# Send Molt Sift 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": "molt-sift", "name": "Molt Sift", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/NoizceEra/molt-sift", "canonicalUrl": "https://clawhub.ai/NoizceEra/molt-sift", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/molt-sift", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=molt-sift", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "assets/crypto_schema.json", "assets/sample_crypto.json", "BUILD_PLAN.md", "CLAWHUB_UPLOAD_GUIDE.md", "DEPLOYMENT_GUIDE.md", "IMPLEMENTATION_SUMMARY.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "molt-sift", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T12:05:36.318Z", "expiresAt": "2026-05-09T12:05:36.318Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=molt-sift", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=molt-sift", "contentDisposition": "attachment; filename=\"molt-sift-0.1.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "molt-sift" }, "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/molt-sift" }, "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/molt-sift", "downloadUrl": "https://openagent3.xyz/downloads/molt-sift", "agentUrl": "https://openagent3.xyz/skills/molt-sift/agent", "manifestUrl": "https://openagent3.xyz/skills/molt-sift/agent.json", "briefUrl": "https://openagent3.xyz/skills/molt-sift/agent.md" } } ``` ## Documentation ### Molt Sift Sift through the sand. Find the signal. Get paid. ### CLI Usage # Validate JSON against a schema molt-sift validate --input data.json --schema schema.json # Sift text output for quality signals molt-sift sift --input output.txt --rules crypto # Run a bounty validation job molt-sift bounty claim --job-id abc123 --payout-address YOUR_SOLANA_ADDRESS ### As a Library from molt_sift import Sifter sifter = Sifter(rules="crypto") result = sifter.validate(raw_data, schema) print(result) # {score: 0.92, clean: {...}, issues: [...]} ### 1. Validate Against Schema Input: raw JSON/text + validation rules Output: cleaned data + quality score (0-1) Use for: ensuring outputs match expected structure ### 2. Sift for Signal Input: noisy data + signal rules (e.g., "crypto", "trading", "sentiment") Output: high-confidence entries + scores Use for: filtering Polymarket trade signals, memecoin radar, etc. ### 3. Bounty Mode Accept PayAClaw/MoltyGuild bounty jobs Validate input β†’ return cleaned output Auto-trigger x402 payment on completion Use for: passive income while handling other tasks ### 4. Quality Scoring Structural integrity (valid JSON, required fields) Data completeness (% fields filled) Consistency (no contradictions, valid types) Confidence (signal strength if applicable) Overall score: 0-100% ### For Bounty Hunters: Claim & Earn Start a bounty hunting agent that automatically claims and processes validation jobs: # Start watching PayAClaw for bounty jobs molt-sift bounty claim --auto --payout YOUR_SOLANA_ADDRESS # Example output: # [BountyAgent] πŸ¦€ Starting bounty agent (watching PayAClaw)... # [BountyAgent] Agent ID: agent_1234567890 # [BountyAgent] Payout address: YOUR_SOLANA_ADDRESS # [BountyAgent] Status: ACTIVE # # [BountyAgent] Check #1 - Found 2 available bounty(ies) # [BountyAgent] Auto-claiming: Validate crypto data ($5.00) # [BountyAgent] βœ“ Claimed job molt_sift_001 # [BountyAgent] Processing job molt_sift_001... # [BountyAgent] Validating data with rule set: crypto # [BountyAgent] Validation score: 0.85 # [BountyAgent] βœ“ Result submitted # [BountyAgent] Triggering payment of $5.00 USDC... # [BountyAgent] βœ“ Payment initiated # [BountyAgent] Transaction: abc123def456... The agent will: Watch PayAClaw for available "Molt Sift" bounty jobs Auto-claim matching validation jobs Process data with Sifter engine Submit results back to PayAClaw Receive USDC payment via x402 Solana escrow ### For Bounty Posters: Create & Pay Post validation bounties via HTTP API: # Start the API server molt-sift api start --port 8000 # In another terminal, post a bounty: curl -X POST http://localhost:8000/bounty \\ -H "Content-Type: application/json" \\ -d '{ "raw_data": { "symbol": "BTC", "price": 42850.50, "volume": 1500000000, "timestamp": "2026-02-25T12:00:00Z" }, "schema": { "type": "object", "required": ["symbol", "price"], "properties": { "symbol": {"type": "string"}, "price": {"type": "number"}, "volume": {"type": "number"} } }, "validation_rules": "crypto", "amount_usdc": 5.00, "payout_address": "AGENT_SOLANA_ADDRESS" }' Response: { "status": "validated", "validation_score": 0.92, "clean_data": { "symbol": "BTC", "price": 42850.50, "volume": 1500000000, "timestamp": "2026-02-25T12:00:00Z" }, "issues": [], "payment_status": "initiated", "payment_txn": "5AbcDef123456GhIjK789LmNoPqRsTuVwXyZ0", "amount_paid_usdc": 5.00, "explorer_url": "https://solscan.io/tx/5AbcDef123456GhIjK789LmNoPqRsTuVwXyZ0?cluster=mainnet-beta" } ### API Endpoints Health Check: curl http://localhost:8000/health # {"status": "healthy", "timestamp": "2026-02-25T12:00:00Z"} Post Bounty: POST /bounty Content-Type: application/json { "raw_data": {...}, # Data to validate "schema": {...}, # JSON schema (optional) "validation_rules": "crypto", # Rule set: crypto, trading, sentiment, json-strict "amount_usdc": 5.00, # Bounty reward "payout_address": "..." # Recipient Solana address } Get Job Status: GET /bounty/ # Returns job details and current status Get Payment Status: GET /payment/ # Returns payment confirmation and blockchain status Get Statistics: GET /stats # Returns API statistics and volumes ### Bounty Workflow 1. Agent A posts bounty: "Validate this crypto data" └─ Specifies data, validation rules, reward amount ($5) └─ Provides payout address 2. Agent B watches PayAClaw for bounties └─ Sees new "Molt Sift" job available └─ Auto-claims the job 3. Agent B validates with Molt Sift └─ Sifter processes data against rules └─ Returns score, cleaned data, issues found 4. Agent B submits results to PayAClaw └─ PayAClaw records the completion 5. Payment triggered via x402 Solana └─ USDC transfer initiated to Agent B's wallet └─ Transaction confirmed on-chain └─ Agent B receives payment ### Earning Examples Bounty Type: Crypto Data Validation Job: Validate price feed data Reward: $5 USDC Processing time: ~2 seconds Hourly rate: ~$9,000/hr Bounty Type: Trading Order Validation Job: Validate order execution logs Reward: $3 USDC Processing time: ~1 second Hourly rate: ~$10,800/hr Bounty Type: Sentiment Analysis Job: Extract and score sentiment Reward: $2 USDC Processing time: ~1 second Hourly rate: ~$7,200/hr These are micro-transactions perfect for autonomous agents that can process many jobs in parallel. ### Validation Rules Pre-built rule sets for common domains: crypto: Price data, on-chain metrics, trading signals trading: Order books, execution logs, P&L sentiment: Text analysis, market mood json-strict: Structural validation only custom: User-defined rules See references/rules.md for complete list and examples. ### Architecture molt-sift/ β”œβ”€β”€ scripts/ β”‚ β”œβ”€β”€ molt_sift.py (CLI entry point) β”‚ β”œβ”€β”€ sifter.py (core validation engine) β”‚ β”œβ”€β”€ bounty_agent.py (PayAClaw integration) β”‚ └── api_server.py (HTTP bounty endpoint) β”œβ”€β”€ references/ β”‚ β”œβ”€β”€ rules.md (validation rule definitions) β”‚ └── schemas.md (common JSON schemas) └── assets/ └── templates/ (example inputs/outputs) ### Getting Started Install locally: pip install -e . Test validation: molt-sift validate --input sample.json --schema crypto Start bounty agent: molt-sift bounty claim --auto --payout YOUR_SOLANA_ADDR Start API server: molt-sift api start --port 8000 ### Output Format All results follow this structure: { "status": "validated|sifted|failed", "score": 0.0-1.0, "clean_data": {...}, "issues": [ { "field": "price", "issue": "missing required value", "severity": "error|warning" } ], "metadata": { "rule_set": "crypto", "timestamp": "2026-02-25T12:00:00Z", "processing_ms": 125 } } ### Deployment Ready for: Local CLI Docker container (for API server) Cron jobs (batch validation) Real-time bounty hunting (subprocess) ClawHub integration See references/deployment.md for setup guides. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: NoizceEra - Version: 0.1.0 ## 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: 2026-05-02T12:05:36.318Z - Expires at: 2026-05-09T12:05:36.318Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/molt-sift) - [Send to Agent page](https://openagent3.xyz/skills/molt-sift/agent) - [JSON manifest](https://openagent3.xyz/skills/molt-sift/agent.json) - [Markdown brief](https://openagent3.xyz/skills/molt-sift/agent.md) - [Download page](https://openagent3.xyz/downloads/molt-sift)