Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Content Creation
Loopuman
Route tasks needing real human judgment, local knowledge, or cultural insight to verified workers paid via cUSD on Celo, for verification, translation, moder...
skill openclawclawhub Free
Route tasks needing real human judgment, local knowledge, or cultural insight to verified workers paid via cUSD on Celo, for verification, translation, moder...
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, references/api-reference.md, scripts/loopuman.sh
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- 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.
New install
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
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.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 0.1.0
Provenance
- Publisher
- seesayearn-boop
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Loopuman โ The Human Layer for AI
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 โ workers operate via Telegram and WhatsApp.
When to Use This Skill
Use Loopuman when the task requires real human judgment, perception, or local knowledge that AI cannot reliably provide: Verification โ "Is this business address real?" "Does this photo match this listing?" Translation โ Nuanced, culturally-aware translation (not just word-for-word) Content moderation โ "Is this image appropriate?" "Does this review violate guidelines?" Image labeling โ "What objects are in this photo?" "Rate this image quality 1-10" Local knowledge โ "What's the current price of tomatoes in Nairobi?" Surveys & opinions โ "Which logo design is better?" "Rate this product description" Data collection โ "Find the phone number for this restaurant" Quality assurance โ "Does this AI-generated text sound natural?" Do NOT use for tasks AI can handle: math, code generation, summarization, web search, file operations.
Setup
Create the config file with your Loopuman API key: mkdir -p ~/.openclaw/skills/loopuman cat > ~/.openclaw/skills/loopuman/config.json << 'EOF' { "apiKey": "YOUR_API_KEY", "apiUrl": "https://api.loopuman.com" } EOF Get your API key (one command, no auth needed): curl -X POST https://api.loopuman.com/api/v1/register \ -H "Content-Type: application/json" \ -d '{"email": "you@example.com", "company_name": "Your Name", "promo_code": "LOBSTER"}' This returns your api_key (starts with lpm_). Save it immediately โ it cannot be retrieved later. Promo codes for free credits: CLAW500 โ 500 VAE ($5.00) for first 10 OpenClaw testers LOBSTER โ 100 VAE ($1.00) for early access (50 spots) No code โ 25 VAE ($0.25) welcome bonus To add more funds, message @LoopumanBot on Telegram and link your account.
API Authentication
All requests use the x-api-key header: x-api-key: YOUR_API_KEY
Creating a Task
scripts/loopuman.sh create \ --title "Verify business address" \ --description "Check if this address exists on Google Maps: 123 Main St, Nairobi, Kenya. Reply with YES/NO and a screenshot." \ --category other \ --budget 50 \ --estimated-seconds 120 Parameters: --title โ Short task title (required) --description โ Detailed instructions for the human worker (required, be specific!) --category โ 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. --budget โ Payment in VAE tokens. 100 VAE = $1 USD. (default: 100) --estimated-seconds โ Expected time for worker to complete (required for fair pay calculation, default: 120) --max-workers โ Number of workers (default: 1, max: 100) --priority โ normal or high (high notifies workers immediately) --webhook โ URL for push notifications on completion Category minimum budgets: survey, labeling, ai_training, micro: 25 VAE ($0.25) research, content_creation: 75 VAE ($0.75) writing, translation: 100 VAE ($1.00) Fair 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. Writing good task descriptions: Be specific about what you need ("Reply YES or NO" not "verify this") Include all context the worker needs Specify the expected format of the response Set clear success criteria
Checking Task Status + Getting Results
scripts/loopuman.sh status --task-id <TASK_ID> Returns full task details including: status: active, completed, expired, cancelled progress: count of approved, pending_review, in_progress submissions submissions: array of approved worker results with content pending_submissions: results awaiting your approval
Polling for Completion
For tasks that need a result before continuing: # Poll every 30 seconds, timeout after 10 minutes scripts/loopuman.sh wait --task-id <TASK_ID> --interval 30 --timeout 600 Returns the result as soon as an approved submission is available.
Listing Tasks
scripts/loopuman.sh list
Cancelling a Task
scripts/loopuman.sh cancel --task-id <TASK_ID> Refunds your balance if no workers have started.
Task Types and Pricing
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
Examples
Verify an address: "Create a Loopuman task to verify if '456 Kenyatta Ave, Nairobi' is a real business address" โ 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 Translate with cultural context: "Use Loopuman to translate 'We're excited to launch' into Swahili naturally" โ 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 Get a human opinion: "Ask a real person which logo looks more professional" โ 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 Check AI output: "Have a human verify this AI-generated product description" โ 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
Error Handling
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
Links
Website: https://loopuman.com Telegram Bot: https://t.me/LoopumanBot ERC-8004 Agent: https://www.8004scan.io/agents/celo/17 MCP: https://api.loopuman.com/.well-known/mcp.json A2A: https://api.loopuman.com/.well-known/agent-card.json โ ๏ธ 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.
Category context
Writing, remixing, publishing, visual generation, and marketing content production.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
2 Docs1 Scripts
- SKILL.md
- references/api-reference.md
- scripts/loopuman.sh