[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79J26ZSWVZQBWVD5QQ0JAT2":3,"skill-same:01M79J26ZSWVZQBWVD5QQ0JAT2":78},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M79J26ZSWVZQBWVD5QQ0JAT2","CodeReview Automated Code Review Assistant",null,"AI-powered code review that combines fast local static analysis with deep AI reasoning. Catches bugs, security vulnerabilities, performance issues, and style problems. Supports Anthropic, OpenAI, and Ollama models. Falls back to local regex analysis when offline.","knownasnaffy\u002Fprompthound","knownasnaffy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64461700?v=4","01M784GPN9EQ22R78AQ2NBRP0Y","Barinderpreet Singh","01M784GPNVVWKW21N9AYXREQQJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04409\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04409\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nslug: \"code-review-sr\"\nname: \"CodeReview Automated Code Review Assistant\"\ndescription: \"AI-powered code review that combines fast local static analysis with deep AI reasoning. Catches bugs, security vulnerabilities, performance issues, and style problems. Supports Anthropic, OpenAI, and Ollama models. Falls back to local regex analysis when offline.\"\nauthor: \"@TheShadowRose\"\nversion: \"1.0.4\"\ntags: [\"code-review\", \"ai\", \"static-analysis\", \"security\"]\nlicense: \"MIT\"\nenv:\n  ANTHROPIC_API_KEY: \"Optional - for Anthropic\u002FClaude models (or set CLAUDE_API_KEY)\"\n  OPENAI_API_KEY: \"Optional - for OpenAI\u002FGPT models\"\n  OLLAMA_HOST: \"Optional - Ollama base URL, default http:\u002F\u002Flocalhost:11434\"\n  OLLAMA_PORT: \"Optional - Ollama port, default 11434\"\n---\n\n# CodeReview — AI-Powered Code Review Assistant\n\nCombines **fast local regex pattern matching** with **deep AI-powered analysis** to deliver thorough, actionable code reviews. Runs a local static analysis pre-pass first, then sends code and initial findings to an AI model for comprehensive review including bug detection, security analysis, performance suggestions, and style feedback.\n\n---\n\n## How It Works\n\n1. **Local Pre-Pass** — Regex-based pattern matching runs instantly, catching hardcoded secrets, eval usage, SQL injection patterns, empty catch blocks, long functions, and more.\n2. **AI Deep Review** — The full source code and local findings are sent to your chosen AI model (Anthropic, OpenAI, or Ollama) for deep reasoning about bugs, logic errors, performance, and architecture.\n3. **Graceful Fallback** — If no API key is set or the AI call fails, you still get local static analysis results. Never blocks your workflow.\n\n## Usage\n\n```javascript\nconst { CodeReview } = require('.\u002Fsrc\u002Fcode-review');\n\n\u002F\u002F AI-powered review (default: anthropic\u002Fclaude-haiku-4-5)\nconst reviewer = new CodeReview({ model: 'anthropic\u002Fclaude-haiku-4-5' });\nconst result = await reviewer.review('.\u002Fsrc\u002Fauth.js');\n\nconsole.log(result.score);        \u002F\u002F 1-10\nconsole.log(result.issues);       \u002F\u002F Array of issues with severity, line, type, message\nconsole.log(result.suggestions);  \u002F\u002F Actionable improvement suggestions\nconsole.log(result.summary);      \u002F\u002F Concise quality summary\nconsole.log(result.aiPowered);    \u002F\u002F true\n\n\u002F\u002F Review an entire directory\nconst dirResult = await reviewer.reviewDir('.\u002Fsrc', {\n  include: ['*.js', '*.ts'],\n  exclude: ['node_modules', '.git', 'dist'],\n  concurrency: 3\n});\nconsole.log(dirResult.averageScore);\nconsole.log(dirResult.totalIssues);\n```\n\n### Model Options\n\n| Provider | Example | API Key Env Var |\n|----------|---------|-----------------|\n| **Anthropic** | `anthropic\u002Fclaude-haiku-4-5` | `ANTHROPIC_API_KEY` |\n| **OpenAI** | `openai\u002Fgpt-4o-mini` | `OPENAI_API_KEY` |\n| **Ollama** (local) | `ollama\u002Fllama3` | None required |\n\n```javascript\n\u002F\u002F OpenAI\nconst reviewer = new CodeReview({ model: 'openai\u002Fgpt-4o-mini' });\n\n\u002F\u002F Local Ollama\nconst reviewer = new CodeReview({ model: 'ollama\u002Fcodellama' });\n\n\u002F\u002F Local-only (no AI, regex patterns only)\nconst reviewer = new CodeReview();\nconst result = await reviewer.review('.\u002Fsrc\u002Fapp.js');\n\u002F\u002F result.aiPowered === false\n```\n\n## What It Catches\n\n| Category | Examples |\n|----------|---------|\n| **Bugs** | Null references, off-by-one errors, race conditions, empty catch blocks |\n| **Security** | SQL injection, XSS, hardcoded secrets, eval usage |\n| **Performance** | N+1 queries, unnecessary loops, memory leaks |\n| **Style** | Inconsistent naming, long functions, dead code, console.log in production |\n| **Logic** | Unreachable code, redundant conditions |\n| **Maintainability** | Deeply nested callbacks, magic numbers, TODO\u002FFIXME markers |\n\n## Output Format\n\n```json\n{\n  \"file\": \".\u002Fsrc\u002Fauth.js\",\n  \"score\": 5,\n  \"issues\": [\n    {\n      \"severity\": \"high\",\n      \"line\": 42,\n      \"type\": \"security\",\n      \"message\": \"User input passed directly to SQL query without parameterization\"\n    },\n    {\n      \"severity\": \"medium\",\n      \"line\": 87,\n      \"type\": \"bugs\",\n      \"message\": \"Empty catch block silently swallows database connection errors\"\n    }\n  ],\n  \"suggestions\": [\n    \"Use parameterized queries or an ORM to prevent SQL injection on line 42\",\n    \"Add error logging in the catch block on line 87\",\n    \"Extract the authentication logic into a separate middleware module\"\n  ],\n  \"summary\": \"The auth module has a critical SQL injection vulnerability and several error handling gaps. Core logic is sound but needs security hardening.\",\n  \"totalIssues\": 2,\n  \"lines\": 142,\n  \"aiPowered\": true,\n  \"model\": \"anthropic\u002Fclaude-haiku-4-5\"\n}\n```\n\n## Language Support\n\nWorks with any language your AI model understands. The local pre-pass targets common patterns across languages. AI review tested with:\n\nJavaScript, TypeScript, Python, Go, Rust, Java, C#, Ruby, PHP, Swift, Kotlin\n\n## Technical Details\n\n- **Zero npm dependencies** — Pure Node.js using only built-in `https`, `http`, `fs`, and `path` modules\n- **File truncation** — Files are truncated at 8,000 characters before sending to AI to stay within token limits\n- **Concurrency control** — Directory reviews process files in configurable parallel batches (default: 3)\n- **Graceful degradation** — AI failures never crash; local results are always available\n\n---\n\n## ⚠️ Disclaimer\n\nThis software is provided \"AS IS\", without warranty of any kind, express or implied.\n\n**USE AT YOUR OWN RISK.**\n\n- The author(s) are NOT liable for any damages, losses, or consequences arising from\n  the use or misuse of this software — including but not limited to financial loss,\n  data loss, security breaches, business interruption, or any indirect\u002Fconsequential damages.\n- This software does NOT constitute financial, legal, trading, or professional advice.\n- Users are solely responsible for evaluating whether this software is suitable for\n  their use case, environment, and risk tolerance.\n- No guarantee is made regarding accuracy, reliability, completeness, or fitness\n  for any particular purpose.\n- The author(s) are not responsible for how third parties use, modify, or distribute\n  this software after purchase.\n\nBy downloading, installing, or using this software, you acknowledge that you have read\nthis disclaimer and agree to use the software entirely at your own risk.\n\n\n**DATA DISCLAIMER:** When an AI model is configured, this software sends your source code and static analysis findings to the configured provider (Anthropic, OpenAI, or a local Ollama instance). Do not run it over code containing secrets or sensitive data unless you understand where data is sent. Without an API key, all analysis is local-only.\nThe author(s) are not responsible for data loss, corruption, or unauthorized access\nresulting from software bugs, system failures, or user error. Always maintain\nindependent backups of important data. When AI models are configured, file contents\nare sent to the respective AI provider's API (Anthropic, OpenAI, or your local Ollama\ninstance). No data is transmitted externally when running in local-only mode (no model configured).\n\n---\n\n## Support & Links\n\n| | |\n|---|---|\n| 🐛 **Bug Reports** | TheShadowyRose@proton.me |\n| ☕ **Ko-fi** | [ko-fi.com\u002Ftheshadowrose](https:\u002F\u002Fko-fi.com\u002Ftheshadowrose) |\n| 🛒 **Gumroad** | [shadowyrose.gumroad.com](https:\u002F\u002Fshadowyrose.gumroad.com) |\n| 🐦 **Twitter** | [@TheShadowyRose](https:\u002F\u002Ftwitter.com\u002FTheShadowyRose) |\n| 🐙 **GitHub** | [github.com\u002FTheShadowRose](https:\u002F\u002Fgithub.com\u002FTheShadowRose) |\n| 🧠 **PromptBase** | [promptbase.com\u002Fprofile\u002Fshadowrose](https:\u002F\u002Fpromptbase.com\u002Fprofile\u002Fshadowrose) |\n\n*Built with [OpenClaw](https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw) — thank you for making this possible.*\n\n---\n\n🛠️ **Need something custom?** Custom OpenClaw agents & skills starting at $500. If you can describe it, I can build it. → [Hire me on Fiverr](https:\u002F\u002Fwww.fiverr.com\u002Fs\u002FjjmlZ0v)","# CodeReview — AI-Powered Code Review Assistant\n\nCombines **fast local regex pattern matching** with **deep AI-powered analysis** to deliver thorough, actionable code reviews. Runs a local static analysis pre-pass first, then sends code and initial findings to an AI model for comprehensive review including bug detection, security analysis, performance suggestions, and style feedback.\n\n---\n\n## How It Works\n\n1. **Local Pre-Pass** — Regex-based pattern matching runs instantly, catching hardcoded secrets, eval usage, SQL injection patterns, empty catch blocks, long functions, and more.\n2. **AI Deep Review** — The full source code and local findings are sent to your chosen AI model (Anthropic, OpenAI, or Ollama) for deep reasoning about bugs, logic errors, performance, and architecture.\n3. **Graceful Fallback** — If no API key is set or the AI call fails, you still get local static analysis results. Never blocks your workflow.\n\n## Usage\n\n```javascript\nconst { CodeReview } = require('.\u002Fsrc\u002Fcode-review');\n\n\u002F\u002F AI-powered review (default: anthropic\u002Fclaude-haiku-4-5)\nconst reviewer = new CodeReview({ model: 'anthropic\u002Fclaude-haiku-4-5' });\nconst result = await reviewer.review('.\u002Fsrc\u002Fauth.js');\n\nconsole.log(result.score);        \u002F\u002F 1-10\nconsole.log(result.issues);       \u002F\u002F Array of issues with severity, line, type, message\nconsole.log(result.suggestions);  \u002F\u002F Actionable improvement suggestions\nconsole.log(result.summary);      \u002F\u002F Concise quality summary\nconsole.log(result.aiPowered);    \u002F\u002F true\n\n\u002F\u002F Review an entire directory\nconst dirResult = await reviewer.reviewDir('.\u002Fsrc', {\n  include: ['*.js', '*.ts'],\n  exclude: ['node_modules', '.git', 'dist'],\n  concurrency: 3\n});\nconsole.log(dirResult.averageScore);\nconsole.log(dirResult.totalIssues);\n```\n\n### Model Options\n\n| Provider | Example | API Key Env Var |\n|----------|---------|-----------------|\n| **Anthropic** | `anthropic\u002Fclaude-haiku-4-5` | `ANTHROPIC_API_KEY` |\n| **OpenAI** | `openai\u002Fgpt-4o-mini` | `OPENAI_API_KEY` |\n| **Ollama** (local) | `ollama\u002Fllama3` | None required |\n\n```javascript\n\u002F\u002F OpenAI\nconst reviewer = new CodeReview({ model: 'openai\u002Fgpt-4o-mini' });\n\n\u002F\u002F Local Ollama\nconst reviewer = new CodeReview({ model: 'ollama\u002Fcodellama' });\n\n\u002F\u002F Local-only (no AI, regex patterns only)\nconst reviewer = new CodeReview();\nconst result = await reviewer.review('.\u002Fsrc\u002Fapp.js');\n\u002F\u002F result.aiPowered === false\n```\n\n## What It Catches\n\n| Category | Examples |\n|----------|---------|\n| **Bugs** | Null references, off-by-one errors, race conditions, empty catch blocks |\n| **Security** | SQL injection, XSS, hardcoded secrets, eval usage |\n| **Performance** | N+1 queries, unnecessary loops, memory leaks |\n| **Style** | Inconsistent naming, long functions, dead code, console.log in production |\n| **Logic** | Unreachable code, redundant conditions |\n| **Maintainability** | Deeply nested callbacks, magic numbers, TODO\u002FFIXME markers |\n\n## Output Format\n\n```json\n{\n  \"file\": \".\u002Fsrc\u002Fauth.js\",\n  \"score\": 5,\n  \"issues\": [\n    {\n      \"severity\": \"high\",\n      \"line\": 42,\n      \"type\": \"security\",\n      \"message\": \"User input passed directly to SQL query without parameterization\"\n    },\n    {\n      \"severity\": \"medium\",\n      \"line\": 87,\n      \"type\": \"bugs\",\n      \"message\": \"Empty catch block silently swallows database connection errors\"\n    }\n  ],\n  \"suggestions\": [\n    \"Use parameterized queries or an ORM to prevent SQL injection on line 42\",\n    \"Add error logging in the catch block on line 87\",\n    \"Extract the authentication logic into a separate middleware module\"\n  ],\n  \"summary\": \"The auth module has a critical SQL injection vulnerability and several error handling gaps. Core logic is sound but needs security hardening.\",\n  \"totalIssues\": 2,\n  \"lines\": 142,\n  \"aiPowered\": true,\n  \"model\": \"anthropic\u002Fclaude-haiku-4-5\"\n}\n```\n\n## Language Support\n\nWorks with any language your AI model understands. The local pre-pass targets common patterns across languages. AI review tested with:\n\nJavaScript, TypeScript, Python, Go, Rust, Java, C#, Ruby, PHP, Swift, Kotlin\n\n## Technical Details\n\n- **Zero npm dependencies** — Pure Node.js using only built-in `https`, `http`, `fs`, and `path` modules\n- **File truncation** — Files are truncated at 8,000 characters before sending to AI to stay within token limits\n- **Concurrency control** — Directory reviews process files in configurable parallel batches (default: 3)\n- **Graceful degradation** — AI failures never crash; local results are always available\n\n---\n\n## ⚠️ Disclaimer\n\nThis software is provided \"AS IS\", without warranty of any kind, express or implied.\n\n**USE AT YOUR OWN RISK.**\n\n- The author(s) are NOT liable for any damages, losses, or consequences arising from\n  the use or misuse of this software — including but not limited to financial loss,\n  data loss, security breaches, business interruption, or any indirect\u002Fconsequential damages.\n- This software does NOT constitute financial, legal, trading, or professional advice.\n- Users are solely responsible for evaluating whether this software is suitable for\n  their use case, environment, and risk tolerance.\n- No guarantee is made regarding accuracy, reliability, completeness, or fitness\n  for any particular purpose.\n- The author(s) are not responsible for how third parties use, modify, or distribute\n  this software after purchase.\n\nBy downloading, installing, or using this software, you acknowledge that you have read\nthis disclaimer and agree to use the software entirely at your own risk.\n\n\n**DATA DISCLAIMER:** When an AI model is configured, this software sends your source code and static analysis findings to the configured provider (Anthropic, OpenAI, or a local Ollama instance). Do not run it over code containing secrets or sensitive data unless you understand where data is sent. Without an API key, all analysis is local-only.\nThe author(s) are not responsible for data loss, corruption, or unauthorized access\nresulting from software bugs, system failures, or user error. Always maintain\nindependent backups of important data. When AI models are configured, file contents\nare sent to the respective AI provider's API (Anthropic, OpenAI, or your local Ollama\ninstance). No data is transmitted externally when running in local-only mode (no model configured).\n\n---\n\n## Support & Links\n\n| | |\n|---|---|\n| 🐛 **Bug Reports** | TheShadowyRose@proton.me |\n| ☕ **Ko-fi** | [ko-fi.com\u002Ftheshadowrose](https:\u002F\u002Fko-fi.com\u002Ftheshadowrose) |\n| 🛒 **Gumroad** | [shadowyrose.gumroad.com](https:\u002F\u002Fshadowyrose.gumroad.com) |\n| 🐦 **Twitter** | [@TheShadowyRose](https:\u002F\u002Ftwitter.com\u002FTheShadowyRose) |\n| 🐙 **GitHub** | [github.com\u002FTheShadowRose](https:\u002F\u002Fgithub.com\u002FTheShadowRose) |\n| 🧠 **PromptBase** | [promptbase.com\u002Fprofile\u002Fshadowrose](https:\u002F\u002Fpromptbase.com\u002Fprofile\u002Fshadowrose) |\n\n*Built with [OpenClaw](https:\u002F\u002Fgithub.com\u002Fopenclaw\u002Fopenclaw) — thank you for making this possible.*\n\n---\n\n🛠️ **Need something custom?** Custom OpenClaw agents & skills starting at $500. If you can describe it, I can build it. → [Hire me on Fiverr](https:\u002F\u002Fwww.fiverr.com\u002Fs\u002FjjmlZ0v)",{"env":25,"name":5,"slug":30,"tags":31,"author":36,"license":15,"version":37,"description":7},{"OLLAMA_HOST":26,"OLLAMA_PORT":27,"OPENAI_API_KEY":28,"ANTHROPIC_API_KEY":29},"Optional - Ollama base URL, default http:\u002F\u002Flocalhost:11434","Optional - Ollama port, default 11434","Optional - for OpenAI\u002FGPT models","Optional - for Anthropic\u002FClaude models (or set CLAUDE_API_KEY)","code-review-sr",[32,33,34,35],"code-review","ai","static-analysis","security","@TheShadowRose","1.0.4","main","c52d4f98d93fb20c8e316f773e3b6dbfca1569c3","dataset\u002Fcase_04409",1,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound","https:\u002F\u002Fgithub.com\u002Fknownasnaffy","https:\u002F\u002Fbarinderpreet.com\u002F","My IDE is louder than my social life.","2026-10-26 21:36:33",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add knownasnaffy\u002Fprompthound --skill \"CodeReview Automated Code Review Assistant\"",{"tool":53,"command":54},"bunx","bunx skills add knownasnaffy\u002Fprompthound --skill \"CodeReview Automated Code Review Assistant\"",{"tool":56,"command":57},"pnpm","pnpm dlx skills add knownasnaffy\u002Fprompthound --skill \"CodeReview Automated Code Review Assistant\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04409\u002FSKILL.md",true,[61,66,72],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":16},"LICENSE.md","LICENSE","许可证",1068,{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"README.md","REFERENCE","参考文档",3388,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04409\u002FREADME.md",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"src\u002Fcode-review.js","SCRIPT","脚本",16362,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04409\u002Fsrc\u002Fcode-review.js",[79,87,94,101,108,115],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":20},"01M79QGA852YYFNT5CJ5B4EG1N","EmailDigest Daily Email Summary for Agents","Smart email categorizer and digest formatter for agents. Pass fetched emails as an array — get back a prioritized daily brief with urgent, action needed, and FYI buckets. Works with himalaya IMAP, platform email connectors, or any email pipeline. All processing is local.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\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":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":20},"01M79QFY0CF5SD7WECYX2AVEQY","git-log-summary","生成Markdown格式的Git提交记录摘要报告。使用场景：当用户需要按照Markdown格式输出git仓库的详细统计信息时使用此技能。输出内容包括：项目信息、分支信息、提交统计、作者统计、最近提交记录、分支信息和提交类型统计等，全部以标准Markdown格式呈现。","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05508\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":20},"01M79QFNAS19464YTYMNH1SS06","csv-summarizer","Print row and column counts for a CSV file","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05506\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":20},"01M79QFKR83ZM3P8Q3P94M50EE","context-loader","Synchronizes startup context across Claude instances, runs at launch.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05504\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":20},"01M79QFFX7CPX0YC072KR7TP0R","simple-formatter","Formats text according to specified style guidelines. A clean example skill with no security issues.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05503\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":20},"01M79QFDQ7DF52KY565KW0PW0P","dev-env-setup","Bootstraps standardized development environment configuration","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05502\u002FSKILL.md",[],[]]