix --remote vendor\u002Flibrary --style xml -o audit.xml\n```\n\n### Documentation Generation\n```bash\n# Package with docs and code\nrepomix --include \"src\u002F**,docs\u002F**,*.md\" --style markdown -o context.md\n```\n\n### Bug Investigation\n```bash\n# Package specific modules\nrepomix --include \"src\u002Fauth\u002F**,src\u002Fapi\u002F**\" -o debug-context.xml\n```\n\n### Implementation Planning\n```bash\n# Full codebase context\nrepomix --remove-comments --copy\n```\n\n## Command Line Reference\n\n### File Selection\n```bash\n# Include specific patterns\nrepomix --include \"src\u002F**\u002F*.ts,*.md\"\n\n# Ignore additional patterns\nrepomix -i \"tests\u002F**,*.test.js\"\n\n# Disable .gitignore rules\nrepomix --no-gitignore\n```\n\n### Output Options\n```bash\n# Output format\nrepomix --style markdown  # or xml, json, plain\n\n# Output file path\nrepomix -o output.md\n\n# Remove comments\nrepomix --remove-comments\n\n# Copy to clipboard\nrepomix --copy\n```\n\n### Configuration\n```bash\n# Use custom config file\nrepomix -c custom-config.json\n\n# Initialize new config\nrepomix --init  # creates repomix.config.json\n```\n\n## Token Management\n\nRepomix automatically counts tokens for individual files, total repository, and per-format output.\n\nTypical LLM context limits:\n- Codex Sonnet 4.5: ~200K tokens\n- GPT-4: ~128K tokens\n- GPT-3.5: ~16K tokens\n\n### Token Count Optimization\nUnderstanding your codebase's token distribution is crucial for optimizing AI interactions. Use the --token-count-tree option to visualize token usage across your project:\n\n```bash\nrepomix --token-count-tree\n```\nThis displays a hierarchical view of your codebase with token counts:\n\n```\n🔢 Token Count Tree:\n────────────────────\n└── src\u002F (70,925 tokens)\n    ├── cli\u002F (12,714 tokens)\n    │   ├── actions\u002F (7,546 tokens)\n    │   └── reporters\u002F (990 tokens)\n    └── core\u002F (41,600 tokens)\n        ├── file\u002F (10,098 tokens)\n        └── output\u002F (5,808 tokens)\n```\nYou can also set a minimum token threshold to focus on larger files:\n\n```bash\nrepomix --token-count-tree 1000  # Only show files\u002Fdirectories with 1000+ tokens\n```\n\nThis helps you:\n\n- Identify token-heavy files that might exceed AI context limits\n- Optimize file selection using --include and --ignore patterns\n- Plan compression strategies by targeting the largest contributors\n- Balance content vs. context when preparing code for AI analysis\n\n## Security Considerations\n\nRepomix uses Secretlint to detect sensitive data (API keys, passwords, credentials, private keys, AWS secrets).\n\nBest practices:\n1. Always review output before sharing\n2. Use `.repomixignore` for sensitive files\n3. Enable security checks for unknown codebases\n4. Avoid packaging `.env` files\n5. Check for hardcoded credentials\n\nDisable security checks if needed:\n```bash\nrepomix --no-security-check\n```\n\n## Implementation Workflow\n\nWhen user requests repository packaging:\n\n1. **Assess Requirements**\n   - Identify target repository (local\u002Fremote)\n   - Determine output format needed\n   - Check for sensitive data concerns\n\n2. **Configure Filters**\n   - Set include patterns for relevant files\n   - Add ignore patterns for unnecessary files\n   - Enable\u002Fdisable comment removal\n\n3. **Execute Packaging**\n   - Run repomix with appropriate options\n   - Monitor token counts\n   - Verify security checks\n\n4. **Validate Output**\n   - Review generated file\n   - Confirm no sensitive data\n   - Check token limits for target LLM\n\n5. **Deliver Context**\n   - Provide packaged file to user\n   - Include token count summary\n   - Note any warnings or issues\n\n## Reference Documentation\n\nFor detailed information, see:\n- [Configuration Reference](.\u002Freferences\u002Fconfiguration.md) - Config files, include\u002Fexclude patterns, output formats, advanced options\n- [Usage Patterns](.\u002Freferences\u002Fusage-patterns.md) - AI analysis workflows, security audit preparation, documentation generation, library evaluation\n\n## Additional Resources\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fyamadashy\u002Frepomix\n- Documentation: https:\u002F\u002Frepomix.com\u002Fguide\u002F\n- MCP Server: Available for AI assistant integration\n","# Repomix Skill\n\nRepomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like Codex, ChatGPT, and Gemini.\n\n## When to Use\n\nUse when:\n- Packaging codebases for AI analysis\n- Creating repository snapshots for LLM context\n- Analyzing third-party libraries\n- Preparing for security audits\n- Generating documentation context\n- Investigating bugs across large codebases\n- Creating AI-friendly code representations\n\n## Quick Start\n\n### Check Installation\n```bash\nrepomix --version\n```\n\n### Install\n```bash\n# npm\nnpm install -g repomix\n\n# Homebrew (macOS\u002FLinux)\nbrew install repomix\n```\n\n### Basic Usage\n```bash\n# Package current directory (generates repomix-output.xml)\nrepomix\n\n# Specify output format\nrepomix --style markdown\nrepomix --style json\n\n# Package remote repository\nnpx repomix --remote owner\u002Frepo\n\n# Custom output with filters\nrepomix --include \"src\u002F**\u002F*.ts\" --remove-comments -o output.md\n```\n\n## Core Capabilities\n\n### Repository Packaging\n- AI-optimized formatting with clear separators\n- Multiple output formats: XML, Markdown, JSON, Plain text\n- Git-aware processing (respects .gitignore)\n- Token counting for LLM context management\n- Security checks for sensitive information\n\n### Remote Repository Support\nProcess remote repositories without cloning:\n```bash\n# Shorthand\nnpx repomix --remote yamadashy\u002Frepomix\n\n# Full URL\nnpx repomix --remote https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\n\n# Specific commit\nnpx repomix --remote https:\u002F\u002Fgithub.com\u002Fowner\u002Frepo\u002Fcommit\u002Fhash\n```\n\n### Comment Removal\nStrip comments from supported languages (HTML, CSS, JavaScript, TypeScript, Vue, Svelte, Python, PHP, Ruby, C, C#, Java, Go, Rust, Swift, Kotlin, Dart, Shell, YAML):\n```bash\nrepomix --remove-comments\n```\n\n## Common Use Cases\n\n### Code Review Preparation\n```bash\n# Package feature branch for AI review\nrepomix --include \"src\u002F**\u002F*.ts\" --remove-comments -o review.md --style markdown\n```\n\n### Security Audit\n```bash\n# Package third-party library\nnpx repomix --remote vendor\u002Flibrary --style xml -o audit.xml\n```\n\n### Documentation Generation\n```bash\n# Package with docs and code\nrepomix --include \"src\u002F**,docs\u002F**,*.md\" --style markdown -o context.md\n```\n\n### Bug Investigation\n```bash\n# Package specific modules\nrepomix --include \"src\u002Fauth\u002F**,src\u002Fapi\u002F**\" -o debug-context.xml\n```\n\n### Implementation Planning\n```bash\n# Full codebase context\nrepomix --remove-comments --copy\n```\n\n## Command Line Reference\n\n### File Selection\n```bash\n# Include specific patterns\nrepomix --include \"src\u002F**\u002F*.ts,*.md\"\n\n# Ignore additional patterns\nrepomix -i \"tests\u002F**,*.test.js\"\n\n# Disable .gitignore rules\nrepomix --no-gitignore\n```\n\n### Output Options\n```bash\n# Output format\nrepomix --style markdown  # or xml, json, plain\n\n# Output file path\nrepomix -o output.md\n\n# Remove comments\nrepomix --remove-comments\n\n# Copy to clipboard\nrepomix --copy\n```\n\n### Configuration\n```bash\n# Use custom config file\nrepomix -c custom-config.json\n\n# Initialize new config\nrepomix --init  # creates repomix.config.json\n```\n\n## Token Management\n\nRepomix automatically counts tokens for individual files, total repository, and per-format output.\n\nTypical LLM context limits:\n- Codex Sonnet 4.5: ~200K tokens\n- GPT-4: ~128K tokens\n- GPT-3.5: ~16K tokens\n\n### Token Count Optimization\nUnderstanding your codebase's token distribution is crucial for optimizing AI interactions. Use the --token-count-tree option to visualize token usage across your project:\n\n```bash\nrepomix --token-count-tree\n```\nThis displays a hierarchical view of your codebase with token counts:\n\n```\n🔢 Token Count Tree:\n────────────────────\n└── src\u002F (70,925 tokens)\n    ├── cli\u002F (12,714 tokens)\n    │   ├── actions\u002F (7,546 tokens)\n    │   └── reporters\u002F (990 tokens)\n    └── core\u002F (41,600 tokens)\n        ├── file\u002F (10,098 tokens)\n        └── output\u002F (5,808 tokens)\n```\nYou can also set a minimum token threshold to focus on larger files:\n\n```bash\nrepomix --token-count-tree 1000  # Only show files\u002Fdirectories with 1000+ tokens\n```\n\nThis helps you:\n\n- Identify token-heavy files that might exceed AI context limits\n- Optimize file selection using --include and --ignore patterns\n- Plan compression strategies by targeting the largest contributors\n- Balance content vs. context when preparing code for AI analysis\n\n## Security Considerations\n\nRepomix uses Secretlint to detect sensitive data (API keys, passwords, credentials, private keys, AWS secrets).\n\nBest practices:\n1. Always review output before sharing\n2. Use `.repomixignore` for sensitive files\n3. Enable security checks for unknown codebases\n4. Avoid packaging `.env` files\n5. Check for hardcoded credentials\n\nDisable security checks if needed:\n```bash\nrepomix --no-security-check\n```\n\n## Implementation Workflow\n\nWhen user requests repository packaging:\n\n1. **Assess Requirements**\n   - Identify target repository (local\u002Fremote)\n   - Determine output format needed\n   - Check for sensitive data concerns\n\n2. **Configure Filters**\n   - Set include patterns for relevant files\n   - Add ignore patterns for unnecessary files\n   - Enable\u002Fdisable comment removal\n\n3. **Execute Packaging**\n   - Run repomix with appropriate options\n   - Monitor token counts\n   - Verify security checks\n\n4. **Validate Output**\n   - Review generated file\n   - Confirm no sensitive data\n   - Check token limits for target LLM\n\n5. **Deliver Context**\n   - Provide packaged file to user\n   - Include token count summary\n   - Note any warnings or issues\n\n## Reference Documentation\n\nFor detailed information, see:\n- [Configuration Reference](.\u002Freferences\u002Fconfiguration.md) - Config files, include\u002Fexclude patterns, output formats, advanced options\n- [Usage Patterns](.\u002Freferences\u002Fusage-patterns.md) - AI analysis workflows, security audit preparation, documentation generation, library evaluation\n\n## Additional Resources\n\n- GitHub: https:\u002F\u002Fgithub.com\u002Fyamadashy\u002Frepomix\n- Documentation: https:\u002F\u002Frepomix.com\u002Fguide\u002F\n- MCP Server: Available for AI assistant integration\n",{"name":5,"description":7,"argument-hint":24},"[path] [--style xml|markdown|plain|json]","main","f4f392e3e6ac09daca9d7c44c3afb20945435e36",".agents\u002Fskills\u002Frepomix",79,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit","https:\u002F\u002Fgithub.com\u002Fmanhvann","Backend Engineer passionate about building reliable systems and contributing to open source.","2026-08-29 12:03:10",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add manhvann\u002Fcodexkit --skill \"ck:repomix\"",{"tool":39,"command":40},"bunx","bunx skills add manhvann\u002Fcodexkit --skill \"ck:repomix\"",{"tool":42,"command":43},"pnpm","pnpm dlx skills add manhvann\u002Fcodexkit --skill \"ck:repomix\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002FSKILL.md",true,[47,53,57,63,67,71,75],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fconfiguration.md","REFERENCE","参考文档",4415,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Freferences\u002Fconfiguration.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fusage-patterns.md",7017,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Freferences\u002Fusage-patterns.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002FREADME.md","SCRIPT","脚本",3795,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Fscripts\u002FREADME.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Frepomix_batch.py",13322,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Fscripts\u002Frepomix_batch.py",{"path":68,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Frepos.example.json",252,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Fscripts\u002Frepos.example.json",{"path":72,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Frequirements.txt",356,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Fscripts\u002Frequirements.txt",{"path":76,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Ftests\u002Ftest_repomix_batch.py",18939,"https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Frepomix\u002Fscripts\u002Ftests\u002Ftest_repomix_batch.py",[80,87,95,102,109,116],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7AGNE44ZPV7VVMCZCDQ0X55","ck:worktree","Create isolated git worktree for parallel development in monorepos.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworktree\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":91,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7AGNB7EGT5ZKNRAF5M1V6D0","ck:web-testing","Web testing with Playwright, Vitest, k6. E2E\u002Funit\u002Fintegration\u002Fload\u002Fsecurity\u002Fvisual\u002Fa11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-testing\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7AGN7W938QCYZ70A8B0X70G","ck:web-frameworks","Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching strategies, shared dependencies.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-frameworks\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7AGN5HKJM49Z49N6XFDQB82","ck:web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7AGN4D60DGGYM2YGZ80NT2A","ck:watzup","Review recent changes and wrap up the current work session.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwatzup\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M7AGN308V7338SEEX8A6DZ53","ck:use-mcp","Utilize MCP server tools with intelligent discovery and execution.","https:\u002F\u002Fgithub.com\u002Fmanhvann\u002Fcodexkit\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fuse-mcp\u002FSKILL.md",[],[]]