{ "schemaVersion": "1.0", "item": { "slug": "loopuman", "name": "Loopuman", "source": "tencent", "type": "skill", "category": "内容创作", "sourceUrl": "https://clawhub.ai/seesayearn-boop/loopuman", "canonicalUrl": "https://clawhub.ai/seesayearn-boop/loopuman", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/loopuman", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=loopuman", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/api-reference.md", "scripts/loopuman.sh" ], "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": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/loopuman" }, "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/loopuman", "agentPageUrl": "https://openagent3.xyz/skills/loopuman/agent", "manifestUrl": "https://openagent3.xyz/skills/loopuman/agent.json", "briefUrl": "https://openagent3.xyz/skills/loopuman/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": "Loopuman — The Human Layer for AI", "body": "Route tasks to verified human workers when AI alone isn't enough. Workers are paid in 8 seconds via cUSD on Celo blockchain. No app download required — workers operate via Telegram and WhatsApp." }, { "title": "When to Use This Skill", "body": "Use Loopuman when the task requires real human judgment, perception, or local knowledge that AI cannot reliably provide:\n\nVerification — \"Is this business address real?\" \"Does this photo match this listing?\"\nTranslation — Nuanced, culturally-aware translation (not just word-for-word)\nContent moderation — \"Is this image appropriate?\" \"Does this review violate guidelines?\"\nImage labeling — \"What objects are in this photo?\" \"Rate this image quality 1-10\"\nLocal knowledge — \"What's the current price of tomatoes in Nairobi?\"\nSurveys & opinions — \"Which logo design is better?\" \"Rate this product description\"\nData collection — \"Find the phone number for this restaurant\"\nQuality assurance — \"Does this AI-generated text sound natural?\"\n\nDo NOT use for tasks AI can handle: math, code generation, summarization, web search, file operations." }, { "title": "Setup", "body": "Create the config file with your Loopuman API key:\n\nmkdir -p ~/.openclaw/skills/loopuman\ncat > ~/.openclaw/skills/loopuman/config.json << 'EOF'\n{\n \"apiKey\": \"YOUR_API_KEY\",\n \"apiUrl\": \"https://api.loopuman.com\"\n}\nEOF\n\nGet your API key (one command, no auth needed):\n\ncurl -X POST https://api.loopuman.com/api/v1/register \\\n -H \"Content-Type: application/json\" \\\n -d '{\"email\": \"you@example.com\", \"company_name\": \"Your Name\", \"promo_code\": \"LOBSTER\"}'\n\nThis returns your api_key (starts with lpm_). Save it immediately — it cannot be retrieved later.\n\nPromo codes for free credits:\n\nCLAW500 — 500 VAE ($5.00) for first 10 OpenClaw testers\nLOBSTER — 100 VAE ($1.00) for early access (50 spots)\nNo code — 25 VAE ($0.25) welcome bonus\n\nTo add more funds, message @LoopumanBot on Telegram and link your account." }, { "title": "API Authentication", "body": "All requests use the x-api-key header:\n\nx-api-key: YOUR_API_KEY" }, { "title": "Creating a Task", "body": "scripts/loopuman.sh create \\\n --title \"Verify business address\" \\\n --description \"Check if this address exists on Google Maps: 123 Main St, Nairobi, Kenya. Reply with YES/NO and a screenshot.\" \\\n --category other \\\n --budget 50 \\\n --estimated-seconds 120\n\nParameters:\n\n--title — Short task title (required)\n--description — Detailed instructions for the human worker (required, be specific!)\n--category — One of: survey, labeling, translation, writing, research, content_creation, ai_training, micro, other (default: other). Note: for verification tasks use other, for moderation use other, for data collection use research.\n--budget — Payment in VAE tokens. 100 VAE = $1 USD. (default: 100)\n--estimated-seconds — Expected time for worker to complete (required for fair pay calculation, default: 120)\n--max-workers — Number of workers (default: 1, max: 100)\n--priority — normal or high (high notifies workers immediately)\n--webhook — URL for push notifications on completion\n\nCategory minimum budgets:\n\nsurvey, labeling, ai_training, micro: 25 VAE ($0.25)\nresearch, content_creation: 75 VAE ($0.75)\nwriting, translation: 100 VAE ($1.00)\n\nFair pay enforcement: Loopuman enforces a $6/hr minimum effective rate. If your budget divided by estimated time is below this, the API will suggest a higher budget.\n\nWriting good task descriptions:\n\nBe specific about what you need (\"Reply YES or NO\" not \"verify this\")\nInclude all context the worker needs\nSpecify the expected format of the response\nSet clear success criteria" }, { "title": "Checking Task Status + Getting Results", "body": "scripts/loopuman.sh status --task-id \n\nReturns full task details including:\n\nstatus: active, completed, expired, cancelled\nprogress: count of approved, pending_review, in_progress submissions\nsubmissions: array of approved worker results with content\npending_submissions: results awaiting your approval" }, { "title": "Polling for Completion", "body": "For tasks that need a result before continuing:\n\n# Poll every 30 seconds, timeout after 10 minutes\nscripts/loopuman.sh wait --task-id --interval 30 --timeout 600\n\nReturns the result as soon as an approved submission is available." }, { "title": "Listing Tasks", "body": "scripts/loopuman.sh list" }, { "title": "Cancelling a Task", "body": "scripts/loopuman.sh cancel --task-id \n\nRefunds your balance if no workers have started." }, { "title": "Task Types and Pricing", "body": "CategoryDescriptionMin Budget (VAE)Typical CompletionsurveyQuick responses, opinions25 ($0.25)1-5 minlabelingTag images, categorize content25 ($0.25)1-5 minmicro5-second microtasks25 ($0.25)<1 minai_trainingRLHF, preference ranking25 ($0.25)1-5 minresearchFind info, investigate75 ($0.75)5-20 mincontent_creationCreative work75 ($0.75)5-20 minwritingArticles, descriptions100 ($1.00)10-30 mintranslationLanguage translation100 ($1.00)5-15 minotherCustom tasks25 ($0.25)Varies" }, { "title": "Examples", "body": "Verify an address:\n\"Create a Loopuman task to verify if '456 Kenyatta Ave, Nairobi' is a real business address\"\n→ create --title \"Verify address\" --description \"Check Google Maps for 456 Kenyatta Ave, Nairobi. Reply YES/NO with screenshot.\" --category other --budget 30 --estimated-seconds 120\n\nTranslate with cultural context:\n\"Use Loopuman to translate 'We're excited to launch' into Swahili naturally\"\n→ create --title \"Translate to Swahili\" --description \"Translate to Swahili. Make it sound natural, not robotic: 'We're excited to launch our new product'\" --category translation --budget 100 --estimated-seconds 180\n\nGet a human opinion:\n\"Ask a real person which logo looks more professional\"\n→ create --title \"Logo comparison\" --description \"Which logo looks more professional? A or B? Explain why in 2 sentences.\" --category survey --budget 25 --estimated-seconds 60\n\nCheck AI output:\n\"Have a human verify this AI-generated product description\"\n→ create --title \"QA check on AI text\" --description \"Does this sound natural and accurate? Flag any issues: [paste text]\" --category other --budget 30 --estimated-seconds 90" }, { "title": "Error Handling", "body": "HTTP CodeMeaningFix401Invalid API keyCheck x-api-key in config.json400Missing fields or invalid categoryCheck required params402Insufficient VAE balanceTop up via @LoopumanBot404Task not foundVerify task ID429Rate limit exceededWait and retry" }, { "title": "Links", "body": "Website: https://loopuman.com\nTelegram Bot: https://t.me/LoopumanBot\nERC-8004 Agent: https://www.8004scan.io/agents/celo/17\nMCP: https://api.loopuman.com/.well-known/mcp.json\nA2A: https://api.loopuman.com/.well-known/agent-card.json\n\n⚠️ Budget Safety: Tasks are paid to workers upon completion. Start with small budgets (25-50 VAE) when testing. Loopuman charges 20% commission on top of the budget you set." } ], "body": "Loopuman — The Human Layer for AI\n\nRoute tasks to verified human workers when AI alone isn't enough. Workers are paid in 8 seconds via cUSD on Celo blockchain. No app download required — workers operate via Telegram and WhatsApp.\n\nWhen to Use This Skill\n\nUse Loopuman when the task requires real human judgment, perception, or local knowledge that AI cannot reliably provide:\n\nVerification — \"Is this business address real?\" \"Does this photo match this listing?\"\nTranslation — Nuanced, culturally-aware translation (not just word-for-word)\nContent moderation — \"Is this image appropriate?\" \"Does this review violate guidelines?\"\nImage labeling — \"What objects are in this photo?\" \"Rate this image quality 1-10\"\nLocal knowledge — \"What's the current price of tomatoes in Nairobi?\"\nSurveys & opinions — \"Which logo design is better?\" \"Rate this product description\"\nData collection — \"Find the phone number for this restaurant\"\nQuality assurance — \"Does this AI-generated text sound natural?\"\n\nDo NOT use for tasks AI can handle: math, code generation, summarization, web search, file operations.\n\nSetup\n\nCreate the config file with your Loopuman API key:\n\nmkdir -p ~/.openclaw/skills/loopuman\ncat > ~/.openclaw/skills/loopuman/config.json << 'EOF'\n{\n \"apiKey\": \"YOUR_API_KEY\",\n \"apiUrl\": \"https://api.loopuman.com\"\n}\nEOF\n\n\nGet your API key (one command, no auth needed):\n\ncurl -X POST https://api.loopuman.com/api/v1/register \\\n -H \"Content-Type: application/json\" \\\n -d '{\"email\": \"you@example.com\", \"company_name\": \"Your Name\", \"promo_code\": \"LOBSTER\"}'\n\n\nThis returns your api_key (starts with lpm_). Save it immediately — it cannot be retrieved later.\n\nPromo codes for free credits:\n\nCLAW500 — 500 VAE ($5.00) for first 10 OpenClaw testers\nLOBSTER — 100 VAE ($1.00) for early access (50 spots)\nNo code — 25 VAE ($0.25) welcome bonus\n\nTo add more funds, message @LoopumanBot on Telegram and link your account.\n\nAPI Authentication\n\nAll requests use the x-api-key header:\n\nx-api-key: YOUR_API_KEY\n\nCreating a Task\nscripts/loopuman.sh create \\\n --title \"Verify business address\" \\\n --description \"Check if this address exists on Google Maps: 123 Main St, Nairobi, Kenya. Reply with YES/NO and a screenshot.\" \\\n --category other \\\n --budget 50 \\\n --estimated-seconds 120\n\n\nParameters:\n\n--title — Short task title (required)\n--description — Detailed instructions for the human worker (required, be specific!)\n--category — One of: survey, labeling, translation, writing, research, content_creation, ai_training, micro, other (default: other). Note: for verification tasks use other, for moderation use other, for data collection use research.\n--budget — Payment in VAE tokens. 100 VAE = $1 USD. (default: 100)\n--estimated-seconds — Expected time for worker to complete (required for fair pay calculation, default: 120)\n--max-workers — Number of workers (default: 1, max: 100)\n--priority — normal or high (high notifies workers immediately)\n--webhook — URL for push notifications on completion\n\nCategory minimum budgets:\n\nsurvey, labeling, ai_training, micro: 25 VAE ($0.25)\nresearch, content_creation: 75 VAE ($0.75)\nwriting, translation: 100 VAE ($1.00)\n\nFair pay enforcement: Loopuman enforces a $6/hr minimum effective rate. If your budget divided by estimated time is below this, the API will suggest a higher budget.\n\nWriting good task descriptions:\n\nBe specific about what you need (\"Reply YES or NO\" not \"verify this\")\nInclude all context the worker needs\nSpecify the expected format of the response\nSet clear success criteria\nChecking Task Status + Getting Results\nscripts/loopuman.sh status --task-id \n\n\nReturns full task details including:\n\nstatus: active, completed, expired, cancelled\nprogress: count of approved, pending_review, in_progress submissions\nsubmissions: array of approved worker results with content\npending_submissions: results awaiting your approval\nPolling for Completion\n\nFor tasks that need a result before continuing:\n\n# Poll every 30 seconds, timeout after 10 minutes\nscripts/loopuman.sh wait --task-id --interval 30 --timeout 600\n\n\nReturns the result as soon as an approved submission is available.\n\nListing Tasks\nscripts/loopuman.sh list\n\nCancelling a Task\nscripts/loopuman.sh cancel --task-id \n\n\nRefunds your balance if no workers have started.\n\nTask Types and Pricing\nCategory\tDescription\tMin Budget (VAE)\tTypical Completion\nsurvey\tQuick responses, opinions\t25 ($0.25)\t1-5 min\nlabeling\tTag images, categorize content\t25 ($0.25)\t1-5 min\nmicro\t5-second microtasks\t25 ($0.25)\t<1 min\nai_training\tRLHF, preference ranking\t25 ($0.25)\t1-5 min\nresearch\tFind info, investigate\t75 ($0.75)\t5-20 min\ncontent_creation\tCreative work\t75 ($0.75)\t5-20 min\nwriting\tArticles, descriptions\t100 ($1.00)\t10-30 min\ntranslation\tLanguage translation\t100 ($1.00)\t5-15 min\nother\tCustom tasks\t25 ($0.25)\tVaries\nExamples\n\nVerify an address: \"Create a Loopuman task to verify if '456 Kenyatta Ave, Nairobi' is a real business address\" → create --title \"Verify address\" --description \"Check Google Maps for 456 Kenyatta Ave, Nairobi. Reply YES/NO with screenshot.\" --category other --budget 30 --estimated-seconds 120\n\nTranslate with cultural context: \"Use Loopuman to translate 'We're excited to launch' into Swahili naturally\" → create --title \"Translate to Swahili\" --description \"Translate to Swahili. Make it sound natural, not robotic: 'We're excited to launch our new product'\" --category translation --budget 100 --estimated-seconds 180\n\nGet a human opinion: \"Ask a real person which logo looks more professional\" → create --title \"Logo comparison\" --description \"Which logo looks more professional? A or B? Explain why in 2 sentences.\" --category survey --budget 25 --estimated-seconds 60\n\nCheck AI output: \"Have a human verify this AI-generated product description\" → create --title \"QA check on AI text\" --description \"Does this sound natural and accurate? Flag any issues: [paste text]\" --category other --budget 30 --estimated-seconds 90\n\nError Handling\nHTTP Code\tMeaning\tFix\n401\tInvalid API key\tCheck x-api-key in config.json\n400\tMissing fields or invalid category\tCheck required params\n402\tInsufficient VAE balance\tTop up via @LoopumanBot\n404\tTask not found\tVerify task ID\n429\tRate limit exceeded\tWait and retry\nLinks\nWebsite: https://loopuman.com\nTelegram Bot: https://t.me/LoopumanBot\nERC-8004 Agent: https://www.8004scan.io/agents/celo/17\nMCP: https://api.loopuman.com/.well-known/mcp.json\nA2A: https://api.loopuman.com/.well-known/agent-card.json\n\n⚠️ Budget Safety: Tasks are paid to workers upon completion. Start with small budgets (25-50 VAE) when testing. Loopuman charges 20% commission on top of the budget you set." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/seesayearn-boop/loopuman", "publisherUrl": "https://clawhub.ai/seesayearn-boop/loopuman", "owner": "seesayearn-boop", "version": "0.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/loopuman", "downloadUrl": "https://openagent3.xyz/downloads/loopuman", "agentUrl": "https://openagent3.xyz/skills/loopuman/agent", "manifestUrl": "https://openagent3.xyz/skills/loopuman/agent.json", "briefUrl": "https://openagent3.xyz/skills/loopuman/agent.md" } }