[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F2EE9VDEW535WP0G3ZTKJB":3,"skill-same:01M7F2EE9VDEW535WP0G3ZTKJB":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7F2EE9VDEW535WP0G3ZTKJB","opc-architecture",null,"OPC Architecture Understanding","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\u002F05-技能与代理开发\u002Fopc-architecture\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: opc-architecture\ndescription: OPC Architecture Understanding\nuser-invocable: false\n---\n\n# OPC Architecture Understanding\n\nOPC (Orchestrated Parallel Claude) extends Claude Code - it does NOT replace it.\n\n## Core Concept\n\nClaude Code CLI is the execution engine. OPC adds orchestration via:\n- **Hooks** - Intercept Claude Code events (PreToolUse, PostToolUse, SessionStart, etc.)\n- **Skills** - Load prompts into Claude Code\n- **Scripts** - Called by hooks\u002Fskills for coordination\n- **Database** - Store state between Claude Code instances\n\n## How Agents Work\n\nWhen you spawn an agent:\n1. Main Claude Code instance (your terminal) runs hook on Task tool\n2. Hook calls `subprocess.Popen([\"claude\", \"-p\", \"prompt\"])`\n3. A NEW Claude Code instance spawns as child process\n4. Child runs independently, reads\u002Fwrites to coordination DB\n5. Parent tracks child via PID in DB\n\n```\n$ claude                         ← Main Claude Code (your terminal)\n    ↓ Task tool triggers hook\n    ↓ subprocess.Popen([\"claude\", \"-p\", \"...\"])\n        ├── claude -p \"research...\"   ← Child agent 1\n        ├── claude -p \"implement...\"  ← Child agent 2\n        └── claude -p \"test...\"       ← Child agent 3\n```\n\n## What OPC Is NOT\n\n- OPC is NOT a separate application\n- OPC does NOT run without Claude Code\n- OPC does NOT intercept Claude API calls directly\n- OPC does NOT modify Claude Code's internal behavior\n\n## What OPC IS\n\n- OPC IS hooks that Claude Code loads from `.claude\u002Fhooks\u002F`\n- OPC IS skills that Claude Code loads from `.claude\u002Fskills\u002F`\n- OPC IS scripts that hooks\u002Fskills call for coordination\n- OPC IS a database backend for state across Claude Code instances\n\n## Key Files\n\n```\n.claude\u002F\n├── hooks\u002F           ← TypeScript hooks that Claude Code runs\n├── skills\u002F          ← SKILL.md prompts that Claude Code loads\n├── settings.json    ← Hook registration, Claude Code reads this\n└── cache\u002F           ← State files, agent outputs\n\nopc\u002F\n├── scripts\u002F         ← Python scripts called by hooks\n├── docker-compose.yml ← PostgreSQL, Redis, PgBouncer\n└── init-db.sql      ← Database schema\n```\n\n## Coordination Flow\n\n1. User runs `claude` in terminal\n2. Claude Code loads hooks from `.claude\u002Fsettings.json`\n3. User says \"spawn a research agent\"\n4. Claude uses Task tool\n5. PreToolUse hook fires, checks resources\n6. Hook spawns `claude -p \"research...\"` as subprocess\n7. Hook stores PID in PostgreSQL\n8. Child agent runs, writes output to `.claude\u002Fcache\u002Fagents\u002F\u003Cid>\u002F`\n9. Child completes, broadcasts \"done\" to PostgreSQL\n10. Parent checks DB, reads child's output file\n\n## Remember\n\n- Every \"agent\" is just another `claude -p` process\n- Hooks intercept events, they don't create new functionality\n- All coordination happens via files and PostgreSQL\n- Claude Code is always the execution engine\n","# OPC Architecture Understanding\n\nOPC (Orchestrated Parallel Claude) extends Claude Code - it does NOT replace it.\n\n## Core Concept\n\nClaude Code CLI is the execution engine. OPC adds orchestration via:\n- **Hooks** - Intercept Claude Code events (PreToolUse, PostToolUse, SessionStart, etc.)\n- **Skills** - Load prompts into Claude Code\n- **Scripts** - Called by hooks\u002Fskills for coordination\n- **Database** - Store state between Claude Code instances\n\n## How Agents Work\n\nWhen you spawn an agent:\n1. Main Claude Code instance (your terminal) runs hook on Task tool\n2. Hook calls `subprocess.Popen([\"claude\", \"-p\", \"prompt\"])`\n3. A NEW Claude Code instance spawns as child process\n4. Child runs independently, reads\u002Fwrites to coordination DB\n5. Parent tracks child via PID in DB\n\n```\n$ claude                         ← Main Claude Code (your terminal)\n    ↓ Task tool triggers hook\n    ↓ subprocess.Popen([\"claude\", \"-p\", \"...\"])\n        ├── claude -p \"research...\"   ← Child agent 1\n        ├── claude -p \"implement...\"  ← Child agent 2\n        └── claude -p \"test...\"       ← Child agent 3\n```\n\n## What OPC Is NOT\n\n- OPC is NOT a separate application\n- OPC does NOT run without Claude Code\n- OPC does NOT intercept Claude API calls directly\n- OPC does NOT modify Claude Code's internal behavior\n\n## What OPC IS\n\n- OPC IS hooks that Claude Code loads from `.claude\u002Fhooks\u002F`\n- OPC IS skills that Claude Code loads from `.claude\u002Fskills\u002F`\n- OPC IS scripts that hooks\u002Fskills call for coordination\n- OPC IS a database backend for state across Claude Code instances\n\n## Key Files\n\n```\n.claude\u002F\n├── hooks\u002F           ← TypeScript hooks that Claude Code runs\n├── skills\u002F          ← SKILL.md prompts that Claude Code loads\n├── settings.json    ← Hook registration, Claude Code reads this\n└── cache\u002F           ← State files, agent outputs\n\nopc\u002F\n├── scripts\u002F         ← Python scripts called by hooks\n├── docker-compose.yml ← PostgreSQL, Redis, PgBouncer\n└── init-db.sql      ← Database schema\n```\n\n## Coordination Flow\n\n1. User runs `claude` in terminal\n2. Claude Code loads hooks from `.claude\u002Fsettings.json`\n3. User says \"spawn a research agent\"\n4. Claude uses Task tool\n5. PreToolUse hook fires, checks resources\n6. Hook spawns `claude -p \"research...\"` as subprocess\n7. Hook stores PID in PostgreSQL\n8. Child agent runs, writes output to `.claude\u002Fcache\u002Fagents\u002F\u003Cid>\u002F`\n9. Child completes, broadcasts \"done\" to PostgreSQL\n10. Parent checks DB, reads child's output file\n\n## Remember\n\n- Every \"agent\" is just another `claude -p` process\n- Hooks intercept events, they don't create new functionality\n- All coordination happens via files and PostgreSQL\n- Claude Code is always the execution engine\n",{"name":5,"description":7,"user-invocable":20},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fopc-architecture",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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill opc-architecture",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill opc-architecture",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill opc-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fopc-architecture\u002FSKILL.md",true,[],[47,54,59,66,73,80],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"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",[],[],{"skillNo":55,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"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":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":79,"publishedAt":19},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"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",[],[]]