{ "schemaVersion": "1.0", "item": { "slug": "warden-studio-deploy", "name": "Deploy Agent on Warden Studio", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Kryptopaid/warden-studio-deploy", "canonicalUrl": "https://clawhub.ai/Kryptopaid/warden-studio-deploy", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/warden-studio-deploy", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=warden-studio-deploy", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "references/warden-studio-ui-notes.md", "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": "2026-04-30T16:55:25.780Z", "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/warden-studio-deploy" }, "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/warden-studio-deploy", "agentPageUrl": "https://openagent3.xyz/skills/warden-studio-deploy/agent", "manifestUrl": "https://openagent3.xyz/skills/warden-studio-deploy/agent.json", "briefUrl": "https://openagent3.xyz/skills/warden-studio-deploy/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": "Warden Studio", "body": "Automate publishing a Community Agent in Warden Studio through a safe, repeatable workflow that other agents can follow." }, { "title": "Safety & constraints (non-negotiable)", "body": "Never request or store seed phrases / private keys.\nNever ask the user to paste secrets into chat. If an API key must be entered, instruct the user to paste it directly into the Studio UI field.\nTreat publishing/onchain registration as high-risk: confirm network, fees, and what is being signed before any wallet confirmation.\nPrefer read-only validation (checking forms, status, preview) unless the user explicitly authorizes execution (e.g., \"yes, publish\" / \"yes, execute\").\nDo not reveal any private info (local files, credentials, IPs, internal logs).\nPublic comms: do not claim any affiliation or relationship unless it is publicly disclosed and the user explicitly asks you to state it." }, { "title": "What this skill does", "body": "Typical outcomes:\n\nLog into https://studio.wardenprotocol.org\nCreate a new Agent submission/listing\nProvide:\n\nAPI URL (service endpoint)\nAPI key / auth method (if required)\nName, description, skills, avatar\nBilling model (free vs paid per inference, in USDC)\n\n\nPay registration fee + gas (if prompted by the UI)\nVerify the agent shows up in Studio and becomes discoverable in Warden's Agent Hub (Community tab), when applicable." }, { "title": "0) Preconditions", "body": "A Chromium browser is available (Chrome/Brave/Edge/Chromium). (Firefox not supported.)\nUser can log in to Warden Studio (email/SSO/2FA completed).\nThe agent is already deployed somewhere and reachable via HTTPS (no UI required):\n\nstable API base URL\n(optional) API key or token if the endpoint is protected\n\n\nFunding is ready for registration (if required by the flow):\n\nUSDC on Base for the registration fee (confirm the fee in the UI)\nETH on Base for gas\n\nIf any of the above is missing, stop and ask the user to do that step." }, { "title": "1) Open + stabilize Studio", "body": "Open: https://studio.wardenprotocol.org\nWait for the landing/dashboard to load.\nTake a snapshot and identify:\n\nlogged-in user / account handle\nany \"Agents\" list/table or \"Submit / Create agent\" entry point\nnetwork/payment cues (e.g., Base, USDC, wallet connection state)\n\nIf Studio is gated by login, stop and ask the user to complete login in the UI." }, { "title": "2) Read-only checks (default)", "body": "Use these first to prevent failed submissions:\n\nConfirm the agent endpoint is reachable:\n\nthe URL is HTTPS\nno obvious typos\n(if a \"Test connection\" exists) run it\n\n\nValidate required metadata is prepared:\n\nagent name (short)\ndescription (clear, non-misleading)\nskills list (concise + accurate)\navatar image ready (square recommended)\n\n\nCheck billing/monetization options:\n\nfree vs per-inference (USDC)\nexpected fees shown by the UI" }, { "title": "3) Draft the submission (no publishing yet)", "body": "Direct create page (recommended): https://studio.wardenprotocol.org/agents/create\n\nCurrent “Register Agent” form fields\n\nFill the form top-to-bottom to match the UI sections:\n\nAPI details\n\nAPI URL* — your agent’s HTTPS endpoint\nAPI Key — if your endpoint requires a key\nNever paste secrets into chat; enter them directly into the Studio field.\n\nThe UI may also show helper links like “Build an agent using LangGraph” / “How it works”.\n\n\nInfo\n\nAgent Name*\nSelect agent skills* — choose the relevant skill tags\nDescribe the key features of the agent* — short, accurate capability summary\n\n\n\nAgent avatar\n\nPaste link to add an agent avatar → Image link (URL)\n\n\n\nBilling model\n\nChoose how the agent charges users: Per inference or Free\nIf Per inference: Cost in USDC* (numeric)\n\n\n\nAgent Preview\n\nAgent name\nShort description about your agent (max 100 characters)\n\n\n\nFinal action: Register agent\n\nNavigate to the agent submission flow (or go directly to https://studio.wardenprotocol.org/agents/create), then fill fields in a deterministic order:\n\nIdentity\n\nAgent name\nShort tagline (if any)\nCategory (if any)\n\n\n\nCapabilities\n\nDescription\nSkills (keywords and/or bullet list)\nLinks (docs, GitHub, website) if requested\n\n\n\nIntegration\n\nAPI URL (service endpoint)\nAuth:\n\nAPI key field (if present), or\nheader/token configuration (if present)\n\n\n\n\n\nBranding\n\nUpload avatar\nOptional banner/images (if supported)\n\n\n\nMonetization\n\nChoose billing model (free vs paid/per inference) if supported\nReview any platform/registration fee disclosures\n\nAt the end of drafting, stop and show the user a Submission Summary:\n\nAgent name + description (1–2 lines)\nSkills list\nAPI URL (domain + path)\nAuth method (mask any key/token)\nBilling model + any displayed fees" }, { "title": "4) Publish / register (requires explicit approval)", "body": "Execution gate: Do not click the final \"Publish / Register / Submit\" button unless the user explicitly replies with \"yes, publish\" or \"yes, execute\" (or an unambiguous equivalent).\n\nBefore finalizing, summarize:\n\nWhat action will happen (publish/register agent listing)\nWhat network/payment is involved (e.g., Base; registration fee + gas, as shown in the UI)\nAny costs shown in the UI (USDC amount + estimated gas)\nWhat could go wrong:\n\nwrong endpoint / downtime → failed validation\nwrong billing settings\nwallet prompt on wrong network\nunintended fee payment\n\nThen proceed with the final click and wallet confirmation step (user signs in their wallet)." }, { "title": "5) Post-publish verification", "body": "After publishing/registration:\n\nConfirm status in Studio:\n\n\"Submitted\", \"Pending\", \"Published\", etc.\n\n\nCapture any agent identifier or link shown (listing URL).\nCheck the agent appears in Studio's Agents list.\nIf the UI mentions distribution:\n\nverify it appears in Warden Agent Hub → Community tab (when available)\n\n\nRecord any errors verbatim and capture screenshots of:\n\nvalidation errors\npayment failures\nendpoint/auth failures" }, { "title": "Troubleshooting playbook", "body": "Common failures and fixes:\n\nEndpoint validation fails\n\nCheck HTTPS, trailing slashes, versioned paths\nConfirm the agent server is live and not geo-blocked\nIf auth required, verify the correct key/token was entered in UI (never paste it into chat)\n\n\n\nWallet/network mismatch\n\nEnsure wallet is on the correct network (e.g., Base) if Studio requires it\n\n\n\nInsufficient funds\n\nAdd USDC on Base for fee and ETH on Base for gas, then retry" }, { "title": "Building a wrapper skill other agents can use", "body": "When asked to \"create a skill that lets other agents publish via Warden Studio\":\n\nRecord the minimal repeatable workflow (URLs + UI landmarks) in references/warden-studio-ui-notes.md.\nKeep SKILL.md stable and general; put volatile UI selectors, screenshots, and clickpaths in references.\nOnly add deterministic scripts if they reduce errors (e.g., a submission summary checklist formatter)." }, { "title": "References", "body": "Read references/warden-studio-ui-notes.md for the latest Studio navigation map, observed fields, and publishing quirks." } ], "body": "Warden Studio\n\nAutomate publishing a Community Agent in Warden Studio through a safe, repeatable workflow that other agents can follow.\n\nSafety & constraints (non-negotiable)\nNever request or store seed phrases / private keys.\nNever ask the user to paste secrets into chat. If an API key must be entered, instruct the user to paste it directly into the Studio UI field.\nTreat publishing/onchain registration as high-risk: confirm network, fees, and what is being signed before any wallet confirmation.\nPrefer read-only validation (checking forms, status, preview) unless the user explicitly authorizes execution (e.g., \"yes, publish\" / \"yes, execute\").\nDo not reveal any private info (local files, credentials, IPs, internal logs).\nPublic comms: do not claim any affiliation or relationship unless it is publicly disclosed and the user explicitly asks you to state it.\nWhat this skill does\n\nTypical outcomes:\n\nLog into https://studio.wardenprotocol.org\nCreate a new Agent submission/listing\nProvide:\nAPI URL (service endpoint)\nAPI key / auth method (if required)\nName, description, skills, avatar\nBilling model (free vs paid per inference, in USDC)\nPay registration fee + gas (if prompted by the UI)\nVerify the agent shows up in Studio and becomes discoverable in Warden's Agent Hub (Community tab), when applicable.\nWorkflow (UI automation)\n0) Preconditions\nA Chromium browser is available (Chrome/Brave/Edge/Chromium). (Firefox not supported.)\nUser can log in to Warden Studio (email/SSO/2FA completed).\nThe agent is already deployed somewhere and reachable via HTTPS (no UI required):\nstable API base URL\n(optional) API key or token if the endpoint is protected\nFunding is ready for registration (if required by the flow):\nUSDC on Base for the registration fee (confirm the fee in the UI)\nETH on Base for gas\n\nIf any of the above is missing, stop and ask the user to do that step.\n\n1) Open + stabilize Studio\nOpen: https://studio.wardenprotocol.org\nWait for the landing/dashboard to load.\nTake a snapshot and identify:\nlogged-in user / account handle\nany \"Agents\" list/table or \"Submit / Create agent\" entry point\nnetwork/payment cues (e.g., Base, USDC, wallet connection state)\n\nIf Studio is gated by login, stop and ask the user to complete login in the UI.\n\n2) Read-only checks (default)\n\nUse these first to prevent failed submissions:\n\nConfirm the agent endpoint is reachable:\nthe URL is HTTPS\nno obvious typos\n(if a \"Test connection\" exists) run it\nValidate required metadata is prepared:\nagent name (short)\ndescription (clear, non-misleading)\nskills list (concise + accurate)\navatar image ready (square recommended)\nCheck billing/monetization options:\nfree vs per-inference (USDC)\nexpected fees shown by the UI\n3) Draft the submission (no publishing yet)\n\nDirect create page (recommended): https://studio.wardenprotocol.org/agents/create\n\nCurrent “Register Agent” form fields\n\nFill the form top-to-bottom to match the UI sections:\n\nAPI details\n\nAPI URL* — your agent’s HTTPS endpoint\nAPI Key — if your endpoint requires a key\nNever paste secrets into chat; enter them directly into the Studio field.\n\nThe UI may also show helper links like “Build an agent using LangGraph” / “How it works”.\n\nInfo\n\nAgent Name*\nSelect agent skills* — choose the relevant skill tags\nDescribe the key features of the agent* — short, accurate capability summary\n\nAgent avatar\n\nPaste link to add an agent avatar → Image link (URL)\n\nBilling model\n\nChoose how the agent charges users: Per inference or Free\nIf Per inference: Cost in USDC* (numeric)\n\nAgent Preview\n\nAgent name\nShort description about your agent (max 100 characters)\n\nFinal action: Register agent\n\nNavigate to the agent submission flow (or go directly to https://studio.wardenprotocol.org/agents/create), then fill fields in a deterministic order:\n\nIdentity\n\nAgent name\nShort tagline (if any)\nCategory (if any)\n\nCapabilities\n\nDescription\nSkills (keywords and/or bullet list)\nLinks (docs, GitHub, website) if requested\n\nIntegration\n\nAPI URL (service endpoint)\nAuth:\nAPI key field (if present), or\nheader/token configuration (if present)\n\nBranding\n\nUpload avatar\nOptional banner/images (if supported)\n\nMonetization\n\nChoose billing model (free vs paid/per inference) if supported\nReview any platform/registration fee disclosures\n\nAt the end of drafting, stop and show the user a Submission Summary:\n\nAgent name + description (1–2 lines)\nSkills list\nAPI URL (domain + path)\nAuth method (mask any key/token)\nBilling model + any displayed fees\n4) Publish / register (requires explicit approval)\n\nExecution gate: Do not click the final \"Publish / Register / Submit\" button unless the user explicitly replies with \"yes, publish\" or \"yes, execute\" (or an unambiguous equivalent).\n\nBefore finalizing, summarize:\n\nWhat action will happen (publish/register agent listing)\nWhat network/payment is involved (e.g., Base; registration fee + gas, as shown in the UI)\nAny costs shown in the UI (USDC amount + estimated gas)\nWhat could go wrong:\nwrong endpoint / downtime → failed validation\nwrong billing settings\nwallet prompt on wrong network\nunintended fee payment\n\nThen proceed with the final click and wallet confirmation step (user signs in their wallet).\n\n5) Post-publish verification\n\nAfter publishing/registration:\n\nConfirm status in Studio:\n\"Submitted\", \"Pending\", \"Published\", etc.\nCapture any agent identifier or link shown (listing URL).\nCheck the agent appears in Studio's Agents list.\nIf the UI mentions distribution:\nverify it appears in Warden Agent Hub → Community tab (when available)\nRecord any errors verbatim and capture screenshots of:\nvalidation errors\npayment failures\nendpoint/auth failures\nTroubleshooting playbook\n\nCommon failures and fixes:\n\nEndpoint validation fails\n\nCheck HTTPS, trailing slashes, versioned paths\nConfirm the agent server is live and not geo-blocked\nIf auth required, verify the correct key/token was entered in UI (never paste it into chat)\n\nWallet/network mismatch\n\nEnsure wallet is on the correct network (e.g., Base) if Studio requires it\n\nInsufficient funds\n\nAdd USDC on Base for fee and ETH on Base for gas, then retry\nBuilding a wrapper skill other agents can use\n\nWhen asked to \"create a skill that lets other agents publish via Warden Studio\":\n\nRecord the minimal repeatable workflow (URLs + UI landmarks) in references/warden-studio-ui-notes.md.\nKeep SKILL.md stable and general; put volatile UI selectors, screenshots, and clickpaths in references.\nOnly add deterministic scripts if they reduce errors (e.g., a submission summary checklist formatter).\nReferences\nRead references/warden-studio-ui-notes.md for the latest Studio navigation map, observed fields, and publishing quirks." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Kryptopaid/warden-studio-deploy", "publisherUrl": "https://clawhub.ai/Kryptopaid/warden-studio-deploy", "owner": "Kryptopaid", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/warden-studio-deploy", "downloadUrl": "https://openagent3.xyz/downloads/warden-studio-deploy", "agentUrl": "https://openagent3.xyz/skills/warden-studio-deploy/agent", "manifestUrl": "https://openagent3.xyz/skills/warden-studio-deploy/agent.json", "briefUrl": "https://openagent3.xyz/skills/warden-studio-deploy/agent.md" } }