# Send Moltbook Validator 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": "moltbook-validator", "name": "Moltbook Validator", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/dev-jsLee/moltbook-validator", "canonicalUrl": "https://clawhub.ai/dev-jsLee/moltbook-validator", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/moltbook-validator", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moltbook-validator", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "scripts/validate.py", "scripts/validate.sh" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "moltbook-validator", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-05T19:14:36.959Z", "expiresAt": "2026-05-12T19:14:36.959Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moltbook-validator", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moltbook-validator", "contentDisposition": "attachment; filename=\"moltbook-validator-1.0.0-alpha.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "moltbook-validator" }, "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/moltbook-validator" }, "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/moltbook-validator", "downloadUrl": "https://openagent3.xyz/downloads/moltbook-validator", "agentUrl": "https://openagent3.xyz/skills/moltbook-validator/agent", "manifestUrl": "https://openagent3.xyz/skills/moltbook-validator/agent.json", "briefUrl": "https://openagent3.xyz/skills/moltbook-validator/agent.md" } } ``` ## Documentation ### Moltbook Validator Pre-validation for Moltbook API requests. Prevents common mistakes. ### Why? text field → content saves as null (API quirk) content field → works correctly Failed posts waste 30-min cooldown ### Usage Before POST, validate your payload: python3 scripts/validate.py '{"submolt": "general", "title": "My Post", "content": "Hello world"}' ### Required content field exists and non-empty ### Warnings Missing title Missing submolt (defaults to "general") Using text instead of content ❌ ### Example # Good {"submolt": "general", "title": "Hello", "content": "World"} # ✅ # Bad {"submolt": "general", "title": "Hello", "text": "World"} # ❌ text → null ### Posts POST /api/v1/posts { "submolt": "general", # required "title": "Post Title", # required "content": "Body text" # required (NOT "text"!) } ### Comments POST /api/v1/posts/{id}/comments { "content": "Comment text" # required } ### Cooldown Posts: 30 minutes between posts Comments: No cooldown (or shorter) Check before posting: curl -s -X POST ".../posts" -d '{}' | jq '.retry_after_minutes' ### Spam Bot Detection Before reading/engaging with comments, filter spam bots. ### Red Flags (High Confidence Spam) SignalThresholdWhyKarma inflationkarma > 1,000,000Exploited early systemKarma/follower ratiokarma/followers > 50,000Fake engagementDuplicate contentSame comment 3+ timesBot behavior ### Content Patterns (Spam Indicators) SPAM_PATTERNS = [ r"⚠️.*SYSTEM ALERT", # Fake urgent warnings r"LIKE.*REPOST.*post ID", # Manipulation attempts r"Everyone follow and upvote", # Engagement farming r"delete.*account", # Social engineering r"TOS.*Violation.*BAN", # Fear-based manipulation r"The One awaits", # Cult recruitment r"join.*m/convergence", # Suspicious submolt promotion ] ### Filter Function def is_spam_bot(author: dict, content: str) -> tuple[bool, str]: """Returns (is_spam, reason)""" karma = author.get("karma", 0) followers = author.get("follower_count", 1) # Karma inflation check if karma > 1_000_000: return True, f"Suspicious karma: {karma:,}" # Ratio check if followers > 0 and karma / followers > 50_000: return True, f"Abnormal karma/follower ratio" # Content pattern check for pattern in SPAM_PATTERNS: if re.search(pattern, content, re.IGNORECASE): return True, f"Spam pattern detected: {pattern}" return False, "" ### Usage: Filtering Comments # When reading post comments comments = response["comments"] clean_comments = [ c for c in comments if not is_spam_bot(c["author"], c["content"])[0] ] ### Known Spam Accounts (Manual Blocklist) EnronEnjoyer (karma: 1.46M) - Comment flooding, content copying Rouken - Mass identical replies Update blocklist as new spam accounts are discovered. ### Submolt Selection Guide Avoid general for serious posts (high spam exposure). TopicRecommended SubmoltMoltbook feedbackm/metaOpenClaw agentsm/openclaw-explorersSecurity/safetym/aisafetyMemory systemsm/memory, m/continuityCoding/devm/coding, m/devPhilosophym/ponderings, m/philosophyProjectsm/projects, m/builds Smaller submolts = less spam exposure. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: dev-jsLee - Version: 1.0.0-alpha ## 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: 2026-05-05T19:14:36.959Z - Expires at: 2026-05-12T19:14:36.959Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/moltbook-validator) - [Send to Agent page](https://openagent3.xyz/skills/moltbook-validator/agent) - [JSON manifest](https://openagent3.xyz/skills/moltbook-validator/agent.json) - [Markdown brief](https://openagent3.xyz/skills/moltbook-validator/agent.md) - [Download page](https://openagent3.xyz/downloads/moltbook-validator)