{ "schemaVersion": "1.0", "item": { "slug": "myosin-hivemind", "name": "Myosin Hivemind Knowledge Retrieval", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/divine-comedian/myosin-hivemind", "canonicalUrl": "https://clawhub.ai/divine-comedian/myosin-hivemind", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/myosin-hivemind", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=myosin-hivemind", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "hivemind-search.mjs", "SKILL.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/myosin-hivemind" }, "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/myosin-hivemind", "agentPageUrl": "https://openagent3.xyz/skills/myosin-hivemind/agent", "manifestUrl": "https://openagent3.xyz/skills/myosin-hivemind/agent.json", "briefUrl": "https://openagent3.xyz/skills/myosin-hivemind/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": "Hivemind Knowledge API", "body": "Search Hivemind's curated knowledge base of Web3 marketing intelligence — practitioner insights, frameworks, playbooks, and case studies from 100+ operators in the Myosin network." }, { "title": "When to Use This Skill", "body": "ALWAYS search the knowledge base before giving marketing advice. This is what differentiates you from generic AI. Your advice should be grounded in practitioner experience." }, { "title": "Trigger Conditions", "body": "Use this skill when the conversation involves ANY of:\n\nStrategy questions — \"How should I launch my token?\", \"What's a good GTM for DeFi?\"\nFramework requests — \"What framework should I use for community building?\"\nTactical advice — \"How do I grow on CT?\", \"Best Discord strategies?\"\nAudit/analysis — Evaluating a project's marketing approach\nContent creation — Writing posts, threads, or analysis grounded in real knowledge\nCompetitive research — Understanding what works in specific verticals\nCounterarguments — When you need evidence to challenge a founder's assumptions\nDeep dives — Any topic where surface-level AI knowledge isn't enough" }, { "title": "When NOT to Use", "body": "Simple factual questions (\"What is DeFi?\")\nCasual conversation or greetings\nQuestions unrelated to marketing/growth/Web3 strategy\nWhen you already retrieved relevant knowledge in this session" }, { "title": "CLI Tool: hivemind-search.mjs", "body": "The preferred way to query the knowledge base. Located alongside this skill file." }, { "title": "Authentication", "body": "The script automatically resolves credentials in this order:\n\nShell environment variables — set by the runtime or exported in your shell\n~/.openclaw/.env — dotenv file in the OpenClaw config directory\n~/.openclaw/openclaw.json → env object — inline env config in the OpenClaw JSON config\n\nThree variables are required: HIVEMIND_API_URL, HIVEMIND_API_KEY, HIVEMIND_VERCEL_BYPASS.\n\nAPI keys are issued at the discretion of Myosin. To request access, email product@myosin.xyz." }, { "title": "Quick Start", "body": "node hivemind-search.mjs -q \"token launch marketing strategies\"" }, { "title": "Usage", "body": "hivemind-search --query [options]\n\nOptions:\n -q, --query Search query (required)\n -p, --persona Persona (see below)\n -t, --threshold <0-1> Relevance threshold (default: 0.4)\n -m, --max <1-25> Max results (default: 10)\n --intent Enable intent filtering\n --objective Enable objective filtering\n --no-rerank Disable LLM reranking\n --no-boost Disable metadata boosting\n --raw Output raw JSON response\n -h, --help Show help" }, { "title": "Personas", "body": "Flag valueUse Whengenius-strategistStrategic thinking, positioning, narrative design, high-level planninggtm-architectTactical execution, implementation plans, channel strategies, launch sequencesghostwriterContent creation, copywriting, messaging, narrative framinggeneral-assistantGeneral queries that don't fit a specific persona" }, { "title": "Strategy Questions", "body": "When a founder asks about strategy, positioning, or narrative:\n\nnode hivemind-search.mjs \\\n -q \"narrative positioning for DeFi protocol launch\" \\\n -p genius-strategist \\\n -m 12 \\\n --objective" }, { "title": "Tactical / Execution Questions", "body": "When someone needs specific how-to guidance:\n\nnode hivemind-search.mjs \\\n -q \"Discord community launch first 30 days playbook\" \\\n -p gtm-architect \\\n -m 10 \\\n --intent" }, { "title": "Content Creation", "body": "When drafting posts, threads, or marketing copy:\n\nnode hivemind-search.mjs \\\n -q \"bear market marketing tactics that build long-term community\" \\\n -p ghostwriter \\\n -t 0.3 \\\n -m 8" }, { "title": "Broad Research", "body": "When exploring a topic or doing competitive analysis:\n\nnode hivemind-search.mjs \\\n -q \"KOL influencer strategy crypto\" \\\n -t 0.3 \\\n -m 15" }, { "title": "Raw JSON Output", "body": "When you need the full API response for further processing:\n\nnode hivemind-search.mjs \\\n -q \"token launch strategies\" \\\n -p genius-strategist \\\n --raw" }, { "title": "Response Format", "body": "The CLI outputs a human-readable summary by default. Each result includes:\n\n--- [1] Title (relevance%) ---\nAuthor: ...\nMeta: doc_type, objective, industry, channels\n\nChunk content...\n\nWith --raw, the full JSON response is returned:\n\n{\n \"success\": true,\n \"data\": {\n \"chunks\": [\n {\n \"title\": \"Token Launch Playbook\",\n \"author\": \"Marketing Team\",\n \"content\": \"Full chunk content...\",\n \"objective\": \"TGE (Token Generation Event)\",\n \"doc_type\": \"playbook\",\n \"audience\": [\"retail\", \"developers\"],\n \"geography\": [\"global\"],\n \"industry\": [\"defi\"],\n \"marketing_verticals\": [\"growth\", \"content\"],\n \"channels\": [\"twitter\", \"discord\"],\n \"score\": 0.87,\n \"relevance\": \"87%\"\n }\n ],\n \"total_results\": 5,\n \"query\": \"your search query\",\n \"metrics\": {\n \"searchTime\": 234,\n \"relevanceScore\": 0.82\n }\n }\n}" }, { "title": "How to Use Results", "body": "Read the chunks — each contains practitioner knowledge relevant to the query\nNote the metadata — doc_type, objective, channels, and industry give context\nSynthesize, don't regurgitate — combine multiple chunks into a coherent, opinionated response\nCite the source — when appropriate, mention insights come from \"practitioner intelligence from the Hivemind network\"\nChallenge with evidence — use retrieved knowledge to push back on weak strategies" }, { "title": "Error Handling", "body": "StatusMeaningAction400Invalid parametersCheck the details array for which fields failed validation401Bad API keyVerify HIVEMIND_API_KEY is set correctly403Vercel protection blockedVerify HIVEMIND_VERCEL_BYPASS is set correctly429Rate limitedWait the Retry-After seconds before retrying500Server errorRetry once; if it persists, proceed without knowledge base\n\nRate limit: 30 requests/minute." }, { "title": "Guidelines", "body": "Search before advising. If a founder asks a substantive marketing question, search first.\nMultiple queries are fine. If the topic is broad, run 2-3 searches with different angles.\nLow threshold for broad topics. Use -t 0.3 when exploring. Use -t 0.5 or higher when you need precision.\nPick the right persona. Strategy = genius-strategist. Execution = gtm-architect. Content = ghostwriter. Unsure = general-assistant.\nDon't dump raw results. Synthesize knowledge into your own voice and framing.\nGraceful degradation. If the API is down or returns no results, fall back to your training — but note that you couldn't access the knowledge base." } ], "body": "Hivemind Knowledge API\n\nSearch Hivemind's curated knowledge base of Web3 marketing intelligence — practitioner insights, frameworks, playbooks, and case studies from 100+ operators in the Myosin network.\n\nWhen to Use This Skill\n\nALWAYS search the knowledge base before giving marketing advice. This is what differentiates you from generic AI. Your advice should be grounded in practitioner experience.\n\nTrigger Conditions\n\nUse this skill when the conversation involves ANY of:\n\nStrategy questions — \"How should I launch my token?\", \"What's a good GTM for DeFi?\"\nFramework requests — \"What framework should I use for community building?\"\nTactical advice — \"How do I grow on CT?\", \"Best Discord strategies?\"\nAudit/analysis — Evaluating a project's marketing approach\nContent creation — Writing posts, threads, or analysis grounded in real knowledge\nCompetitive research — Understanding what works in specific verticals\nCounterarguments — When you need evidence to challenge a founder's assumptions\nDeep dives — Any topic where surface-level AI knowledge isn't enough\nWhen NOT to Use\nSimple factual questions (\"What is DeFi?\")\nCasual conversation or greetings\nQuestions unrelated to marketing/growth/Web3 strategy\nWhen you already retrieved relevant knowledge in this session\nCLI Tool: hivemind-search.mjs\n\nThe preferred way to query the knowledge base. Located alongside this skill file.\n\nAuthentication\n\nThe script automatically resolves credentials in this order:\n\nShell environment variables — set by the runtime or exported in your shell\n~/.openclaw/.env — dotenv file in the OpenClaw config directory\n~/.openclaw/openclaw.json → env object — inline env config in the OpenClaw JSON config\n\nThree variables are required: HIVEMIND_API_URL, HIVEMIND_API_KEY, HIVEMIND_VERCEL_BYPASS.\n\nAPI keys are issued at the discretion of Myosin. To request access, email product@myosin.xyz.\n\nQuick Start\nnode hivemind-search.mjs -q \"token launch marketing strategies\"\n\nUsage\nhivemind-search --query [options]\n\nOptions:\n -q, --query Search query (required)\n -p, --persona Persona (see below)\n -t, --threshold <0-1> Relevance threshold (default: 0.4)\n -m, --max <1-25> Max results (default: 10)\n --intent Enable intent filtering\n --objective Enable objective filtering\n --no-rerank Disable LLM reranking\n --no-boost Disable metadata boosting\n --raw Output raw JSON response\n -h, --help Show help\n\nPersonas\nFlag value\tUse When\ngenius-strategist\tStrategic thinking, positioning, narrative design, high-level planning\ngtm-architect\tTactical execution, implementation plans, channel strategies, launch sequences\nghostwriter\tContent creation, copywriting, messaging, narrative framing\ngeneral-assistant\tGeneral queries that don't fit a specific persona\nRecommended Search Patterns\nStrategy Questions\n\nWhen a founder asks about strategy, positioning, or narrative:\n\nnode hivemind-search.mjs \\\n -q \"narrative positioning for DeFi protocol launch\" \\\n -p genius-strategist \\\n -m 12 \\\n --objective\n\nTactical / Execution Questions\n\nWhen someone needs specific how-to guidance:\n\nnode hivemind-search.mjs \\\n -q \"Discord community launch first 30 days playbook\" \\\n -p gtm-architect \\\n -m 10 \\\n --intent\n\nContent Creation\n\nWhen drafting posts, threads, or marketing copy:\n\nnode hivemind-search.mjs \\\n -q \"bear market marketing tactics that build long-term community\" \\\n -p ghostwriter \\\n -t 0.3 \\\n -m 8\n\nBroad Research\n\nWhen exploring a topic or doing competitive analysis:\n\nnode hivemind-search.mjs \\\n -q \"KOL influencer strategy crypto\" \\\n -t 0.3 \\\n -m 15\n\nRaw JSON Output\n\nWhen you need the full API response for further processing:\n\nnode hivemind-search.mjs \\\n -q \"token launch strategies\" \\\n -p genius-strategist \\\n --raw\n\nResponse Format\n\nThe CLI outputs a human-readable summary by default. Each result includes:\n\n--- [1] Title (relevance%) ---\nAuthor: ...\nMeta: doc_type, objective, industry, channels\n\nChunk content...\n\n\nWith --raw, the full JSON response is returned:\n\n{\n \"success\": true,\n \"data\": {\n \"chunks\": [\n {\n \"title\": \"Token Launch Playbook\",\n \"author\": \"Marketing Team\",\n \"content\": \"Full chunk content...\",\n \"objective\": \"TGE (Token Generation Event)\",\n \"doc_type\": \"playbook\",\n \"audience\": [\"retail\", \"developers\"],\n \"geography\": [\"global\"],\n \"industry\": [\"defi\"],\n \"marketing_verticals\": [\"growth\", \"content\"],\n \"channels\": [\"twitter\", \"discord\"],\n \"score\": 0.87,\n \"relevance\": \"87%\"\n }\n ],\n \"total_results\": 5,\n \"query\": \"your search query\",\n \"metrics\": {\n \"searchTime\": 234,\n \"relevanceScore\": 0.82\n }\n }\n}\n\nHow to Use Results\nRead the chunks — each contains practitioner knowledge relevant to the query\nNote the metadata — doc_type, objective, channels, and industry give context\nSynthesize, don't regurgitate — combine multiple chunks into a coherent, opinionated response\nCite the source — when appropriate, mention insights come from \"practitioner intelligence from the Hivemind network\"\nChallenge with evidence — use retrieved knowledge to push back on weak strategies\nError Handling\nStatus\tMeaning\tAction\n400\tInvalid parameters\tCheck the details array for which fields failed validation\n401\tBad API key\tVerify HIVEMIND_API_KEY is set correctly\n403\tVercel protection blocked\tVerify HIVEMIND_VERCEL_BYPASS is set correctly\n429\tRate limited\tWait the Retry-After seconds before retrying\n500\tServer error\tRetry once; if it persists, proceed without knowledge base\n\nRate limit: 30 requests/minute.\n\nGuidelines\nSearch before advising. If a founder asks a substantive marketing question, search first.\nMultiple queries are fine. If the topic is broad, run 2-3 searches with different angles.\nLow threshold for broad topics. Use -t 0.3 when exploring. Use -t 0.5 or higher when you need precision.\nPick the right persona. Strategy = genius-strategist. Execution = gtm-architect. Content = ghostwriter. Unsure = general-assistant.\nDon't dump raw results. Synthesize knowledge into your own voice and framing.\nGraceful degradation. If the API is down or returns no results, fall back to your training — but note that you couldn't access the knowledge base." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/divine-comedian/myosin-hivemind", "publisherUrl": "https://clawhub.ai/divine-comedian/myosin-hivemind", "owner": "divine-comedian", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/myosin-hivemind", "downloadUrl": "https://openagent3.xyz/downloads/myosin-hivemind", "agentUrl": "https://openagent3.xyz/skills/myosin-hivemind/agent", "manifestUrl": "https://openagent3.xyz/skills/myosin-hivemind/agent.json", "briefUrl": "https://openagent3.xyz/skills/myosin-hivemind/agent.md" } }