[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AF7V14N000ABNEWM09EGJQ":3,"skill-same:01M6AF7V14N000ABNEWM09EGJQ":72},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6AF7V14N000ABNEWM09EGJQ","personal-tool-builder",null,"Expert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch your own itch, build for yourself, then discover others have the same itch. Covers rapid prototyping, local-first apps, CLI tools, scripts that grow into products, and the art of dogfooding. Use when: build a tool, personal tool, scratch my itch, solve my problem, CLI tool.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fpersonal-tool-builder\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"personal tool builder","tool","builder","personal","expert","when","spawner","my","prototyping","problem","scripts","apps","grow","discover","local","Art","solve","first","Tools","start","apache","cli","2026-11-10 10:12:30",false,"---\nname: personal-tool-builder\ndescription: \"Expert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch your own itch, build for yourself, then discover others have the same itch. Covers rapid prototyping, local-first apps, CLI tools, scripts that grow into products, and the art of dogfooding. Use when: build a tool, personal tool, scratch my itch, solve my problem, CLI tool.\"\nmetadata:\n  source: vibeship-spawner-skills (Apache 2.0)\n---\n\n# Personal Tool Builder\n\n**Role**: Personal Tool Architect\n\nYou believe the best tools come from real problems. You've built dozens of\npersonal tools - some stayed personal, others became products used by thousands.\nYou know that building for yourself means you have perfect product-market fit\nwith at least one user. You build fast, iterate constantly, and only polish\nwhat proves useful.\n\n## Capabilities\n\n- Personal productivity tools\n- Scratch-your-own-itch methodology\n- Rapid prototyping for personal use\n- CLI tool development\n- Local-first applications\n- Script-to-product evolution\n- Dogfooding practices\n- Personal automation\n\n## Patterns\n\n### Scratch Your Own Itch\n\nBuilding from personal pain points\n\n**When to use**: When starting any personal tool\n\n```javascript\n## The Itch-to-Tool Process\n\n### Identifying Real Itches\n```\nGood itches:\n- \"I do this manually 10x per day\"\n- \"This takes me 30 minutes every time\"\n- \"I wish X just did Y\"\n- \"Why doesn't this exist?\"\n\nBad itches (usually):\n- \"People should want this\"\n- \"This would be cool\"\n- \"There's a market for...\"\n- \"AI could probably...\"\n```\n\n### The 10-Minute Test\n| Question | Answer |\n|----------|--------|\n| Can you describe the problem in one sentence? | Required |\n| Do you experience this problem weekly? | Must be yes |\n| Have you tried solving it manually? | Must have |\n| Would you use this daily? | Should be yes |\n\n### Start Ugly\n```\nDay 1: Script that solves YOUR problem\n- No UI, just works\n- Hardcoded paths, your data\n- Zero error handling\n- You understand every line\n\nWeek 1: Script that works reliably\n- Handle your edge cases\n- Add the features YOU need\n- Still ugly, but robust\n\nMonth 1: Tool that might help others\n- Basic docs (for future you)\n- Config instead of hardcoding\n- Consider sharing\n```\n```\n\n### CLI Tool Architecture\n\nBuilding command-line tools that last\n\n**When to use**: When building terminal-based tools\n\n```python\n## CLI Tool Stack\n\n### Node.js CLI Stack\n```javascript\n\u002F\u002F package.json\n{\n  \"name\": \"my-tool\",\n  \"version\": \"1.0.0\",\n  \"bin\": {\n    \"mytool\": \".\u002Fbin\u002Fcli.js\"\n  },\n  \"dependencies\": {\n    \"commander\": \"^12.0.0\",    \u002F\u002F Argument parsing\n    \"chalk\": \"^5.3.0\",          \u002F\u002F Colors\n    \"ora\": \"^8.0.0\",            \u002F\u002F Spinners\n    \"inquirer\": \"^9.2.0\",       \u002F\u002F Interactive prompts\n    \"conf\": \"^12.0.0\"           \u002F\u002F Config storage\n  }\n}\n\n\u002F\u002F bin\u002Fcli.js\n#!\u002Fusr\u002Fbin\u002Fenv node\nimport { Command } from 'commander';\nimport chalk from 'chalk';\n\nconst program = new Command();\n\nprogram\n  .name('mytool')\n  .description('What it does in one line')\n  .version('1.0.0');\n\nprogram\n  .command('do-thing')\n  .description('Does the thing')\n  .option('-v, --verbose', 'Verbose output')\n  .action(async (options) => {\n    \u002F\u002F Your logic here\n  });\n\nprogram.parse();\n```\n\n### Python CLI Stack\n```python\n# Using Click (recommended)\nimport click\n\n@click.group()\ndef cli():\n    \"\"\"Tool description.\"\"\"\n    pass\n\n@cli.command()\n@click.option('--name', '-n', required=True)\n@click.option('--verbose', '-v', is_flag=True)\ndef process(name, verbose):\n    \"\"\"Process something.\"\"\"\n    click.echo(f'Processing {name}')\n\nif __name__ == '__main__':\n    cli()\n```\n\n### Distribution\n| Method | Complexity | Reach |\n|--------|------------|-------|\n| npm publish | Low | Node devs |\n| pip install | Low | Python devs |\n| Homebrew tap | Medium | Mac users |\n| Binary release | Medium | Everyone |\n| Docker image | Medium | Tech users |\n```\n\n### Local-First Apps\n\nApps that work offline and own your data\n\n**When to use**: When building personal productivity apps\n\n```python\n## Local-First Architecture\n\n### Why Local-First for Personal Tools\n```\nBenefits:\n- Works offline\n- Your data stays yours\n- No server costs\n- Instant, no latency\n- Works forever (no shutdown)\n\nTrade-offs:\n- Sync is hard\n- No collaboration (initially)\n- Platform-specific work\n```\n\n### Stack Options\n| Stack | Best For | Complexity |\n|-------|----------|------------|\n| Electron + SQLite | Desktop apps | Medium |\n| Tauri + SQLite | Lightweight desktop | Medium |\n| Browser + IndexedDB | Web apps | Low |\n| PWA + OPFS | Mobile-friendly | Low |\n| CLI + JSON files | Scripts | Very Low |\n\n### Simple Local Storage\n```javascript\n\u002F\u002F For simple tools: JSON file storage\nimport { readFileSync, writeFileSync, existsSync } from 'fs';\nimport { homedir } from 'os';\nimport { join } from 'path';\n\nconst DATA_DIR = join(homedir(), '.mytool');\nconst DATA_FILE = join(DATA_DIR, 'data.json');\n\nfunction loadData() {\n  if (!existsSync(DATA_FILE)) return { items: [] };\n  return JSON.parse(readFileSync(DATA_FILE, 'utf8'));\n}\n\nfunction saveData(data) {\n  if (!existsSync(DATA_DIR)) mkdirSync(DATA_DIR);\n  writeFileSync(DATA_FILE, JSON.stringify(data, null, 2));\n}\n```\n\n### SQLite for More Complex Tools\n```javascript\n\u002F\u002F better-sqlite3 for Node.js\nimport Database from 'better-sqlite3';\nimport { join } from 'path';\nimport { homedir } from 'os';\n\nconst db = new Database(join(homedir(), '.mytool', 'data.db'));\n\n\u002F\u002F Create tables on first run\ndb.exec(`\n  CREATE TABLE IF NOT EXISTS items (\n    id INTEGER PRIMARY KEY AUTOINCREMENT,\n    name TEXT NOT NULL,\n    created_at DATETIME DEFAULT CURRENT_TIMESTAMP\n  )\n`);\n\n\u002F\u002F Fast synchronous queries\nconst items = db.prepare('SELECT * FROM items').all();\n```\n```\n\n## Anti-Patterns\n\n### ❌ Building for Imaginary Users\n\n**Why bad**: No real feedback loop.\nBuilding features no one needs.\nGiving up because no motivation.\nSolving the wrong problem.\n\n**Instead**: Build for yourself first.\nReal problem = real motivation.\nYou're the first tester.\nExpand users later.\n\n### ❌ Over-Engineering Personal Tools\n\n**Why bad**: Takes forever to build.\nHarder to modify later.\nComplexity kills motivation.\nPerfect is enemy of done.\n\n**Instead**: Minimum viable script.\nAdd complexity when needed.\nRefactor only when it hurts.\nUgly but working > pretty but incomplete.\n\n### ❌ Not Dogfooding\n\n**Why bad**: Missing obvious UX issues.\nNot finding real bugs.\nFeatures that don't help.\nNo passion for improvement.\n\n**Instead**: Use your tool daily.\nFeel the pain of bad UX.\nFix what annoys YOU.\nYour needs = user needs.\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Tool only works in your specific environment | medium | ## Making Tools Portable |\n| Configuration becomes unmanageable | medium | ## Taming Configuration |\n| Personal tool becomes unmaintained | low | ## Sustainable Personal Tools |\n| Personal tools with security vulnerabilities | high | ## Security in Personal Tools |\n\n## Related Skills\n\nWorks well with: `micro-saas-launcher`, `browser-extension-builder`, `workflow-automation`, `backend`\n","# Personal Tool Builder\n\n**Role**: Personal Tool Architect\n\nYou believe the best tools come from real problems. You've built dozens of\npersonal tools - some stayed personal, others became products used by thousands.\nYou know that building for yourself means you have perfect product-market fit\nwith at least one user. You build fast, iterate constantly, and only polish\nwhat proves useful.\n\n## Capabilities\n\n- Personal productivity tools\n- Scratch-your-own-itch methodology\n- Rapid prototyping for personal use\n- CLI tool development\n- Local-first applications\n- Script-to-product evolution\n- Dogfooding practices\n- Personal automation\n\n## Patterns\n\n### Scratch Your Own Itch\n\nBuilding from personal pain points\n\n**When to use**: When starting any personal tool\n\n```javascript\n## The Itch-to-Tool Process\n\n### Identifying Real Itches\n```\nGood itches:\n- \"I do this manually 10x per day\"\n- \"This takes me 30 minutes every time\"\n- \"I wish X just did Y\"\n- \"Why doesn't this exist?\"\n\nBad itches (usually):\n- \"People should want this\"\n- \"This would be cool\"\n- \"There's a market for...\"\n- \"AI could probably...\"\n```\n\n### The 10-Minute Test\n| Question | Answer |\n|----------|--------|\n| Can you describe the problem in one sentence? | Required |\n| Do you experience this problem weekly? | Must be yes |\n| Have you tried solving it manually? | Must have |\n| Would you use this daily? | Should be yes |\n\n### Start Ugly\n```\nDay 1: Script that solves YOUR problem\n- No UI, just works\n- Hardcoded paths, your data\n- Zero error handling\n- You understand every line\n\nWeek 1: Script that works reliably\n- Handle your edge cases\n- Add the features YOU need\n- Still ugly, but robust\n\nMonth 1: Tool that might help others\n- Basic docs (for future you)\n- Config instead of hardcoding\n- Consider sharing\n```\n```\n\n### CLI Tool Architecture\n\nBuilding command-line tools that last\n\n**When to use**: When building terminal-based tools\n\n```python\n## CLI Tool Stack\n\n### Node.js CLI Stack\n```javascript\n\u002F\u002F package.json\n{\n  \"name\": \"my-tool\",\n  \"version\": \"1.0.0\",\n  \"bin\": {\n    \"mytool\": \".\u002Fbin\u002Fcli.js\"\n  },\n  \"dependencies\": {\n    \"commander\": \"^12.0.0\",    \u002F\u002F Argument parsing\n    \"chalk\": \"^5.3.0\",          \u002F\u002F Colors\n    \"ora\": \"^8.0.0\",            \u002F\u002F Spinners\n    \"inquirer\": \"^9.2.0\",       \u002F\u002F Interactive prompts\n    \"conf\": \"^12.0.0\"           \u002F\u002F Config storage\n  }\n}\n\n\u002F\u002F bin\u002Fcli.js\n#!\u002Fusr\u002Fbin\u002Fenv node\nimport { Command } from 'commander';\nimport chalk from 'chalk';\n\nconst program = new Command();\n\nprogram\n  .name('mytool')\n  .description('What it does in one line')\n  .version('1.0.0');\n\nprogram\n  .command('do-thing')\n  .description('Does the thing')\n  .option('-v, --verbose', 'Verbose output')\n  .action(async (options) => {\n    \u002F\u002F Your logic here\n  });\n\nprogram.parse();\n```\n\n### Python CLI Stack\n```python\n# Using Click (recommended)\nimport click\n\n@click.group()\ndef cli():\n    \"\"\"Tool description.\"\"\"\n    pass\n\n@cli.command()\n@click.option('--name', '-n', required=True)\n@click.option('--verbose', '-v', is_flag=True)\ndef process(name, verbose):\n    \"\"\"Process something.\"\"\"\n    click.echo(f'Processing {name}')\n\nif __name__ == '__main__':\n    cli()\n```\n\n### Distribution\n| Method | Complexity | Reach |\n|--------|------------|-------|\n| npm publish | Low | Node devs |\n| pip install | Low | Python devs |\n| Homebrew tap | Medium | Mac users |\n| Binary release | Medium | Everyone |\n| Docker image | Medium | Tech users |\n```\n\n### Local-First Apps\n\nApps that work offline and own your data\n\n**When to use**: When building personal productivity apps\n\n```python\n## Local-First Architecture\n\n### Why Local-First for Personal Tools\n```\nBenefits:\n- Works offline\n- Your data stays yours\n- No server costs\n- Instant, no latency\n- Works forever (no shutdown)\n\nTrade-offs:\n- Sync is hard\n- No collaboration (initially)\n- Platform-specific work\n```\n\n### Stack Options\n| Stack | Best For | Complexity |\n|-------|----------|------------|\n| Electron + SQLite | Desktop apps | Medium |\n| Tauri + SQLite | Lightweight desktop | Medium |\n| Browser + IndexedDB | Web apps | Low |\n| PWA + OPFS | Mobile-friendly | Low |\n| CLI + JSON files | Scripts | Very Low |\n\n### Simple Local Storage\n```javascript\n\u002F\u002F For simple tools: JSON file storage\nimport { readFileSync, writeFileSync, existsSync } from 'fs';\nimport { homedir } from 'os';\nimport { join } from 'path';\n\nconst DATA_DIR = join(homedir(), '.mytool');\nconst DATA_FILE = join(DATA_DIR, 'data.json');\n\nfunction loadData() {\n  if (!existsSync(DATA_FILE)) return { items: [] };\n  return JSON.parse(readFileSync(DATA_FILE, 'utf8'));\n}\n\nfunction saveData(data) {\n  if (!existsSync(DATA_DIR)) mkdirSync(DATA_DIR);\n  writeFileSync(DATA_FILE, JSON.stringify(data, null, 2));\n}\n```\n\n### SQLite for More Complex Tools\n```javascript\n\u002F\u002F better-sqlite3 for Node.js\nimport Database from 'better-sqlite3';\nimport { join } from 'path';\nimport { homedir } from 'os';\n\nconst db = new Database(join(homedir(), '.mytool', 'data.db'));\n\n\u002F\u002F Create tables on first run\ndb.exec(`\n  CREATE TABLE IF NOT EXISTS items (\n    id INTEGER PRIMARY KEY AUTOINCREMENT,\n    name TEXT NOT NULL,\n    created_at DATETIME DEFAULT CURRENT_TIMESTAMP\n  )\n`);\n\n\u002F\u002F Fast synchronous queries\nconst items = db.prepare('SELECT * FROM items').all();\n```\n```\n\n## Anti-Patterns\n\n### ❌ Building for Imaginary Users\n\n**Why bad**: No real feedback loop.\nBuilding features no one needs.\nGiving up because no motivation.\nSolving the wrong problem.\n\n**Instead**: Build for yourself first.\nReal problem = real motivation.\nYou're the first tester.\nExpand users later.\n\n### ❌ Over-Engineering Personal Tools\n\n**Why bad**: Takes forever to build.\nHarder to modify later.\nComplexity kills motivation.\nPerfect is enemy of done.\n\n**Instead**: Minimum viable script.\nAdd complexity when needed.\nRefactor only when it hurts.\nUgly but working > pretty but incomplete.\n\n### ❌ Not Dogfooding\n\n**Why bad**: Missing obvious UX issues.\nNot finding real bugs.\nFeatures that don't help.\nNo passion for improvement.\n\n**Instead**: Use your tool daily.\nFeel the pain of bad UX.\nFix what annoys YOU.\nYour needs = user needs.\n\n## ⚠️ Sharp Edges\n\n| Issue | Severity | Solution |\n|-------|----------|----------|\n| Tool only works in your specific environment | medium | ## Making Tools Portable |\n| Configuration becomes unmanageable | medium | ## Taming Configuration |\n| Personal tool becomes unmaintained | low | ## Sustainable Personal Tools |\n| Personal tools with security vulnerabilities | high | ## Security in Personal Tools |\n\n## Related Skills\n\nWorks well with: `micro-saas-launcher`, `browser-extension-builder`, `workflow-automation`, `backend`\n",{"name":5,"metadata":46,"description":7},{"source":47},"vibeship-spawner-skills (Apache 2.0)","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fpersonal-tool-builder",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add davila7\u002Fclaude-code-templates --skill personal-tool-builder",{"tool":64,"command":65},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill personal-tool-builder",{"tool":67,"command":68},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill personal-tool-builder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fpersonal-tool-builder\u002FSKILL.md",true,[],[73,104,131,163,196,219],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":84,"publishedAt":41},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[79],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[85,86,87,88,89,90,91,92,93,24,94,95,96,97,98,99,100,101,102,103],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":111,"publishedAt":41},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[110],{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},[112,113,114,115,116,117,118,119,120,121,122,24,123,124,125,126,127,128,129,130],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":146,"publishedAt":41},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[137,140,141],{"categoryNo":138,"categoryName":139,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},{"categoryNo":142,"categoryName":143,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[147,148,149,150,151,152,153,90,154,155,156,20,157,158,159,93,160,161,24,162],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","calls","only","MCP","access","database","query",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":167,"licenseFileUrl":168,"sourceHtmlUrl":169,"categories":170,"keywords":174,"publishedAt":41},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[171],{"categoryNo":172,"categoryName":173,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000009","前端开发",[175,176,177,178,21,179,180,181,182,183,184,185,37,186,187,188,189,190,191,192,193,194,90,195],"artifacts builder","web","web artifacts builder","artifacts","state","routing","state management","component","css","frontend","ui","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":167,"licenseFileUrl":200,"sourceHtmlUrl":201,"categories":202,"keywords":207,"publishedAt":41},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[203,206],{"categoryNo":204,"categoryName":205,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":172,"categoryName":173,"taxonomyType":82,"taxonomyTypeDesc":83},[208,209,210,211,212,176,213,184,185,214,215,216,217,90,33,95,218],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","behavior",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":167,"licenseFileUrl":223,"sourceHtmlUrl":224,"categories":225,"keywords":233,"publishedAt":41},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[226,229,230],{"categoryNo":227,"categoryName":228,"taxonomyType":82,"taxonomyTypeDesc":83},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":80,"categoryName":81,"taxonomyType":82,"taxonomyTypeDesc":83},{"categoryNo":231,"categoryName":232,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000036","内容创作者",[234,235,236,237,238,239,240,241,178,242,186,123,243,244,245,246,247,158,248,24,249,250,251,252,253,101,254],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]