[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AE6DG0D5ZYDN9TYPE7CZPY":3,"skill-same:01M6AE6DG0D5ZYDN9TYPE7CZPY":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":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6AE6DG0D5ZYDN9TYPE7CZPY","excalidraw",null,"Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams\u002Fflowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33332,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Fexcalidraw\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"diagrams","when","limits","single","delegates","can","requests","with","tokens","files","architecture","use","subagents","operations","user","context","read","json","visualization","2026-11-10 10:12:30",false,"---\nname: excalidraw\ndescription: \"Use when working with *.excalidraw or *.excalidraw.json files, user mentions diagrams\u002Fflowcharts, or requests architecture visualization - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)\"\n---\n\n# Excalidraw Subagent Delegation\n\n## Overview\n\n**Core principle:** Main agents NEVER read Excalidraw files directly. Always delegate to subagents to isolate context consumption.\n\nExcalidraw files are JSON with high token cost but low information density. Single files range from 4k-22k tokens (largest can exceed read tool limits). Reading multiple diagrams quickly exhausts context budget (7 files = 67k tokens = 33% of budget).\n\n## The Problem\n\nExcalidraw JSON structure:\n- Each shape has 20+ properties (x, y, width, height, strokeColor, seed, version, etc.)\n- Most properties are visual metadata (positioning, styling, roughness)\n- Actual content: text labels and element relationships (\u003C10% of file)\n- **Signal-to-noise ratio is extremely low**\n\nExample: 14-element diagram = 596 lines, 16K, ~4k tokens. 79-element diagram = 2,916 lines, 88K, ~22k tokens (exceeds read limit).\n\n## When to Use\n\n**Trigger on ANY of these:**\n- File path contains `.excalidraw` or `.excalidraw.json`\n- User requests: \"explain\u002Fupdate\u002Fcreate diagram\", \"show architecture\", \"visualize flow\"\n- User mentions: \"flowchart\", \"architecture diagram\", \"Excalidraw file\"\n- Architecture\u002Fdesign documentation tasks involving visual artifacts\n\n**Use delegation even for:**\n- \"Small\" files (smallest is 4k tokens - still significant)\n- \"Quick checks\" (checking component names still loads full JSON)\n- Single file operations (isolation prevents context pollution)\n- Modifications (don't need full format understanding in main context)\n\n## Delegation Pattern\n\n### Main Agent Responsibilities\n\n**NEVER:**\n- ❌ Use Read tool on *.excalidraw files\n- ❌ Parse Excalidraw JSON in main context\n- ❌ Load multiple diagrams for comparison\n- ❌ Inspect file to \"understand the format\"\n\n**ALWAYS:**\n- ✅ Delegate ALL Excalidraw operations to subagents\n- ✅ Provide clear task description to subagent\n- ✅ Request text-only summaries (not raw JSON)\n- ✅ Keep diagram analysis isolated from main work\n\n### Subagent Task Templates\n\n#### Read\u002FUnderstand Operation\n```\nTask: Extract and explain the components in [file.excalidraw.json]\n\nApproach:\n1. Read the Excalidraw JSON\n2. Extract only text elements (ignore positioning\u002Fstyling)\n3. Identify relationships between components\n4. Summarize architecture\u002Fflow\n\nReturn:\n- List of components\u002Fservices with descriptions\n- Connection\u002Fdependency relationships\n- Key insights about the architecture\n- DO NOT return raw JSON or verbose element details\n```\n\n#### Modify Operation\n```\nTask: Add [component] to [file.excalidraw.json], connected to [existing-component]\n\nApproach:\n1. Read file to identify existing elements\n2. Find [existing-component] and its position\n3. Create new element JSON for [component]\n4. Add arrow elements for connections\n5. Write updated file\n\nReturn:\n- Confirmation of changes made\n- Position of new element\n- IDs of created elements\n```\n\n#### Create Operation\n```\nTask: Create new Excalidraw diagram showing [description]\n\nApproach:\n1. Design layout for [number] components\n2. Create rectangle elements with text labels\n3. Add arrows showing relationships\n4. Use consistent styling (colors, fonts)\n5. Write to [file.excalidraw.json]\n\nReturn:\n- Confirmation of file created\n- Summary of components included\n- File location\n```\n\n#### Compare Operation\n```\nTask: Compare architecture approaches in [file1] vs [file2]\n\nApproach:\n1. Read both files\n2. Extract text labels from each\n3. Identify structural differences\n4. Compare component relationships\n\nReturn:\n- Key differences in architecture\n- Components unique to each approach\n- Relationship\u002Fflow differences\n- DO NOT return full element details from both files\n```\n\n## Common Rationalizations (STOP and Delegate Instead)\n\n| Excuse | Reality | What to Do |\n|--------|---------|------------|\n| \"Direct reading is most efficient\" | Consumes 4k-22k tokens unnecessarily | Delegate to subagent |\n| \"It's token-efficient to read directly\" | Baseline tests showed 9-45% budget used | Always delegate |\n| \"This is optimal for one-time analysis\" | \"One-time\" still pollutes main context | Subagent isolation |\n| \"The JSON is straightforward\" | Simplicity ≠ token efficiency | Delegate anyway |\n| \"I need to understand the format\" | Format understanding not needed in main agent | Subagent handles format |\n| \"Within reasonable bounds\" (18k tokens) | \"Reasonable\" is subjective rationalization | Hard rule: delegate |\n| \"Just a quick check of components\" | \"Quick check\" still loads full JSON | Extract text via subagent |\n| \"File is small (16K)\" | 4k tokens is NOT small | Size threshold doesn't matter |\n\n## Red Flags - STOP and Delegate\n\nCatch yourself about to:\n- Use Read tool on .excalidraw file\n- \"Quickly check\" what components exist\n- \"Understand the structure\" before modifying\n- Load file to \"see what's there\"\n- Compare multiple diagrams side-by-side\n- Parse JSON to \"extract just the text\"\n\n**All of these mean: Use Task tool with subagent instead.**\n\n## Quick Reference\n\n| Operation | Main Agent Action | Subagent Returns |\n|-----------|-------------------|------------------|\n| **Understand diagram** | Delegate with \"Extract and explain\" template | Component list + relationships |\n| **Modify diagram** | Delegate with \"Add [X] connected to [Y]\" template | Confirmation + changes made |\n| **Create diagram** | Delegate with \"Create showing [description]\" template | File location + summary |\n| **Compare diagrams** | Delegate with \"Compare [A] vs [B]\" template | Key differences (not raw JSON) |\n\n## Token Analysis (Why This Matters)\n\nReal data from baseline testing:\n\n| Scenario | Without Delegation | With Delegation | Savings |\n|----------|-------------------|-----------------|---------|\n| Single large file | 22k tokens (45% budget) | ~500 tokens (subagent summary) | 98% |\n| Two-file comparison | 18k tokens (9% budget) | ~800 tokens (diff summary) | 96% |\n| Modification task | 14k tokens (7% budget) | ~300 tokens (confirmation) | 98% |\n\n**Context pollution impact:**\n- Reading all 7 project diagrams: 67k tokens (33% of 200k budget)\n- With delegation: ~2k tokens (isolated in subagents)\n- **Savings: 97% context budget preserved**\n\n## Implementation Example\n\n**❌ BAD (Direct Read):**\n```\nUser: \"What architecture is shown in detailed-architecture.excalidraw.json?\"\nAgent: Let me read that file... [reads 22k tokens into main context]\n```\n\n**✅ GOOD (Subagent Delegation):**\n```\nUser: \"What architecture is shown in detailed-architecture.excalidraw.json?\"\nAgent: I'll use a subagent to extract the architecture details.\n\n[Dispatches Task tool with general-purpose subagent]\nTask: Extract and explain components in .ryanquinn3\u002Fticketing\u002Fdetailed-architecture.excalidraw.json\n\n[Receives ~500 token summary with component list and relationships]\n[Responds to user with architecture explanation, main context preserved]\n```\n\n## Why \"Straightforward JSON\" Doesn't Matter\n\nAgents often rationalize: \"The format is simple, I can just read it.\"\n\n**The problem isn't complexity - it's verbosity:**\n- Simple structure with 20+ properties per element\n- Repetitive metadata (seed, version, nonce, roughness)\n- Positioning data (x, y, width, height) not semantically useful\n- Visual styling (strokeColor, opacity, fillStyle) irrelevant to content\n\n**Token cost comes from volume, not complexity.**\n\nEven \"straightforward\" JSON consumes 4k-22k tokens because:\n- 79 elements × ~280 tokens\u002Felement = 22k tokens\n- Most tokens are metadata noise\n- Only text labels and relationships matter (~10% of content)\n\n## The Iron Law\n\n**Main agents NEVER read Excalidraw files. No exceptions.**\n\nNot for:\n- \"Quick checks\"\n- \"Small files\"\n- \"Understanding format\"\n- \"One-time analysis\"\n- \"Optimal efficiency\"\n\n**Always delegate. Isolation is free via subagents.**\n","# Excalidraw Subagent Delegation\n\n## Overview\n\n**Core principle:** Main agents NEVER read Excalidraw files directly. Always delegate to subagents to isolate context consumption.\n\nExcalidraw files are JSON with high token cost but low information density. Single files range from 4k-22k tokens (largest can exceed read tool limits). Reading multiple diagrams quickly exhausts context budget (7 files = 67k tokens = 33% of budget).\n\n## The Problem\n\nExcalidraw JSON structure:\n- Each shape has 20+ properties (x, y, width, height, strokeColor, seed, version, etc.)\n- Most properties are visual metadata (positioning, styling, roughness)\n- Actual content: text labels and element relationships (\u003C10% of file)\n- **Signal-to-noise ratio is extremely low**\n\nExample: 14-element diagram = 596 lines, 16K, ~4k tokens. 79-element diagram = 2,916 lines, 88K, ~22k tokens (exceeds read limit).\n\n## When to Use\n\n**Trigger on ANY of these:**\n- File path contains `.excalidraw` or `.excalidraw.json`\n- User requests: \"explain\u002Fupdate\u002Fcreate diagram\", \"show architecture\", \"visualize flow\"\n- User mentions: \"flowchart\", \"architecture diagram\", \"Excalidraw file\"\n- Architecture\u002Fdesign documentation tasks involving visual artifacts\n\n**Use delegation even for:**\n- \"Small\" files (smallest is 4k tokens - still significant)\n- \"Quick checks\" (checking component names still loads full JSON)\n- Single file operations (isolation prevents context pollution)\n- Modifications (don't need full format understanding in main context)\n\n## Delegation Pattern\n\n### Main Agent Responsibilities\n\n**NEVER:**\n- ❌ Use Read tool on *.excalidraw files\n- ❌ Parse Excalidraw JSON in main context\n- ❌ Load multiple diagrams for comparison\n- ❌ Inspect file to \"understand the format\"\n\n**ALWAYS:**\n- ✅ Delegate ALL Excalidraw operations to subagents\n- ✅ Provide clear task description to subagent\n- ✅ Request text-only summaries (not raw JSON)\n- ✅ Keep diagram analysis isolated from main work\n\n### Subagent Task Templates\n\n#### Read\u002FUnderstand Operation\n```\nTask: Extract and explain the components in [file.excalidraw.json]\n\nApproach:\n1. Read the Excalidraw JSON\n2. Extract only text elements (ignore positioning\u002Fstyling)\n3. Identify relationships between components\n4. Summarize architecture\u002Fflow\n\nReturn:\n- List of components\u002Fservices with descriptions\n- Connection\u002Fdependency relationships\n- Key insights about the architecture\n- DO NOT return raw JSON or verbose element details\n```\n\n#### Modify Operation\n```\nTask: Add [component] to [file.excalidraw.json], connected to [existing-component]\n\nApproach:\n1. Read file to identify existing elements\n2. Find [existing-component] and its position\n3. Create new element JSON for [component]\n4. Add arrow elements for connections\n5. Write updated file\n\nReturn:\n- Confirmation of changes made\n- Position of new element\n- IDs of created elements\n```\n\n#### Create Operation\n```\nTask: Create new Excalidraw diagram showing [description]\n\nApproach:\n1. Design layout for [number] components\n2. Create rectangle elements with text labels\n3. Add arrows showing relationships\n4. Use consistent styling (colors, fonts)\n5. Write to [file.excalidraw.json]\n\nReturn:\n- Confirmation of file created\n- Summary of components included\n- File location\n```\n\n#### Compare Operation\n```\nTask: Compare architecture approaches in [file1] vs [file2]\n\nApproach:\n1. Read both files\n2. Extract text labels from each\n3. Identify structural differences\n4. Compare component relationships\n\nReturn:\n- Key differences in architecture\n- Components unique to each approach\n- Relationship\u002Fflow differences\n- DO NOT return full element details from both files\n```\n\n## Common Rationalizations (STOP and Delegate Instead)\n\n| Excuse | Reality | What to Do |\n|--------|---------|------------|\n| \"Direct reading is most efficient\" | Consumes 4k-22k tokens unnecessarily | Delegate to subagent |\n| \"It's token-efficient to read directly\" | Baseline tests showed 9-45% budget used | Always delegate |\n| \"This is optimal for one-time analysis\" | \"One-time\" still pollutes main context | Subagent isolation |\n| \"The JSON is straightforward\" | Simplicity ≠ token efficiency | Delegate anyway |\n| \"I need to understand the format\" | Format understanding not needed in main agent | Subagent handles format |\n| \"Within reasonable bounds\" (18k tokens) | \"Reasonable\" is subjective rationalization | Hard rule: delegate |\n| \"Just a quick check of components\" | \"Quick check\" still loads full JSON | Extract text via subagent |\n| \"File is small (16K)\" | 4k tokens is NOT small | Size threshold doesn't matter |\n\n## Red Flags - STOP and Delegate\n\nCatch yourself about to:\n- Use Read tool on .excalidraw file\n- \"Quickly check\" what components exist\n- \"Understand the structure\" before modifying\n- Load file to \"see what's there\"\n- Compare multiple diagrams side-by-side\n- Parse JSON to \"extract just the text\"\n\n**All of these mean: Use Task tool with subagent instead.**\n\n## Quick Reference\n\n| Operation | Main Agent Action | Subagent Returns |\n|-----------|-------------------|------------------|\n| **Understand diagram** | Delegate with \"Extract and explain\" template | Component list + relationships |\n| **Modify diagram** | Delegate with \"Add [X] connected to [Y]\" template | Confirmation + changes made |\n| **Create diagram** | Delegate with \"Create showing [description]\" template | File location + summary |\n| **Compare diagrams** | Delegate with \"Compare [A] vs [B]\" template | Key differences (not raw JSON) |\n\n## Token Analysis (Why This Matters)\n\nReal data from baseline testing:\n\n| Scenario | Without Delegation | With Delegation | Savings |\n|----------|-------------------|-----------------|---------|\n| Single large file | 22k tokens (45% budget) | ~500 tokens (subagent summary) | 98% |\n| Two-file comparison | 18k tokens (9% budget) | ~800 tokens (diff summary) | 96% |\n| Modification task | 14k tokens (7% budget) | ~300 tokens (confirmation) | 98% |\n\n**Context pollution impact:**\n- Reading all 7 project diagrams: 67k tokens (33% of 200k budget)\n- With delegation: ~2k tokens (isolated in subagents)\n- **Savings: 97% context budget preserved**\n\n## Implementation Example\n\n**❌ BAD (Direct Read):**\n```\nUser: \"What architecture is shown in detailed-architecture.excalidraw.json?\"\nAgent: Let me read that file... [reads 22k tokens into main context]\n```\n\n**✅ GOOD (Subagent Delegation):**\n```\nUser: \"What architecture is shown in detailed-architecture.excalidraw.json?\"\nAgent: I'll use a subagent to extract the architecture details.\n\n[Dispatches Task tool with general-purpose subagent]\nTask: Extract and explain components in .ryanquinn3\u002Fticketing\u002Fdetailed-architecture.excalidraw.json\n\n[Receives ~500 token summary with component list and relationships]\n[Responds to user with architecture explanation, main context preserved]\n```\n\n## Why \"Straightforward JSON\" Doesn't Matter\n\nAgents often rationalize: \"The format is simple, I can just read it.\"\n\n**The problem isn't complexity - it's verbosity:**\n- Simple structure with 20+ properties per element\n- Repetitive metadata (seed, version, nonce, roughness)\n- Positioning data (x, y, width, height) not semantically useful\n- Visual styling (strokeColor, opacity, fillStyle) irrelevant to content\n\n**Token cost comes from volume, not complexity.**\n\nEven \"straightforward\" JSON consumes 4k-22k tokens because:\n- 79 elements × ~280 tokens\u002Felement = 22k tokens\n- Most tokens are metadata noise\n- Only text labels and relationships matter (~10% of content)\n\n## The Iron Law\n\n**Main agents NEVER read Excalidraw files. No exceptions.**\n\nNot for:\n- \"Quick checks\"\n- \"Small files\"\n- \"Understanding format\"\n- \"One-time analysis\"\n- \"Optimal efficiency\"\n\n**Always delegate. Isolation is free via subagents.**\n",{"name":5,"description":7},"main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Fexcalidraw",3911,"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","2026-11-11 21:38:31",{"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 excalidraw",{"tool":64,"command":65},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill excalidraw",{"tool":67,"command":68},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill excalidraw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Fexcalidraw\u002FSKILL.md",true,[72],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"README.md","REFERENCE","参考文档",10326,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Fexcalidraw\u002FREADME.md",[79,104,131,164,199,223],{"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":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":43},"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",[85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[87,88,89,90,91,92,93,94,35,25,95,31,96,97,98,99,100,101,102,103],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","reduce","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":43},"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":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[112,113,114,115,116,117,118,119,120,121,122,25,123,124,125,126,127,128,129,130],"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":43},"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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":142,"categoryName":143,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[147,148,149,150,151,152,153,92,154,155,156,157,158,159,160,35,161,162,25,163],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":169,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":43},"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",[172],{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,92,198],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":203,"sourceHtmlUrl":204,"categories":205,"keywords":210,"publishedAt":43},"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",[206,209],{"categoryNo":207,"categoryName":208,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":173,"categoryName":174,"taxonomyType":21,"taxonomyTypeDesc":22},[211,212,213,214,215,177,216,186,187,217,218,219,220,92,221,31,222],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":168,"licenseFileUrl":227,"sourceHtmlUrl":228,"categories":229,"keywords":237,"publishedAt":43},"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",[230,233,234],{"categoryNo":231,"categoryName":232,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":235,"categoryName":236,"taxonomyType":144,"taxonomyTypeDesc":145},"01JBSEEDCAT000000000000036","内容创作者",[238,239,240,241,242,243,244,245,179,246,189,123,247,248,249,250,251,159,252,25,253,254,255,256,257,101,258],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]