[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78FD9BKF8RF9KBXHZ9DHAX6":3,"skill-same:01M78FD9BKF8RF9KBXHZ9DHAX6":86},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M78FD9BKF8RF9KBXHZ9DHAX6","subagent-orchestrator",null,"Coordinate quota-aware parallel subagents for large, multi-file Antigravity tasks.","princepatel04477-web\u002Ftrivoxa-group","princepatel04477-web","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227740714?v=4","01M788ZAJ2KECD5KXVP55PZXKS","Prince Patel","01M788ZAJTCN8YSD737MRSKC5Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: subagent-orchestrator\nrisk: safe\nsource: community\ndescription: Coordinate quota-aware parallel subagents for large, multi-file Antigravity tasks.\nversion: 1.0.0\nauthor: community\ntags: [subagents, orchestration, quota, parallel, multi-agent]\n---\n\n# Subagent Orchestrator\n\nA quota-aware, parallel subagent coordination skill for Antigravity 2.0. Turns one big task into a set of isolated, efficient agent missions — without burning your weekly quota.\n\n---\n\n## Use this skill when\n- A task spans 3+ files or components\n- You want multiple agents working at the same time\n- You've hit quota issues mid-task before\n- The task involves both planning AND building\n- You need browser agent + code agent + terminal agent running together\n\n## Do not use this skill when\n- Editing a single file or fixing one bug\n- Writing a quick script under 50 lines\n- Asking a question or generating a plan only\n\n---\n\n## Phase 1 — DECOMPOSE (before any agent runs)\n\nBefore spawning any subagent, the orchestrator MUST produce a Mission Brief. Announce:\n> \"Running subagent-orchestrator skill. Decomposing task into isolated missions.\"\n\nThen output a Mission Brief in this format:\n\n```\nMISSION BRIEF\n─────────────────────────────────────────\nGoal: [one sentence, what done looks like]\nTotal Agents: [N]\nQuota Strategy: [FLASH \u002F SONNET \u002F MIXED]\nExpected Token Cost: [LOW \u002F MEDIUM \u002F HIGH]\n\nAGENTS:\n[1] ID: agent-001\n    Role: [e.g. Planner \u002F Builder \u002F Tester \u002F Browser]\n    Scope: [exact files or URLs this agent touches]\n    Model: [Gemini Flash \u002F Claude Sonnet]\n    Input: [what it receives]\n    Output: [what it produces]\n    Depends on: [none \u002F agent-001]\n\n[2] ...\n─────────────────────────────────────────\n```\n\n**Wait for user to approve the Mission Brief before proceeding.**\nIf the user edits it, update and re-confirm. Never skip this step.\n\n---\n\n## Phase 2 — QUOTA ROUTING\n\nBefore assigning models, apply this decision tree:\n\n```\nIs this task > 20 files OR > 500 lines of new code?\n  YES → Use Gemini Flash for all agents. Reserve Sonnet for final review only.\n  NO  → Is this task creative UI \u002F complex logic \u002F API design?\n          YES → Use Sonnet for builder agent, Flash for all others.\n          NO  → Use Gemini Flash for everything.\n```\n\n**Model cost rules (never violate these):**\n- Claude Opus → NEVER use in subagents. Too expensive.\n- Claude Sonnet → Max 1 subagent per mission.\n- Gemini Flash → Default for all subagents. Fast, cheap, separate quota pool.\n- Browser subagent → Always runs on its own pool. Use sparingly (1 per mission max).\n\n---\n\n## Phase 3 — CONTEXT ISOLATION\n\nEach subagent gets a scoped context packet. Never give all agents the full codebase.\n\nFor each agent, prepare:\n```\nAGENT CONTEXT PACKET — agent-[ID]\nFiles to read: [list only what this agent needs]\nFiles to write: [list only what this agent will create\u002Fedit]\nDo NOT read: [explicitly exclude irrelevant files]\nKnowledge: [paste only the relevant section of GEMINI.md]\n```\n\nRule: If an agent doesn't need `node_modules`, `package-lock.json`, `.next\u002F`, or `dist\u002F` — add them to a `.antigravityignore` before the agent runs.\n\n---\n\n## Phase 4 — PARALLEL EXECUTION\n\nSpawn agents in dependency order:\n\n```\nRound 1 (no dependencies): Run agents in parallel\nRound 2 (depends on Round 1): Wait for all Round 1 outputs, then run\nRound 3 (final): Integrate + verify\n```\n\nBetween rounds, the orchestrator MUST:\n1. Collect each agent's output artifact\n2. Run a 3-point spot check:\n   - Did the agent stay within its assigned scope?\n   - Are there any import\u002Fexport conflicts with other agents' outputs?\n   - Did any agent produce a placeholder (\"TODO\", \"implement later\")?\n3. If any check fails → re-run that agent with corrected context. Do NOT continue.\n\n---\n\n## Phase 5 — ERROR RECOVERY\n\nIf a subagent fails or produces broken output:\n\n```\nRECOVERY PROTOCOL\n─────────────────────────────────────────\n1. Do NOT re-run the full mission.\n2. Identify the exact failure point.\n3. Spawn a single repair agent with:\n   - Only the broken file(s) as scope\n   - The error message as context\n   - Model: Gemini Flash (cheapest for repairs)\n4. Validate the repair before continuing.\n─────────────────────────────────────────\n```\n\nNever cascade a broken output to the next agent. Always fix before moving forward.\n\n---\n\n## Phase 6 — INTEGRATION CHECK\n\nAfter all agents complete, run a final integration sweep:\n\n- [ ] All imports resolve correctly\n- [ ] No duplicate function\u002Fvariable names across files\n- [ ] No hardcoded values that should be env variables\n- [ ] No `console.log` left in production files\n- [ ] Types are consistent across components (TypeScript)\n- [ ] Build would succeed (`npm run build` mentally verified)\n\nIf any check fails, spawn one final repair agent scoped to the exact issue.\n\n---\n\n## Quota Monitoring Rules\n\nTrack estimated usage throughout the mission:\n\n| Event | Quota Impact |\n|-------|-------------|\n| Agent spawned | LOW (setup) |\n| File indexed (each) | LOW |\n| Tool call (file read\u002Fwrite) | MEDIUM |\n| Terminal command | MEDIUM |\n| Browser subagent activated | HIGH |\n| Thinking mode enabled | VERY HIGH |\n\nIf estimated usage crosses 60% of sprint quota mid-mission:\n- Pause and report: \"Quota checkpoint: ~60% of sprint used. Continue or defer remaining agents?\"\n- Switch remaining agents to Gemini Flash\n- Disable browser subagent if not yet started\n\n---\n\n## Communication Rules\n\n- Announce which agent is running at all times\n- Show a compact progress bar between rounds:\n  ```\n  Mission Progress: ████████░░ 4\u002F5 agents complete\n  Quota Status: ▓▓▓▓░░░░░░ ~40% sprint used\n  ```\n- Never go silent for more than one agent turn\n- If blocked, say why explicitly — never just stop\n\n---\n\n## Examples\n\nSee `examples\u002F` folder:\n- `nextjs-feature.md` — Building a full Next.js feature with 3 parallel agents\n- `api-plus-frontend.md` — Backend API agent + Frontend UI agent running in parallel\n- `debug-mission.md` — Repair mission for a broken build using minimal quota\n\n## Limitations\n\n- This skill coordinates agent planning; it does not provide a runtime scheduler or enforce quota limits automatically.\n- Parallel agents still need explicit scoping, review, and integration by the parent agent.\n- Do not use it when a single focused edit or direct answer would be faster and clearer.\n","# Subagent Orchestrator\n\nA quota-aware, parallel subagent coordination skill for Antigravity 2.0. Turns one big task into a set of isolated, efficient agent missions — without burning your weekly quota.\n\n---\n\n## Use this skill when\n- A task spans 3+ files or components\n- You want multiple agents working at the same time\n- You've hit quota issues mid-task before\n- The task involves both planning AND building\n- You need browser agent + code agent + terminal agent running together\n\n## Do not use this skill when\n- Editing a single file or fixing one bug\n- Writing a quick script under 50 lines\n- Asking a question or generating a plan only\n\n---\n\n## Phase 1 — DECOMPOSE (before any agent runs)\n\nBefore spawning any subagent, the orchestrator MUST produce a Mission Brief. Announce:\n> \"Running subagent-orchestrator skill. Decomposing task into isolated missions.\"\n\nThen output a Mission Brief in this format:\n\n```\nMISSION BRIEF\n─────────────────────────────────────────\nGoal: [one sentence, what done looks like]\nTotal Agents: [N]\nQuota Strategy: [FLASH \u002F SONNET \u002F MIXED]\nExpected Token Cost: [LOW \u002F MEDIUM \u002F HIGH]\n\nAGENTS:\n[1] ID: agent-001\n    Role: [e.g. Planner \u002F Builder \u002F Tester \u002F Browser]\n    Scope: [exact files or URLs this agent touches]\n    Model: [Gemini Flash \u002F Claude Sonnet]\n    Input: [what it receives]\n    Output: [what it produces]\n    Depends on: [none \u002F agent-001]\n\n[2] ...\n─────────────────────────────────────────\n```\n\n**Wait for user to approve the Mission Brief before proceeding.**\nIf the user edits it, update and re-confirm. Never skip this step.\n\n---\n\n## Phase 2 — QUOTA ROUTING\n\nBefore assigning models, apply this decision tree:\n\n```\nIs this task > 20 files OR > 500 lines of new code?\n  YES → Use Gemini Flash for all agents. Reserve Sonnet for final review only.\n  NO  → Is this task creative UI \u002F complex logic \u002F API design?\n          YES → Use Sonnet for builder agent, Flash for all others.\n          NO  → Use Gemini Flash for everything.\n```\n\n**Model cost rules (never violate these):**\n- Claude Opus → NEVER use in subagents. Too expensive.\n- Claude Sonnet → Max 1 subagent per mission.\n- Gemini Flash → Default for all subagents. Fast, cheap, separate quota pool.\n- Browser subagent → Always runs on its own pool. Use sparingly (1 per mission max).\n\n---\n\n## Phase 3 — CONTEXT ISOLATION\n\nEach subagent gets a scoped context packet. Never give all agents the full codebase.\n\nFor each agent, prepare:\n```\nAGENT CONTEXT PACKET — agent-[ID]\nFiles to read: [list only what this agent needs]\nFiles to write: [list only what this agent will create\u002Fedit]\nDo NOT read: [explicitly exclude irrelevant files]\nKnowledge: [paste only the relevant section of GEMINI.md]\n```\n\nRule: If an agent doesn't need `node_modules`, `package-lock.json`, `.next\u002F`, or `dist\u002F` — add them to a `.antigravityignore` before the agent runs.\n\n---\n\n## Phase 4 — PARALLEL EXECUTION\n\nSpawn agents in dependency order:\n\n```\nRound 1 (no dependencies): Run agents in parallel\nRound 2 (depends on Round 1): Wait for all Round 1 outputs, then run\nRound 3 (final): Integrate + verify\n```\n\nBetween rounds, the orchestrator MUST:\n1. Collect each agent's output artifact\n2. Run a 3-point spot check:\n   - Did the agent stay within its assigned scope?\n   - Are there any import\u002Fexport conflicts with other agents' outputs?\n   - Did any agent produce a placeholder (\"TODO\", \"implement later\")?\n3. If any check fails → re-run that agent with corrected context. Do NOT continue.\n\n---\n\n## Phase 5 — ERROR RECOVERY\n\nIf a subagent fails or produces broken output:\n\n```\nRECOVERY PROTOCOL\n─────────────────────────────────────────\n1. Do NOT re-run the full mission.\n2. Identify the exact failure point.\n3. Spawn a single repair agent with:\n   - Only the broken file(s) as scope\n   - The error message as context\n   - Model: Gemini Flash (cheapest for repairs)\n4. Validate the repair before continuing.\n─────────────────────────────────────────\n```\n\nNever cascade a broken output to the next agent. Always fix before moving forward.\n\n---\n\n## Phase 6 — INTEGRATION CHECK\n\nAfter all agents complete, run a final integration sweep:\n\n- [ ] All imports resolve correctly\n- [ ] No duplicate function\u002Fvariable names across files\n- [ ] No hardcoded values that should be env variables\n- [ ] No `console.log` left in production files\n- [ ] Types are consistent across components (TypeScript)\n- [ ] Build would succeed (`npm run build` mentally verified)\n\nIf any check fails, spawn one final repair agent scoped to the exact issue.\n\n---\n\n## Quota Monitoring Rules\n\nTrack estimated usage throughout the mission:\n\n| Event | Quota Impact |\n|-------|-------------|\n| Agent spawned | LOW (setup) |\n| File indexed (each) | LOW |\n| Tool call (file read\u002Fwrite) | MEDIUM |\n| Terminal command | MEDIUM |\n| Browser subagent activated | HIGH |\n| Thinking mode enabled | VERY HIGH |\n\nIf estimated usage crosses 60% of sprint quota mid-mission:\n- Pause and report: \"Quota checkpoint: ~60% of sprint used. Continue or defer remaining agents?\"\n- Switch remaining agents to Gemini Flash\n- Disable browser subagent if not yet started\n\n---\n\n## Communication Rules\n\n- Announce which agent is running at all times\n- Show a compact progress bar between rounds:\n  ```\n  Mission Progress: ████████░░ 4\u002F5 agents complete\n  Quota Status: ▓▓▓▓░░░░░░ ~40% sprint used\n  ```\n- Never go silent for more than one agent turn\n- If blocked, say why explicitly — never just stop\n\n---\n\n## Examples\n\nSee `examples\u002F` folder:\n- `nextjs-feature.md` — Building a full Next.js feature with 3 parallel agents\n- `api-plus-frontend.md` — Backend API agent + Frontend UI agent running in parallel\n- `debug-mission.md` — Repair mission for a broken build using minimal quota\n\n## Limitations\n\n- This skill coordinates agent planning; it does not provide a runtime scheduler or enforce quota limits automatically.\n- Parallel agents still need explicit scoping, review, and integration by the parent agent.\n- Do not use it when a single focused edit or direct answer would be faster and clearer.\n",{"name":5,"risk":24,"tags":25,"author":31,"source":31,"version":32,"description":7},"safe",[26,27,28,29,30],"subagents","orchestration","quota","parallel","multi-agent","community","1.0.0","master","877653a671c51fae6476bd9f0d34ee6c408d68b9",".github\u002Fskills\u002Fsubagent-orchestrator","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group","https:\u002F\u002Ftrivoxa-group.vercel.app","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web","2026-08-01 17:29:31",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add princepatel04477-web\u002Ftrivoxa-group --skill subagent-orchestrator",{"tool":46,"command":47},"bunx","bunx skills add princepatel04477-web\u002Ftrivoxa-group --skill subagent-orchestrator",{"tool":49,"command":50},"pnpm","pnpm dlx skills add princepatel04477-web\u002Ftrivoxa-group --skill subagent-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002FSKILL.md",true,[54,60,64,68,72,76,80],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"examples\u002Fapi-plus-frontend.md","REFERENCE","参考文档",2625,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002Fexamples\u002Fapi-plus-frontend.md",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"examples\u002Fdebug-mission.md",2195,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002Fexamples\u002Fdebug-mission.md",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"examples\u002Fnextjs-feature.md",2713,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002Fexamples\u002Fnextjs-feature.md",{"path":69,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":70,"sourceHtmlUrl":71},"README.md",2793,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002FREADME.md",{"path":73,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":74,"sourceHtmlUrl":75},"resources\u002Fmission-brief-template.md",1121,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002Fresources\u002Fmission-brief-template.md",{"path":77,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":78,"sourceHtmlUrl":79},"resources\u002Fquota-reference.md",2168,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002Fresources\u002Fquota-reference.md",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"scripts\u002Finstall.js","SCRIPT","脚本",2029,"https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fsubagent-orchestrator\u002Fscripts\u002Finstall.js",[87,94,101,108,115,122],{"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":19},"01M78G4Z5RFJ72G536XYPC77PG","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzustand-store-ts\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":19},"01M78G4WQMHRST36KDP7AV3NR3","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoom-automation\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":19},"01M78G4T37F4SPS7M4KT0A8JJB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoho-crm-automation\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":19},"01M78G4QAJMF71KD1G38MNDQYK","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzod-validation-expert\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":19},"01M78G4MS3WE96MH5P561KFY95","zipai-optimizer","Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzipai-optimizer\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":19},"01M78G4GZ0T47C6929V9CVH1AK","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[]]