{ "schemaVersion": "1.0", "item": { "slug": "glm-autoroute", "name": "GLM Autoroute", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/raufimusaddiq/glm-autoroute", "canonicalUrl": "https://clawhub.ai/raufimusaddiq/glm-autoroute", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/glm-autoroute", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=glm-autoroute", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "package.json" ], "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": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-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/glm-autoroute" }, "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/glm-autoroute", "agentPageUrl": "https://openagent3.xyz/skills/glm-autoroute/agent", "manifestUrl": "https://openagent3.xyz/skills/glm-autoroute/agent.json", "briefUrl": "https://openagent3.xyz/skills/glm-autoroute/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": "GLM Autoroute", "body": "Binary model routing for ZAI GLM models - lightweight vs heavyweight tasks." }, { "title": "Introduction", "body": "GLM-4.7 is the default model. Only spawn GLM-5 when the task actually needs it.\nUse sessions_spawn to run tasks with GLM-5:\n\nsessions_spawn({\n task: \"\",\n model: \"zai/glm-5\",\n label: \"\"\n})\n\nAfter done with GLM-5, the main session continues with GLM-4.7 as default." }, { "title": "GLM-4.7 (DEFAULT - zai/glm-4.7)", "body": "Use for lightweight tasks:\n\nSimple Q&A - What, When, Who, Where\nCasual chat - No reasoning needed\nQuick lookups\nFile lookups\nSimple tasks - repetitive tasks, formatting\nCron Jobs - if it needs reasoning, THEN ESCALATE TO GLM-5\nStatus checks\nBasic confirmations\nProvide concise output, just plain answer, no explaining\n\nDO NOT:\n\n❌ DO NOT CODE WITH GLM-4.7\n❌ DO NOT ANALYZE USING GLM-4.7\n❌ DO NOT ATTEMPT ANY REASONING USING GLM-4.7\n❌ DO NOT RESEARCH USING GLM-4.7\nIf you think the request does not fall into point 1-8, THEN ESCALATE TO GLM-5\nIf you think you will violate the DO NOT list, THEN ESCALATE TO GLM-5" }, { "title": "GLM-5 (zai/glm-5)", "body": "Use for heavyweight tasks:\n\nCoding (any complexity)\nAnalysis & debugging\nMulti-step reasoning\nResearch & investigation\nCritical planning\nArchitecture decisions\nComplex problem solving\nDeep research\nCritical decisions\nDetailed explanations" }, { "title": "Examples", "body": "TaskModelWhy\"Check calendar\"GLM-4.7Simple lookup\"What time is it?\"GLM-4.7Simple Q&A\"Heartbeat check\"GLM-4.7Routine\"Read this file\"GLM-4.7Simple lookup\"Summarize this\"GLM-4.7Basic task\"Write Python script\"GLM-5Coding\"Debug this error\"GLM-5Analysis\"Research market trends\"GLM-5Deep research\"Plan migration\"GLM-5Complex planning\"Analyze this issue\"GLM-5Analysis" }, { "title": "Other Notes", "body": "When the user asks to use a specific model, use it\nAlways mention which model is used in outputs — example: \"(GLM-5)\" or \"(GLM-4.7)\" at the end of responses\nAfter done with GLM-5 (via sessions_spawn), continue with GLM-4.7 as default\nIf you think the request does not fall into GLM-4.7 use cases, THEN ESCALATE TO GLM-5\nIf you think you will violate the DO NOT list, THEN ESCALATE TO GLM-5\nCoding = always GLM-5\nWhen in doubt → GLM-5 (better safe than sorry)\nHeartbeat checks → always GLM-4.7 unless complex analysis needed" }, { "title": "Memory Management with sessions_spawn", "body": "When spawning GLM-5 sub-agent sessions for ANY task (coding, research, analysis, planning, etc.), follow this pattern:" }, { "title": "Output Rules", "body": "1. Code Output (Important)\n\nFull code ONLY in files — do NOT include in announce unless explicitly requested\nProvide summary: what was created, file path, status, dependencies\nFull code disclosure ONLY when:\n\nUser explicitly requests: \"Show me the code\"\nDebugging needs code review\nUser wants to improve/modify it\n\n2. Full Announce for Other Results\n\nResearch findings, analysis results, solutions → announce FULLY to user\nDo NOT shorten, summarize, or condense non-code output\nUser gets complete findings, not a brief summary\n\n3. Two-Layer Memory Strategy\n\nMEMORY.md (Curated Long-Term)\n\nONLY key insights, decisions, lessons, significant findings, preferences\nClean, concise, actionable\nSkip routine data, step-by-step reasoning, temporary thoughts\n\nDetailed Reports (Task-Specific Files)\n\nFor research: research/YYYY-MM-DD-topic.md (full findings, data, analysis)\nFor coding: add inline docs/README in code folder if needed\nFor analysis: output files in relevant project directories" }, { "title": "Examples", "body": "Research task:\n\nsessions_spawn({\n task: \"Research X. Announce full findings to user. Write full report to research/YYYY-MM-DD-X.md, then write ONLY key insights to MEMORY.md (clean, concise).\",\n model: \"zai/glm-5\",\n label: \"Research X\"\n})\n\nCoding task:\n\nsessions_spawn({\n task: \"Write Python script for X. Save full code to file. Provide summary (what created, path, status, dependencies) in announce. Write key implementation decisions to MEMORY.md (important only).\",\n model: \"zai/glm-5\",\n label: \"Python script X\"\n})\n\nApply this pattern to ALL GLM-5 spawns. Code in files only, summary in announce, full disclosure on request." } ], "body": "GLM Autoroute\n\nBinary model routing for ZAI GLM models - lightweight vs heavyweight tasks.\n\nIntroduction\nGLM-4.7 is the default model. Only spawn GLM-5 when the task actually needs it.\nUse sessions_spawn to run tasks with GLM-5:\nsessions_spawn({\n task: \"\",\n model: \"zai/glm-5\",\n label: \"\"\n})\n\nAfter done with GLM-5, the main session continues with GLM-4.7 as default.\nModels\nGLM-4.7 (DEFAULT - zai/glm-4.7)\n\nUse for lightweight tasks:\n\nSimple Q&A - What, When, Who, Where\nCasual chat - No reasoning needed\nQuick lookups\nFile lookups\nSimple tasks - repetitive tasks, formatting\nCron Jobs - if it needs reasoning, THEN ESCALATE TO GLM-5\nStatus checks\nBasic confirmations\nProvide concise output, just plain answer, no explaining\n\nDO NOT:\n\n❌ DO NOT CODE WITH GLM-4.7\n❌ DO NOT ANALYZE USING GLM-4.7\n❌ DO NOT ATTEMPT ANY REASONING USING GLM-4.7\n❌ DO NOT RESEARCH USING GLM-4.7\nIf you think the request does not fall into point 1-8, THEN ESCALATE TO GLM-5\nIf you think you will violate the DO NOT list, THEN ESCALATE TO GLM-5\nGLM-5 (zai/glm-5)\n\nUse for heavyweight tasks:\n\nCoding (any complexity)\nAnalysis & debugging\nMulti-step reasoning\nResearch & investigation\nCritical planning\nArchitecture decisions\nComplex problem solving\nDeep research\nCritical decisions\nDetailed explanations\nExamples\nTask\tModel\tWhy\n\"Check calendar\"\tGLM-4.7\tSimple lookup\n\"What time is it?\"\tGLM-4.7\tSimple Q&A\n\"Heartbeat check\"\tGLM-4.7\tRoutine\n\"Read this file\"\tGLM-4.7\tSimple lookup\n\"Summarize this\"\tGLM-4.7\tBasic task\n\"Write Python script\"\tGLM-5\tCoding\n\"Debug this error\"\tGLM-5\tAnalysis\n\"Research market trends\"\tGLM-5\tDeep research\n\"Plan migration\"\tGLM-5\tComplex planning\n\"Analyze this issue\"\tGLM-5\tAnalysis\nOther Notes\nWhen the user asks to use a specific model, use it\nAlways mention which model is used in outputs — example: \"(GLM-5)\" or \"(GLM-4.7)\" at the end of responses\nAfter done with GLM-5 (via sessions_spawn), continue with GLM-4.7 as default\nIf you think the request does not fall into GLM-4.7 use cases, THEN ESCALATE TO GLM-5\nIf you think you will violate the DO NOT list, THEN ESCALATE TO GLM-5\nCoding = always GLM-5\nWhen in doubt → GLM-5 (better safe than sorry)\nHeartbeat checks → always GLM-4.7 unless complex analysis needed\nMemory Management with sessions_spawn\n\nWhen spawning GLM-5 sub-agent sessions for ANY task (coding, research, analysis, planning, etc.), follow this pattern:\n\nOutput Rules\n\n1. Code Output (Important)\n\nFull code ONLY in files — do NOT include in announce unless explicitly requested\nProvide summary: what was created, file path, status, dependencies\nFull code disclosure ONLY when:\nUser explicitly requests: \"Show me the code\"\nDebugging needs code review\nUser wants to improve/modify it\n\n2. Full Announce for Other Results\n\nResearch findings, analysis results, solutions → announce FULLY to user\nDo NOT shorten, summarize, or condense non-code output\nUser gets complete findings, not a brief summary\n\n3. Two-Layer Memory Strategy\n\nMEMORY.md (Curated Long-Term)\n\nONLY key insights, decisions, lessons, significant findings, preferences\nClean, concise, actionable\nSkip routine data, step-by-step reasoning, temporary thoughts\n\nDetailed Reports (Task-Specific Files)\n\nFor research: research/YYYY-MM-DD-topic.md (full findings, data, analysis)\nFor coding: add inline docs/README in code folder if needed\nFor analysis: output files in relevant project directories\nExamples\n\nResearch task:\n\nsessions_spawn({\n task: \"Research X. Announce full findings to user. Write full report to research/YYYY-MM-DD-X.md, then write ONLY key insights to MEMORY.md (clean, concise).\",\n model: \"zai/glm-5\",\n label: \"Research X\"\n})\n\n\nCoding task:\n\nsessions_spawn({\n task: \"Write Python script for X. Save full code to file. Provide summary (what created, path, status, dependencies) in announce. Write key implementation decisions to MEMORY.md (important only).\",\n model: \"zai/glm-5\",\n label: \"Python script X\"\n})\n\n\nApply this pattern to ALL GLM-5 spawns. Code in files only, summary in announce, full disclosure on request." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/raufimusaddiq/glm-autoroute", "publisherUrl": "https://clawhub.ai/raufimusaddiq/glm-autoroute", "owner": "raufimusaddiq", "version": "1.2.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/glm-autoroute", "downloadUrl": "https://openagent3.xyz/downloads/glm-autoroute", "agentUrl": "https://openagent3.xyz/skills/glm-autoroute/agent", "manifestUrl": "https://openagent3.xyz/skills/glm-autoroute/agent.json", "briefUrl": "https://openagent3.xyz/skills/glm-autoroute/agent.md" } }