{ "schemaVersion": "1.0", "item": { "slug": "open-router", "name": "Open Router", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/ivangdavila/open-router", "canonicalUrl": "https://clawhub.ai/ivangdavila/open-router", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/open-router", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=open-router", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "auth-and-provider.md", "cost-guardrails.md", "fallback-reliability.md", "memory-template.md", "routing-playbooks.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": "2026-04-30T16:55:25.780Z", "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/open-router" }, "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/open-router", "agentPageUrl": "https://openagent3.xyz/skills/open-router/agent", "manifestUrl": "https://openagent3.xyz/skills/open-router/agent.json", "briefUrl": "https://openagent3.xyz/skills/open-router/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": "Setup", "body": "On first use, read setup.md to align activation boundaries, reliability goals, and routing preferences before making configuration changes." }, { "title": "When to Use", "body": "Use this skill when the user wants to connect an OpenAI-compatible workflow to OpenRouter, choose models by task type, set safe fallbacks, and control cost drift over time." }, { "title": "Architecture", "body": "Memory lives in ~/open-router/. See memory-template.md for structure.\n\n~/open-router/\n├── memory.md # Active routing profile and constraints\n├── providers.md # Confirmed provider and auth choices\n├── routing-rules.md # Task -> model and fallback policy\n├── incidents.md # Outages, rate limits, and recovery notes\n└── budgets.md # Spend guardrails and optimization actions" }, { "title": "Quick Reference", "body": "Use the smallest relevant file for the current task.\n\nTopicFileSetup and activation preferencessetup.mdMemory templatememory-template.mdAuthentication and provider wiringauth-and-provider.mdRouting patterns by workloadrouting-playbooks.mdReliability and fallback handlingfallback-reliability.mdCost controls and spend reviewscost-guardrails.md" }, { "title": "1. Start from Workload Classes, Not Model Hype", "body": "Classify requests first: coding, analysis, extraction, summarization, or long-context synthesis.\nMap each class to a primary model and a fallback before changing any defaults." }, { "title": "2. Keep Authentication Explicit and Verifiable", "body": "Use OPENROUTER_API_KEY from the local environment, never pasted into logs or chat memory.\nValidate auth with a minimal request before applying routing changes." }, { "title": "3. Design Fallbacks for Failure Modes, Not Convenience", "body": "Separate fallback reasons: rate limit, provider outage, latency spike, or output quality failure.\nKeep at least one fallback from a different provider family for resilience." }, { "title": "4. Enforce Cost Boundaries Before Throughput Tuning", "body": "Set cost ceilings by task class and check expected token burn before broad rollout.\nRoute low-stakes tasks to cheaper models and reserve premium models for high-impact tasks." }, { "title": "5. Change One Layer at a Time", "body": "Modify either model selection, fallback policy, or budget limits in a single iteration.\nAfter each change, run a quick verification prompt set and record outcome." }, { "title": "6. Record Decisions for Repeatability", "body": "Save the final routing policy, rationale, and known tradeoffs in memory.\nReuse proven policies instead of repeatedly rebuilding from scratch." }, { "title": "Common Traps", "body": "Choosing one model for every task -> higher cost and unstable quality under varied workloads.\nUsing same-family fallback chain only -> cascading failures during provider-specific incidents.\nIgnoring token limits for long inputs -> truncated responses and hidden quality loss.\nChanging routing and budgets simultaneously -> unclear root cause when quality drops.\nRunning without verification prompts -> broken routing detected only after user-facing failures." }, { "title": "External Endpoints", "body": "These endpoints are used only to discover model metadata and execute routed inference requests under explicit user task intent.\n\nEndpointData SentPurposehttps://openrouter.ai/api/v1/modelsnone or auth header onlyDiscover current model catalog and metadatahttps://openrouter.ai/api/v1/chat/completionsuser prompt content and selected model idExecute routed inference requests\n\nNo other data is sent externally." }, { "title": "Security & Privacy", "body": "Data that leaves your machine:\n\nPrompt text and selected model metadata sent to OpenRouter when inference is requested.\n\nData that stays local:\n\nRouting notes and preferences under ~/open-router/.\nLocal environment variable references and verification logs.\n\nThis skill does NOT:\n\nRequest raw API keys in chat.\nStore plaintext secrets in skill memory files.\nModify files outside ~/open-router/ for its own state." }, { "title": "Trust", "body": "By using this skill, prompt content is sent to OpenRouter for model execution.\nOnly install if you trust this service with your data." }, { "title": "Related Skills", "body": "Install with clawhub install if user confirms:\n\napi — API request design, payload shaping, and response validation patterns\nauth — credential handling and auth troubleshooting workflows\nmodels — model comparison and selection guidance\nmonitoring — runtime health checks and incident tracking practices" }, { "title": "Feedback", "body": "If useful: clawhub star open-router\nStay updated: clawhub sync" } ], "body": "Setup\n\nOn first use, read setup.md to align activation boundaries, reliability goals, and routing preferences before making configuration changes.\n\nWhen to Use\n\nUse this skill when the user wants to connect an OpenAI-compatible workflow to OpenRouter, choose models by task type, set safe fallbacks, and control cost drift over time.\n\nArchitecture\n\nMemory lives in ~/open-router/. See memory-template.md for structure.\n\n~/open-router/\n├── memory.md # Active routing profile and constraints\n├── providers.md # Confirmed provider and auth choices\n├── routing-rules.md # Task -> model and fallback policy\n├── incidents.md # Outages, rate limits, and recovery notes\n└── budgets.md # Spend guardrails and optimization actions\n\nQuick Reference\n\nUse the smallest relevant file for the current task.\n\nTopic\tFile\nSetup and activation preferences\tsetup.md\nMemory template\tmemory-template.md\nAuthentication and provider wiring\tauth-and-provider.md\nRouting patterns by workload\trouting-playbooks.md\nReliability and fallback handling\tfallback-reliability.md\nCost controls and spend reviews\tcost-guardrails.md\nCore Rules\n1. Start from Workload Classes, Not Model Hype\nClassify requests first: coding, analysis, extraction, summarization, or long-context synthesis.\nMap each class to a primary model and a fallback before changing any defaults.\n2. Keep Authentication Explicit and Verifiable\nUse OPENROUTER_API_KEY from the local environment, never pasted into logs or chat memory.\nValidate auth with a minimal request before applying routing changes.\n3. Design Fallbacks for Failure Modes, Not Convenience\nSeparate fallback reasons: rate limit, provider outage, latency spike, or output quality failure.\nKeep at least one fallback from a different provider family for resilience.\n4. Enforce Cost Boundaries Before Throughput Tuning\nSet cost ceilings by task class and check expected token burn before broad rollout.\nRoute low-stakes tasks to cheaper models and reserve premium models for high-impact tasks.\n5. Change One Layer at a Time\nModify either model selection, fallback policy, or budget limits in a single iteration.\nAfter each change, run a quick verification prompt set and record outcome.\n6. Record Decisions for Repeatability\nSave the final routing policy, rationale, and known tradeoffs in memory.\nReuse proven policies instead of repeatedly rebuilding from scratch.\nCommon Traps\nChoosing one model for every task -> higher cost and unstable quality under varied workloads.\nUsing same-family fallback chain only -> cascading failures during provider-specific incidents.\nIgnoring token limits for long inputs -> truncated responses and hidden quality loss.\nChanging routing and budgets simultaneously -> unclear root cause when quality drops.\nRunning without verification prompts -> broken routing detected only after user-facing failures.\nExternal Endpoints\n\nThese endpoints are used only to discover model metadata and execute routed inference requests under explicit user task intent.\n\nEndpoint\tData Sent\tPurpose\nhttps://openrouter.ai/api/v1/models\tnone or auth header only\tDiscover current model catalog and metadata\nhttps://openrouter.ai/api/v1/chat/completions\tuser prompt content and selected model id\tExecute routed inference requests\n\nNo other data is sent externally.\n\nSecurity & Privacy\n\nData that leaves your machine:\n\nPrompt text and selected model metadata sent to OpenRouter when inference is requested.\n\nData that stays local:\n\nRouting notes and preferences under ~/open-router/.\nLocal environment variable references and verification logs.\n\nThis skill does NOT:\n\nRequest raw API keys in chat.\nStore plaintext secrets in skill memory files.\nModify files outside ~/open-router/ for its own state.\nTrust\n\nBy using this skill, prompt content is sent to OpenRouter for model execution. Only install if you trust this service with your data.\n\nRelated Skills\n\nInstall with clawhub install if user confirms:\n\napi — API request design, payload shaping, and response validation patterns\nauth — credential handling and auth troubleshooting workflows\nmodels — model comparison and selection guidance\nmonitoring — runtime health checks and incident tracking practices\nFeedback\nIf useful: clawhub star open-router\nStay updated: clawhub sync" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/open-router", "publisherUrl": "https://clawhub.ai/ivangdavila/open-router", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/open-router", "downloadUrl": "https://openagent3.xyz/downloads/open-router", "agentUrl": "https://openagent3.xyz/skills/open-router/agent", "manifestUrl": "https://openagent3.xyz/skills/open-router/agent.json", "briefUrl": "https://openagent3.xyz/skills/open-router/agent.md" } }