# Send Deploy Agent on Warden Studio to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/warden-studio-deploy", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=warden-studio-deploy", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "references/warden-studio-ui-notes.md", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "warden-studio-deploy", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T10:58:53.854Z", "expiresAt": "2026-05-09T10:58:53.854Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=warden-studio-deploy", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=warden-studio-deploy", "contentDisposition": "attachment; filename=\"warden-studio-deploy-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "warden-studio-deploy" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "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." ] } }, "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" } } ``` ## Documentation ### Warden Studio Automate publishing a Community Agent in Warden Studio through a safe, repeatable workflow that other agents can follow. ### Safety & constraints (non-negotiable) Never request or store seed phrases / private keys. Never 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. Treat publishing/onchain registration as high-risk: confirm network, fees, and what is being signed before any wallet confirmation. Prefer read-only validation (checking forms, status, preview) unless the user explicitly authorizes execution (e.g., "yes, publish" / "yes, execute"). Do not reveal any private info (local files, credentials, IPs, internal logs). Public comms: do not claim any affiliation or relationship unless it is publicly disclosed and the user explicitly asks you to state it. ### What this skill does Typical outcomes: Log into https://studio.wardenprotocol.org Create a new Agent submission/listing Provide: API URL (service endpoint) API key / auth method (if required) Name, description, skills, avatar Billing model (free vs paid per inference, in USDC) Pay registration fee + gas (if prompted by the UI) Verify the agent shows up in Studio and becomes discoverable in Warden's Agent Hub (Community tab), when applicable. ### 0) Preconditions A Chromium browser is available (Chrome/Brave/Edge/Chromium). (Firefox not supported.) User can log in to Warden Studio (email/SSO/2FA completed). The agent is already deployed somewhere and reachable via HTTPS (no UI required): stable API base URL (optional) API key or token if the endpoint is protected Funding is ready for registration (if required by the flow): USDC on Base for the registration fee (confirm the fee in the UI) ETH on Base for gas If any of the above is missing, stop and ask the user to do that step. ### 1) Open + stabilize Studio Open: https://studio.wardenprotocol.org Wait for the landing/dashboard to load. Take a snapshot and identify: logged-in user / account handle any "Agents" list/table or "Submit / Create agent" entry point network/payment cues (e.g., Base, USDC, wallet connection state) If Studio is gated by login, stop and ask the user to complete login in the UI. ### 2) Read-only checks (default) Use these first to prevent failed submissions: Confirm the agent endpoint is reachable: the URL is HTTPS no obvious typos (if a "Test connection" exists) run it Validate required metadata is prepared: agent name (short) description (clear, non-misleading) skills list (concise + accurate) avatar image ready (square recommended) Check billing/monetization options: free vs per-inference (USDC) expected fees shown by the UI ### 3) Draft the submission (no publishing yet) Direct create page (recommended): https://studio.wardenprotocol.org/agents/create Current “Register Agent” form fields Fill the form top-to-bottom to match the UI sections: API details API URL* — your agent’s HTTPS endpoint API Key — if your endpoint requires a key Never paste secrets into chat; enter them directly into the Studio field. The UI may also show helper links like “Build an agent using LangGraph” / “How it works”. Info Agent Name* Select agent skills* — choose the relevant skill tags Describe the key features of the agent* — short, accurate capability summary Agent avatar Paste link to add an agent avatar → Image link (URL) Billing model Choose how the agent charges users: Per inference or Free If Per inference: Cost in USDC* (numeric) Agent Preview Agent name Short description about your agent (max 100 characters) Final action: Register agent Navigate to the agent submission flow (or go directly to https://studio.wardenprotocol.org/agents/create), then fill fields in a deterministic order: Identity Agent name Short tagline (if any) Category (if any) Capabilities Description Skills (keywords and/or bullet list) Links (docs, GitHub, website) if requested Integration API URL (service endpoint) Auth: API key field (if present), or header/token configuration (if present) Branding Upload avatar Optional banner/images (if supported) Monetization Choose billing model (free vs paid/per inference) if supported Review any platform/registration fee disclosures At the end of drafting, stop and show the user a Submission Summary: Agent name + description (1–2 lines) Skills list API URL (domain + path) Auth method (mask any key/token) Billing model + any displayed fees ### 4) Publish / register (requires explicit approval) 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). Before finalizing, summarize: What action will happen (publish/register agent listing) What network/payment is involved (e.g., Base; registration fee + gas, as shown in the UI) Any costs shown in the UI (USDC amount + estimated gas) What could go wrong: wrong endpoint / downtime → failed validation wrong billing settings wallet prompt on wrong network unintended fee payment Then proceed with the final click and wallet confirmation step (user signs in their wallet). ### 5) Post-publish verification After publishing/registration: Confirm status in Studio: "Submitted", "Pending", "Published", etc. Capture any agent identifier or link shown (listing URL). Check the agent appears in Studio's Agents list. If the UI mentions distribution: verify it appears in Warden Agent Hub → Community tab (when available) Record any errors verbatim and capture screenshots of: validation errors payment failures endpoint/auth failures ### Troubleshooting playbook Common failures and fixes: Endpoint validation fails Check HTTPS, trailing slashes, versioned paths Confirm the agent server is live and not geo-blocked If auth required, verify the correct key/token was entered in UI (never paste it into chat) Wallet/network mismatch Ensure wallet is on the correct network (e.g., Base) if Studio requires it Insufficient funds Add USDC on Base for fee and ETH on Base for gas, then retry ### Building a wrapper skill other agents can use When asked to "create a skill that lets other agents publish via Warden Studio": Record the minimal repeatable workflow (URLs + UI landmarks) in references/warden-studio-ui-notes.md. Keep SKILL.md stable and general; put volatile UI selectors, screenshots, and clickpaths in references. Only add deterministic scripts if they reduce errors (e.g., a submission summary checklist formatter). ### References Read references/warden-studio-ui-notes.md for the latest Studio navigation map, observed fields, and publishing quirks. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: Kryptopaid - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-02T10:58:53.854Z - Expires at: 2026-05-09T10:58:53.854Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/warden-studio-deploy) - [Send to Agent page](https://openagent3.xyz/skills/warden-studio-deploy/agent) - [JSON manifest](https://openagent3.xyz/skills/warden-studio-deploy/agent.json) - [Markdown brief](https://openagent3.xyz/skills/warden-studio-deploy/agent.md) - [Download page](https://openagent3.xyz/downloads/warden-studio-deploy)