{ "schemaVersion": "1.0", "item": { "slug": "smart-model-routing-for-zai", "name": "Smart Model Routing for Z.AI", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/PrincNL/smart-model-routing-for-zai", "canonicalUrl": "https://clawhub.ai/PrincNL/smart-model-routing-for-zai", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/smart-model-routing-for-zai", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=smart-model-routing-for-zai", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/smart-model-routing-for-zai" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/smart-model-routing-for-zai", "agentPageUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai/agent", "manifestUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai/agent.json", "briefUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Smart Model Switching", "body": "Three-tier z.ai (GLM) routing: Flash → Standard → Plus / 32B\n\nStart with the cheapest model. Escalate only when needed. Designed to minimize API cost without sacrificing correctness." }, { "title": "The Golden Rule", "body": "If a human would need more than 30 seconds of focused thinking, escalate from Flash to Standard.\nIf the task involves architecture, complex tradeoffs, or deep reasoning, escalate to Plus / 32B." }, { "title": "Model Reality (Relative)", "body": "TierExample ModelsPurposeFlashGLM-4.5-Flash, GLM-4.7-FlashFastest & cheapestStandardGLM-4.6, GLM-4.7Strong reasoning & codePlus / 32BGLM-4-Plus, GLM-4-32B-128KHeavy reasoning & architecture\n\nBottom line: Wrong model selection wastes money OR time. Flash for simple, Standard for normal work, Plus/32B for complex decisions." }, { "title": "💚 FLASH — Default for Simple Tasks", "body": "Stay on Flash for:\n\nFactual Q&A — “what is X”, “who is Y”, “when did Z”\nQuick lookups — definitions, unit conversions, short translations\nStatus checks — monitoring, file reads, session state\nHeartbeats — periodic checks, OK responses\nMemory & reminders\nCasual conversation — greetings, acknowledgments\nSimple file ops — read, list, basic writes\nOne-liner tasks — anything answerable in 1–2 sentences\nCron jobs (always Flash by default)" }, { "title": "NEVER do these on Flash", "body": "❌ Write code longer than 10 lines\n❌ Create comparison tables\n❌ Write more than 3 paragraphs\n❌ Do multi-step analysis\n❌ Write reports or proposals" }, { "title": "💛 STANDARD — Core Workhorse", "body": "Escalate to Standard for:" }, { "title": "Code & Technical", "body": "Code generation — functions, scripts, features\nDebugging — normal bug investigation\nCode review — PRs, refactors\nDocumentation — README, comments, guides" }, { "title": "Analysis & Planning", "body": "Comparisons and evaluations\nPlanning — roadmaps, task breakdowns\nResearch synthesis\nMulti-step reasoning" }, { "title": "Writing & Content", "body": "Long-form writing (>3 paragraphs)\nSummaries of long documents\nStructured output — tables, outlines\n\nMost real user conversations belong here." }, { "title": "❤️ PLUS / 32B — Complex Reasoning Only", "body": "Escalate to Plus / 32B for:" }, { "title": "Architecture & Design", "body": "System and service architecture\nDatabase schema design\nDistributed or multi-tenant systems\nMajor refactors across multiple files" }, { "title": "Deep Analysis", "body": "Complex debugging (race conditions, subtle bugs)\nSecurity reviews\nPerformance optimization strategy\nRoot cause analysis" }, { "title": "Strategic & Judgment-Based Work", "body": "Strategic planning\nNuanced judgment and ambiguity\nDeep or multi-source research\nCritical production decisions" }, { "title": "For Subagents", "body": "// Routine monitoring\nsessions_spawn(task=\"Check backup status\", model=\"GLM-4.5-Flash\")\n\n// Standard code work\nsessions_spawn(task=\"Build the REST API endpoint\", model=\"GLM-4.7\")\n\n// Architecture decisions\nsessions_spawn(task=\"Design the database schema for multi-tenancy\", model=\"GLM-4-Plus\")\nFor Cron Jobs\njson\nCopy code\n{\n \"payload\": {\n \"kind\": \"agentTurn\",\n \"model\": \"GLM-4.5-Flash\"\n }\n}\nAlways use Flash for cron unless the task genuinely needs reasoning.\n\n📊 Quick Decision Tree\npgsql\nCopy code\nIs it a greeting, lookup, status check, or 1–2 sentence answer?\n YES → FLASH\n NO ↓\n\nIs it code, analysis, planning, writing, or multi-step?\n YES → STANDARD\n NO ↓\n\nIs it architecture, deep reasoning, or a critical decision?\n YES → PLUS / 32B\n NO → Default to STANDARD, escalate if struggling\n📋 Quick Reference Card\nless\nCopy code\n┌─────────────────────────────────────────────────────────────┐\n│ SMART MODEL SWITCHING │\n│ Flash → Standard → Plus / 32B │\n├─────────────────────────────────────────────────────────────┤\n│ 💚 FLASH (cheapest) │\n│ • Greetings, status checks, quick lookups │\n│ • Factual Q&A, reminders │\n│ • Simple file ops, 1–2 sentence answers │\n├─────────────────────────────────────────────────────────────┤\n│ 💛 STANDARD (workhorse) │\n│ • Code > 10 lines, debugging │\n│ • Analysis, comparisons, planning │\n│ • Reports, long writing │\n├─────────────────────────────────────────────────────────────┤\n│ ❤️ PLUS / 32B (complex) │\n│ • Architecture decisions │\n│ • Complex debugging, multi-file refactoring │\n│ • Strategic planning, deep research │\n├─────────────────────────────────────────────────────────────┤\n│ 💡 RULE: >30 sec human thinking → escalate │\n│ 💰 START CHEAP → SCALE ONLY WHEN NEEDED │\n└─────────────────────────────────────────────────────────────┘\nBuilt for z.ai (GLM) setups." } ], "body": "Smart Model Switching\n\nThree-tier z.ai (GLM) routing: Flash → Standard → Plus / 32B\n\nStart with the cheapest model. Escalate only when needed. Designed to minimize API cost without sacrificing correctness.\n\nThe Golden Rule\n\nIf a human would need more than 30 seconds of focused thinking, escalate from Flash to Standard.\nIf the task involves architecture, complex tradeoffs, or deep reasoning, escalate to Plus / 32B.\n\nModel Reality (Relative)\nTier\tExample Models\tPurpose\nFlash\tGLM-4.5-Flash, GLM-4.7-Flash\tFastest & cheapest\nStandard\tGLM-4.6, GLM-4.7\tStrong reasoning & code\nPlus / 32B\tGLM-4-Plus, GLM-4-32B-128K\tHeavy reasoning & architecture\n\nBottom line: Wrong model selection wastes money OR time. Flash for simple, Standard for normal work, Plus/32B for complex decisions.\n\n💚 FLASH — Default for Simple Tasks\n\nStay on Flash for:\n\nFactual Q&A — “what is X”, “who is Y”, “when did Z”\nQuick lookups — definitions, unit conversions, short translations\nStatus checks — monitoring, file reads, session state\nHeartbeats — periodic checks, OK responses\nMemory & reminders\nCasual conversation — greetings, acknowledgments\nSimple file ops — read, list, basic writes\nOne-liner tasks — anything answerable in 1–2 sentences\nCron jobs (always Flash by default)\nNEVER do these on Flash\n❌ Write code longer than 10 lines\n❌ Create comparison tables\n❌ Write more than 3 paragraphs\n❌ Do multi-step analysis\n❌ Write reports or proposals\n💛 STANDARD — Core Workhorse\n\nEscalate to Standard for:\n\nCode & Technical\nCode generation — functions, scripts, features\nDebugging — normal bug investigation\nCode review — PRs, refactors\nDocumentation — README, comments, guides\nAnalysis & Planning\nComparisons and evaluations\nPlanning — roadmaps, task breakdowns\nResearch synthesis\nMulti-step reasoning\nWriting & Content\nLong-form writing (>3 paragraphs)\nSummaries of long documents\nStructured output — tables, outlines\n\nMost real user conversations belong here.\n\n❤️ PLUS / 32B — Complex Reasoning Only\n\nEscalate to Plus / 32B for:\n\nArchitecture & Design\nSystem and service architecture\nDatabase schema design\nDistributed or multi-tenant systems\nMajor refactors across multiple files\nDeep Analysis\nComplex debugging (race conditions, subtle bugs)\nSecurity reviews\nPerformance optimization strategy\nRoot cause analysis\nStrategic & Judgment-Based Work\nStrategic planning\nNuanced judgment and ambiguity\nDeep or multi-source research\nCritical production decisions\n🔄 Implementation\nFor Subagents\n// Routine monitoring\nsessions_spawn(task=\"Check backup status\", model=\"GLM-4.5-Flash\")\n\n// Standard code work\nsessions_spawn(task=\"Build the REST API endpoint\", model=\"GLM-4.7\")\n\n// Architecture decisions\nsessions_spawn(task=\"Design the database schema for multi-tenancy\", model=\"GLM-4-Plus\")\nFor Cron Jobs\njson\nCopy code\n{\n \"payload\": {\n \"kind\": \"agentTurn\",\n \"model\": \"GLM-4.5-Flash\"\n }\n}\nAlways use Flash for cron unless the task genuinely needs reasoning.\n\n📊 Quick Decision Tree\npgsql\nCopy code\nIs it a greeting, lookup, status check, or 1–2 sentence answer?\n YES → FLASH\n NO ↓\n\nIs it code, analysis, planning, writing, or multi-step?\n YES → STANDARD\n NO ↓\n\nIs it architecture, deep reasoning, or a critical decision?\n YES → PLUS / 32B\n NO → Default to STANDARD, escalate if struggling\n📋 Quick Reference Card\nless\nCopy code\n┌─────────────────────────────────────────────────────────────┐\n│ SMART MODEL SWITCHING │\n│ Flash → Standard → Plus / 32B │\n├─────────────────────────────────────────────────────────────┤\n│ 💚 FLASH (cheapest) │\n│ • Greetings, status checks, quick lookups │\n│ • Factual Q&A, reminders │\n│ • Simple file ops, 1–2 sentence answers │\n├─────────────────────────────────────────────────────────────┤\n│ 💛 STANDARD (workhorse) │\n│ • Code > 10 lines, debugging │\n│ • Analysis, comparisons, planning │\n│ • Reports, long writing │\n├─────────────────────────────────────────────────────────────┤\n│ ❤️ PLUS / 32B (complex) │\n│ • Architecture decisions │\n│ • Complex debugging, multi-file refactoring │\n│ • Strategic planning, deep research │\n├─────────────────────────────────────────────────────────────┤\n│ 💡 RULE: >30 sec human thinking → escalate │\n│ 💰 START CHEAP → SCALE ONLY WHEN NEEDED │\n└─────────────────────────────────────────────────────────────┘\nBuilt for z.ai (GLM) setups." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/PrincNL/smart-model-routing-for-zai", "publisherUrl": "https://clawhub.ai/PrincNL/smart-model-routing-for-zai", "owner": "PrincNL", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai", "downloadUrl": "https://openagent3.xyz/downloads/smart-model-routing-for-zai", "agentUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai/agent", "manifestUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai/agent.json", "briefUrl": "https://openagent3.xyz/skills/smart-model-routing-for-zai/agent.md" } }