[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EV2Z3R6X5GSXG6Q55MQGS0":3,"skill-same:01M7EV2Z3R6X5GSXG6Q55MQGS0":101},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M7EV2Z3R6X5GSXG6Q55MQGS0","vc-debug",null,"Debug systematically with root-cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, CI failures, or system investigation.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vc-debug\ndescription: \"Debug systematically with root-cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, CI failures, or system investigation.\"\nlanguages: all\nargument-hint: \"[error or issue description]\"\ntrigger_keywords: debug, root cause, investigate, why is this\nlayer: helper\nmetadata:\n  author: claudekit\n  version: \"4.0.0\"\n---\n\n# Debugging & System Investigation\n\n> **Output style:** Follow `process\u002Fdevelopment-protocols\u002Fcommunication-standards.md` — answer-first, plain language, no unexplained jargon, TL;DR on long responses.\n\nComprehensive framework combining systematic debugging, root cause tracing, defense-in-depth validation, verification protocols, and system-level investigation (logs, CI\u002FCD, databases, performance).\n\n## Core Principle\n\n**NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST**\n\nRandom fixes waste time and create new bugs. Find root cause, fix at source, validate at every layer, verify before claiming success.\n\n## When to Use\n\n**Code-level:** Test failures, bugs, unexpected behavior, build failures, integration problems\n**System-level:** Server errors, CI\u002FCD pipeline failures, performance degradation, database issues, log analysis\n**Always:** Before claiming work complete\n\n## Techniques\n\n### 1. Systematic Debugging (`references\u002Fsystematic-debugging.md`)\n\nFour-phase framework: Root Cause Investigation → Pattern Analysis → Hypothesis Testing → Implementation. Complete each phase before proceeding. No fixes without Phase 1.\n\n**Load when:** Any bug\u002Fissue requiring investigation and fix\n\n### 2. Root Cause Tracing (`references\u002Froot-cause-tracing.md`)\n\nTrace bugs backward through call stack to find original trigger. Fix at source, not symptom. Includes `scripts\u002Ffind-polluter.sh` for bisecting test pollution.\n\n**Load when:** Error deep in call stack, unclear where invalid data originated\n\n### 3. Defense-in-Depth (`references\u002Fdefense-in-depth.md`)\n\nValidate at every layer: Entry validation → Business logic → Environment guards → Debug instrumentation\n\n**Load when:** After finding root cause, need comprehensive validation\n\n### 4. Verification (`references\u002Fverification.md`)\n\n**Iron law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. Run command. Read output. Then claim result.\n\n**Load when:** About to claim work complete, fixed, or passing\n\n### 5. Investigation Methodology (`references\u002Finvestigation-methodology.md`)\n\nFive-step structured investigation for system-level issues: Initial Assessment → Data Collection → Analysis → Root Cause ID → Solution Development\n\n**Load when:** Server incidents, system behavior analysis, multi-component failures\n\n### 6. Log & CI\u002FCD Analysis (`references\u002Flog-and-ci-analysis.md`)\n\nCollect and analyze logs from servers, CI\u002FCD pipelines (GitHub Actions), application layers. Tools: `gh` CLI, structured log queries, correlation across sources.\n\n**Load when:** CI\u002FCD pipeline failures, server errors, deployment issues\n\n### 7. Performance Diagnostics (`references\u002Fperformance-diagnostics.md`)\n\nIdentify bottlenecks, analyze query performance, develop optimization strategies. Covers database queries, API response times, resource utilization.\n\n**Load when:** Performance degradation, slow queries, high latency, resource exhaustion\n\n### 8. Reporting Standards (`references\u002Freporting-standards.md`)\n\nStructured diagnostic reports: Executive Summary → Technical Analysis → Recommendations → Evidence\n\n**Load when:** Need to produce investigation report or diagnostic summary\n\n### 9. Task Management (`references\u002Ftask-management-debugging.md`)\n\nTrack investigation pipelines via Claude Native Tasks (TaskCreate, TaskUpdate, TaskList). Hydration pattern for multi-step investigations with dependency chains and parallel evidence collection. **Fallback:** Task tools are CLI-only — if unavailable (VSCode extension), use `TodoWrite` for tracking. Debug workflow remains fully functional.\n\n**Load when:** Multi-component investigation (3+ steps), parallel log collection, coordinating debugger subagents\n\n### 10. Frontend Verification (`references\u002Ffrontend-verification.md`)\n\nVisual verification of frontend implementations via Chrome MCP (Claude Chrome Extension) or `vc-agent-browser` skill fallback. Detect if frontend-related → check Chrome MCP availability → screenshot + console error check → report. Skip if not frontend.\n\n**Load when:** Implementation touches frontend files (tsx\u002Fjsx\u002Fvue\u002Fsvelte\u002Fhtml\u002Fcss), UI bugs, visual regressions\n\n## Quick Reference\n\n```\nCode bug       → systematic-debugging.md (Phase 1-4)\n  Deep in stack  → root-cause-tracing.md (trace backward)\n  Found cause    → defense-in-depth.md (add layers)\n  Claiming done  → verification.md (verify first)\n\nSystem issue   → investigation-methodology.md (5 steps)\n  CI\u002FCD failure  → log-and-ci-analysis.md\n  Slow system    → performance-diagnostics.md\n  Need report    → reporting-standards.md\n\nFrontend fix   → frontend-verification.md (Chrome\u002Fdevtools)\n```\n\n## Tools Integration\n\n- **Database:** `sqlite3` CLI and `drizzle-kit studio` for SQLite\u002FlibSQL diagnostics\n- **CI\u002FCD:** `gh` CLI for GitHub Actions logs and pipeline debugging\n- **Codebase:** `vc-docs-seeker` skill for package\u002Fplugin docs; `vc-scout` skill for codebase exploration\n- **Scouting:** `\u002Fvc-scout` or `\u002Fvc-scout ext` for finding relevant files\n- **Frontend:** Chrome browser or `vc-agent-browser` skill for visual verification (screenshots, console, network)\n- **Skills:** Activate `vc-problem-solving` skill when stuck on complex issues\n\n## Red Flags\n\nStop and follow process if thinking:\n- \"Quick fix for now, investigate later\"\n- \"Just try changing X and see if it works\"\n- \"It's probably X, let me fix that\"\n- \"Should work now\" \u002F \"Seems fixed\"\n- \"Tests pass, we're done\"\n\n**All mean:** Return to systematic process.\n","# Debugging & System Investigation\n\n> **Output style:** Follow `process\u002Fdevelopment-protocols\u002Fcommunication-standards.md` — answer-first, plain language, no unexplained jargon, TL;DR on long responses.\n\nComprehensive framework combining systematic debugging, root cause tracing, defense-in-depth validation, verification protocols, and system-level investigation (logs, CI\u002FCD, databases, performance).\n\n## Core Principle\n\n**NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST**\n\nRandom fixes waste time and create new bugs. Find root cause, fix at source, validate at every layer, verify before claiming success.\n\n## When to Use\n\n**Code-level:** Test failures, bugs, unexpected behavior, build failures, integration problems\n**System-level:** Server errors, CI\u002FCD pipeline failures, performance degradation, database issues, log analysis\n**Always:** Before claiming work complete\n\n## Techniques\n\n### 1. Systematic Debugging (`references\u002Fsystematic-debugging.md`)\n\nFour-phase framework: Root Cause Investigation → Pattern Analysis → Hypothesis Testing → Implementation. Complete each phase before proceeding. No fixes without Phase 1.\n\n**Load when:** Any bug\u002Fissue requiring investigation and fix\n\n### 2. Root Cause Tracing (`references\u002Froot-cause-tracing.md`)\n\nTrace bugs backward through call stack to find original trigger. Fix at source, not symptom. Includes `scripts\u002Ffind-polluter.sh` for bisecting test pollution.\n\n**Load when:** Error deep in call stack, unclear where invalid data originated\n\n### 3. Defense-in-Depth (`references\u002Fdefense-in-depth.md`)\n\nValidate at every layer: Entry validation → Business logic → Environment guards → Debug instrumentation\n\n**Load when:** After finding root cause, need comprehensive validation\n\n### 4. Verification (`references\u002Fverification.md`)\n\n**Iron law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE. Run command. Read output. Then claim result.\n\n**Load when:** About to claim work complete, fixed, or passing\n\n### 5. Investigation Methodology (`references\u002Finvestigation-methodology.md`)\n\nFive-step structured investigation for system-level issues: Initial Assessment → Data Collection → Analysis → Root Cause ID → Solution Development\n\n**Load when:** Server incidents, system behavior analysis, multi-component failures\n\n### 6. Log & CI\u002FCD Analysis (`references\u002Flog-and-ci-analysis.md`)\n\nCollect and analyze logs from servers, CI\u002FCD pipelines (GitHub Actions), application layers. Tools: `gh` CLI, structured log queries, correlation across sources.\n\n**Load when:** CI\u002FCD pipeline failures, server errors, deployment issues\n\n### 7. Performance Diagnostics (`references\u002Fperformance-diagnostics.md`)\n\nIdentify bottlenecks, analyze query performance, develop optimization strategies. Covers database queries, API response times, resource utilization.\n\n**Load when:** Performance degradation, slow queries, high latency, resource exhaustion\n\n### 8. Reporting Standards (`references\u002Freporting-standards.md`)\n\nStructured diagnostic reports: Executive Summary → Technical Analysis → Recommendations → Evidence\n\n**Load when:** Need to produce investigation report or diagnostic summary\n\n### 9. Task Management (`references\u002Ftask-management-debugging.md`)\n\nTrack investigation pipelines via Claude Native Tasks (TaskCreate, TaskUpdate, TaskList). Hydration pattern for multi-step investigations with dependency chains and parallel evidence collection. **Fallback:** Task tools are CLI-only — if unavailable (VSCode extension), use `TodoWrite` for tracking. Debug workflow remains fully functional.\n\n**Load when:** Multi-component investigation (3+ steps), parallel log collection, coordinating debugger subagents\n\n### 10. Frontend Verification (`references\u002Ffrontend-verification.md`)\n\nVisual verification of frontend implementations via Chrome MCP (Claude Chrome Extension) or `vc-agent-browser` skill fallback. Detect if frontend-related → check Chrome MCP availability → screenshot + console error check → report. Skip if not frontend.\n\n**Load when:** Implementation touches frontend files (tsx\u002Fjsx\u002Fvue\u002Fsvelte\u002Fhtml\u002Fcss), UI bugs, visual regressions\n\n## Quick Reference\n\n```\nCode bug       → systematic-debugging.md (Phase 1-4)\n  Deep in stack  → root-cause-tracing.md (trace backward)\n  Found cause    → defense-in-depth.md (add layers)\n  Claiming done  → verification.md (verify first)\n\nSystem issue   → investigation-methodology.md (5 steps)\n  CI\u002FCD failure  → log-and-ci-analysis.md\n  Slow system    → performance-diagnostics.md\n  Need report    → reporting-standards.md\n\nFrontend fix   → frontend-verification.md (Chrome\u002Fdevtools)\n```\n\n## Tools Integration\n\n- **Database:** `sqlite3` CLI and `drizzle-kit studio` for SQLite\u002FlibSQL diagnostics\n- **CI\u002FCD:** `gh` CLI for GitHub Actions logs and pipeline debugging\n- **Codebase:** `vc-docs-seeker` skill for package\u002Fplugin docs; `vc-scout` skill for codebase exploration\n- **Scouting:** `\u002Fvc-scout` or `\u002Fvc-scout ext` for finding relevant files\n- **Frontend:** Chrome browser or `vc-agent-browser` skill for visual verification (screenshots, console, network)\n- **Skills:** Activate `vc-problem-solving` skill when stuck on complex issues\n\n## Red Flags\n\nStop and follow process if thinking:\n- \"Quick fix for now, investigate later\"\n- \"Just try changing X and see if it works\"\n- \"It's probably X, let me fix that\"\n- \"Should work now\" \u002F \"Seems fixed\"\n- \"Tests pass, we're done\"\n\n**All mean:** Return to systematic process.\n",{"name":5,"layer":24,"metadata":25,"languages":28,"description":7,"argument-hint":29,"trigger_keywords":30},"helper",{"author":26,"version":27},"claudekit","4.0.0","all","[error or issue description]","debug, root cause, investigate, why is this","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fvc-debug",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill vc-debug",{"tool":45,"command":46},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill vc-debug",{"tool":48,"command":49},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill vc-debug","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002FSKILL.md",true,[53,59,63,67,71,75,79,83,87,91,95],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fdefense-in-depth.md","REFERENCE","参考文档",3662,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Fdefense-in-depth.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Ffrontend-verification.md",3724,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Ffrontend-verification.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Finvestigation-methodology.md",4083,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Finvestigation-methodology.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Flog-and-ci-analysis.md",3460,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Flog-and-ci-analysis.md",{"path":72,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fperformance-diagnostics.md",3861,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Fperformance-diagnostics.md",{"path":76,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Freporting-standards.md",3003,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Freporting-standards.md",{"path":80,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Froot-cause-tracing.md",3352,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Froot-cause-tracing.md",{"path":84,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fsystematic-debugging.md",4158,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Fsystematic-debugging.md",{"path":88,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Ftask-management-debugging.md",5742,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Ftask-management-debugging.md",{"path":92,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fverification.md",3399,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Freferences\u002Fverification.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Ffind-polluter.test.md","SCRIPT","脚本",2117,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fvc-debug\u002Fscripts\u002Ffind-polluter.test.md",[102,110,115,122,129,136],{"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":109},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":111,"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":112,"categories":113,"keywords":114,"publishedAt":109},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\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":109},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":109},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":109},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":109},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]