{ "schemaVersion": "1.0", "item": { "slug": "reveal-reviewer", "name": "Reveal Reviewer skills", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/tolulopeayo/reveal-reviewer", "canonicalUrl": "https://clawhub.ai/tolulopeayo/reveal-reviewer", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/reveal-reviewer", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=reveal-reviewer", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/api-reference.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/reveal-reviewer" }, "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/reveal-reviewer", "agentPageUrl": "https://openagent3.xyz/skills/reveal-reviewer/agent", "manifestUrl": "https://openagent3.xyz/skills/reveal-reviewer/agent.json", "briefUrl": "https://openagent3.xyz/skills/reveal-reviewer/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": "Reveal Reviewer Agent", "body": "Review products on Reveal by navigating websites, recording observations, and submitting structured feedback via the API.\nSupports both:\n\nTask Review Mode (vendor-created tasks)\nProactive Self-Review Mode (reviewer/agent-initiated reviews not tied to vendor tasks)" }, { "title": "Prerequisites", "body": "REVEAL_REVIEWER_API_KEY environment variable (reviewer API key from Reveal profile)\nagent-browser skill installed for website navigation and screenshots\n\nIf not installed: clawhub install TheSethRose/agent-browser" }, { "title": "Authentication", "body": "All API calls use:\n\nAuthorization: Bearer $REVEAL_REVIEWER_API_KEY\n\nBase URL: https://www.testreveal.ai/api/v1" }, { "title": "Review Workflow", "body": "First determine which workflow applies using prompt context (do not hardcode a mode externally):" }, { "title": "Routing Logic (must run before reviewing)", "body": "Check explicit intent in prompt\n\nIf prompt says \"proactive review\" / \"self review\" / \"review this site even if no task\" → use Proactive Self-Review Mode.\n\n\nIf product name or URL is mentioned, check for matching Reveal tasks\n\nGET /tasks/available?limit=50\nMatch candidates by website, product, or title against prompt context.\n\n\nValidate goal alignment\n\nFor each candidate task, GET /tasks/{taskId} and compare instructions.objective, instructions.steps, and instructions.feedback to the user's requested goal.\nIf a matching task exists and goal aligns, use Task Review Mode.\n\n\nFallback\n\nIf no matching/aligned task exists, use Proactive Self-Review Mode.\n\nAlways state briefly which mode was selected and why." }, { "title": "Step 1: Find available tasks", "body": "GET /tasks/available to browse open review tasks.\n\nOptional query params: taskType (web|mobile), limit (default 20)\n\nResponse contains tasks with: title, description, product name, website URL, spots left, and whether you've already submitted.\n\nPresent the available tasks to the user and ask which one they'd like to review." }, { "title": "Step 2: Get task instructions", "body": "GET /tasks/{taskId} to get full task details including:\n\ninstructions.objective — what the reviewer should accomplish\ninstructions.steps — step-by-step guide\ninstructions.feedback — what kind of feedback to focus on\nwebsite — URL to navigate to\n\nRead the instructions carefully before starting the review." }, { "title": "Step 3: Navigate and review the product", "body": "Use the agent-browser skill to:\n\nNavigate to the task's website URL\nTake a snapshot to understand the page structure\nFollow the task instructions step by step\nAt each significant step:\n\nTake a screenshot using agent-browser's snapshot feature\nNote what you observe (good, bad, confusing, broken)\nTry to interact with elements as instructed\n\n\nRecord issues encountered (bugs, confusing UI, errors, slow loading)\nRecord positives (clean design, fast loading, intuitive flow)\nNote suggestions for improvement\n\nBe thorough but concise. Focus on what the task instructions ask for." }, { "title": "Step 4: Structure your findings", "body": "After completing the review, organize your observations into this structure:\n\n{\n \"issues\": [\n {\"description\": \"Checkout button was not visible on mobile viewport\", \"severity\": \"High\"},\n {\"description\": \"No loading indicator when form submits\", \"severity\": \"Medium\"}\n ],\n \"positives\": [\n {\"description\": \"Clean, modern design with good contrast\"},\n {\"description\": \"Onboarding flow was intuitive and quick\"}\n ],\n \"suggestions\": [\n \"Add a progress bar to the checkout flow\",\n \"Reduce the number of required form fields\"\n ],\n \"sentiment\": \"positive\",\n \"summary\": \"Overall the product is well-designed with good UX. Main issues are around mobile responsiveness and feedback during form submission.\",\n \"stepsCompleted\": [\n \"Navigated to homepage - loaded in 2s\",\n \"Clicked Sign Up - form appeared instantly\",\n \"Filled form and submitted - no loading indicator shown\",\n \"Redirected to dashboard - clean layout\"\n ]\n}\n\nSentiment should be one of: positive, negative, neutral, mixed" }, { "title": "Step 5: Submit the review", "body": "POST /submissions with body:\n\n{\n \"taskId\": \"the_task_id\",\n \"source\": \"agent\",\n \"findings\": {\n \"issues\": [...],\n \"positives\": [...],\n \"suggestions\": [...],\n \"sentiment\": \"positive\",\n \"summary\": \"...\",\n \"stepsCompleted\": [...]\n },\n \"screenshots\": [\"url1\", \"url2\"],\n \"notes\": \"Optional additional notes\"\n}\n\nScreenshots should be URLs if your agent-browser supports image capture/upload. If not, omit the screenshots field.\n\nConfirm the submission was successful and share the response with the user." }, { "title": "Proactive Self-Review Mode", "body": "Use this when the user wants the agent to review a product/site without selecting a vendor-created task." }, { "title": "Step A: Create self-review target", "body": "POST /self-reviews with:\n\n{\n \"websiteUrl\": \"https://example.com\",\n \"websiteName\": \"Example\",\n \"title\": \"Proactive review of Example onboarding\",\n \"category\": \"Technology\",\n \"description\": \"Focus on first-time onboarding and pricing clarity\",\n \"source\": \"agent\"\n}\n\nStore the returned id as selfReviewId." }, { "title": "Step B: Navigate and review", "body": "Use agent-browser to perform the requested journey:\n\nOpen the target URL\nExplore key flows requested by the user\nCapture evidence and observations\nBuild structured findings (issues, positives, suggestions, sentiment, summary, stepsCompleted)" }, { "title": "Step C: Complete the self-review", "body": "PATCH /self-reviews/{selfReviewId} with:\n\n{\n \"source\": \"agent\",\n \"completed\": true,\n \"findings\": {\n \"issues\": [{\"description\": \"...\", \"severity\": \"High\"}],\n \"positives\": [{\"description\": \"...\"}],\n \"suggestions\": [\"...\"],\n \"sentiment\": \"mixed\",\n \"summary\": \"Summary...\",\n \"stepsCompleted\": [\"...\"]\n },\n \"screenshots\": [\"https://...png\"],\n \"notes\": \"Optional notes\"\n}\n\nIf the flow includes a hosted recording/video, include videoUrl too." }, { "title": "Step D: Confirm outcome", "body": "GET /self-reviews/{selfReviewId} to verify it is marked completed and report the result back to the user." }, { "title": "Check your submissions", "body": "GET /tasks/{taskId} — check hasSubmitted field to see if you already reviewed a task." }, { "title": "List proactive self-reviews", "body": "GET /self-reviews?completed=true&source=agent" }, { "title": "Get notifications", "body": "GET /notifications?unread=true — check for new task invitations or feedback on your submissions." }, { "title": "Mark notifications read", "body": "PATCH /notifications with {\"markAllRead\": true}" }, { "title": "Guardrails", "body": "Never fabricate observations. Only report what you actually see when navigating the product.\nIf the website is down or unreachable, report that as your finding instead of making up content.\nAlways follow the task instructions. Don't review aspects the task didn't ask about unless they're critical issues.\nBe objective and fair. Report both positives and negatives.\nIf you can't complete a step in the instructions, note that as an issue with details.\nDon't submit a review if you haven't actually navigated the product.\nConfirm with the user before submitting the review." } ], "body": "Reveal Reviewer Agent\n\nReview products on Reveal by navigating websites, recording observations, and submitting structured feedback via the API. Supports both:\n\nTask Review Mode (vendor-created tasks)\nProactive Self-Review Mode (reviewer/agent-initiated reviews not tied to vendor tasks)\nPrerequisites\nREVEAL_REVIEWER_API_KEY environment variable (reviewer API key from Reveal profile)\nagent-browser skill installed for website navigation and screenshots\nIf not installed: clawhub install TheSethRose/agent-browser\nAuthentication\n\nAll API calls use:\n\nAuthorization: Bearer $REVEAL_REVIEWER_API_KEY\n\n\nBase URL: https://www.testreveal.ai/api/v1\n\nReview Workflow\n\nFirst determine which workflow applies using prompt context (do not hardcode a mode externally):\n\nRouting Logic (must run before reviewing)\nCheck explicit intent in prompt\nIf prompt says \"proactive review\" / \"self review\" / \"review this site even if no task\" → use Proactive Self-Review Mode.\nIf product name or URL is mentioned, check for matching Reveal tasks\nGET /tasks/available?limit=50\nMatch candidates by website, product, or title against prompt context.\nValidate goal alignment\nFor each candidate task, GET /tasks/{taskId} and compare instructions.objective, instructions.steps, and instructions.feedback to the user's requested goal.\nIf a matching task exists and goal aligns, use Task Review Mode.\nFallback\nIf no matching/aligned task exists, use Proactive Self-Review Mode.\n\nAlways state briefly which mode was selected and why.\n\nStep 1: Find available tasks\n\nGET /tasks/available to browse open review tasks.\n\nOptional query params: taskType (web|mobile), limit (default 20)\n\nResponse contains tasks with: title, description, product name, website URL, spots left, and whether you've already submitted.\n\nPresent the available tasks to the user and ask which one they'd like to review.\n\nStep 2: Get task instructions\n\nGET /tasks/{taskId} to get full task details including:\n\ninstructions.objective — what the reviewer should accomplish\ninstructions.steps — step-by-step guide\ninstructions.feedback — what kind of feedback to focus on\nwebsite — URL to navigate to\n\nRead the instructions carefully before starting the review.\n\nStep 3: Navigate and review the product\n\nUse the agent-browser skill to:\n\nNavigate to the task's website URL\nTake a snapshot to understand the page structure\nFollow the task instructions step by step\nAt each significant step:\nTake a screenshot using agent-browser's snapshot feature\nNote what you observe (good, bad, confusing, broken)\nTry to interact with elements as instructed\nRecord issues encountered (bugs, confusing UI, errors, slow loading)\nRecord positives (clean design, fast loading, intuitive flow)\nNote suggestions for improvement\n\nBe thorough but concise. Focus on what the task instructions ask for.\n\nStep 4: Structure your findings\n\nAfter completing the review, organize your observations into this structure:\n\n{\n \"issues\": [\n {\"description\": \"Checkout button was not visible on mobile viewport\", \"severity\": \"High\"},\n {\"description\": \"No loading indicator when form submits\", \"severity\": \"Medium\"}\n ],\n \"positives\": [\n {\"description\": \"Clean, modern design with good contrast\"},\n {\"description\": \"Onboarding flow was intuitive and quick\"}\n ],\n \"suggestions\": [\n \"Add a progress bar to the checkout flow\",\n \"Reduce the number of required form fields\"\n ],\n \"sentiment\": \"positive\",\n \"summary\": \"Overall the product is well-designed with good UX. Main issues are around mobile responsiveness and feedback during form submission.\",\n \"stepsCompleted\": [\n \"Navigated to homepage - loaded in 2s\",\n \"Clicked Sign Up - form appeared instantly\",\n \"Filled form and submitted - no loading indicator shown\",\n \"Redirected to dashboard - clean layout\"\n ]\n}\n\n\nSentiment should be one of: positive, negative, neutral, mixed\n\nStep 5: Submit the review\n\nPOST /submissions with body:\n\n{\n \"taskId\": \"the_task_id\",\n \"source\": \"agent\",\n \"findings\": {\n \"issues\": [...],\n \"positives\": [...],\n \"suggestions\": [...],\n \"sentiment\": \"positive\",\n \"summary\": \"...\",\n \"stepsCompleted\": [...]\n },\n \"screenshots\": [\"url1\", \"url2\"],\n \"notes\": \"Optional additional notes\"\n}\n\n\nScreenshots should be URLs if your agent-browser supports image capture/upload. If not, omit the screenshots field.\n\nConfirm the submission was successful and share the response with the user.\n\nProactive Self-Review Mode\n\nUse this when the user wants the agent to review a product/site without selecting a vendor-created task.\n\nStep A: Create self-review target\n\nPOST /self-reviews with:\n\n{\n \"websiteUrl\": \"https://example.com\",\n \"websiteName\": \"Example\",\n \"title\": \"Proactive review of Example onboarding\",\n \"category\": \"Technology\",\n \"description\": \"Focus on first-time onboarding and pricing clarity\",\n \"source\": \"agent\"\n}\n\n\nStore the returned id as selfReviewId.\n\nStep B: Navigate and review\n\nUse agent-browser to perform the requested journey:\n\nOpen the target URL\nExplore key flows requested by the user\nCapture evidence and observations\nBuild structured findings (issues, positives, suggestions, sentiment, summary, stepsCompleted)\nStep C: Complete the self-review\n\nPATCH /self-reviews/{selfReviewId} with:\n\n{\n \"source\": \"agent\",\n \"completed\": true,\n \"findings\": {\n \"issues\": [{\"description\": \"...\", \"severity\": \"High\"}],\n \"positives\": [{\"description\": \"...\"}],\n \"suggestions\": [\"...\"],\n \"sentiment\": \"mixed\",\n \"summary\": \"Summary...\",\n \"stepsCompleted\": [\"...\"]\n },\n \"screenshots\": [\"https://...png\"],\n \"notes\": \"Optional notes\"\n}\n\n\nIf the flow includes a hosted recording/video, include videoUrl too.\n\nStep D: Confirm outcome\n\nGET /self-reviews/{selfReviewId} to verify it is marked completed and report the result back to the user.\n\nOther Capabilities\nCheck your submissions\n\nGET /tasks/{taskId} — check hasSubmitted field to see if you already reviewed a task.\n\nList proactive self-reviews\n\nGET /self-reviews?completed=true&source=agent\n\nGet notifications\n\nGET /notifications?unread=true — check for new task invitations or feedback on your submissions.\n\nMark notifications read\n\nPATCH /notifications with {\"markAllRead\": true}\n\nGuardrails\nNever fabricate observations. Only report what you actually see when navigating the product.\nIf the website is down or unreachable, report that as your finding instead of making up content.\nAlways follow the task instructions. Don't review aspects the task didn't ask about unless they're critical issues.\nBe objective and fair. Report both positives and negatives.\nIf you can't complete a step in the instructions, note that as an issue with details.\nDon't submit a review if you haven't actually navigated the product.\nConfirm with the user before submitting the review." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/tolulopeayo/reveal-reviewer", "publisherUrl": "https://clawhub.ai/tolulopeayo/reveal-reviewer", "owner": "tolulopeayo", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/reveal-reviewer", "downloadUrl": "https://openagent3.xyz/downloads/reveal-reviewer", "agentUrl": "https://openagent3.xyz/skills/reveal-reviewer/agent", "manifestUrl": "https://openagent3.xyz/skills/reveal-reviewer/agent.json", "briefUrl": "https://openagent3.xyz/skills/reveal-reviewer/agent.md" } }