Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
Myosin Hivemind Knowledge Retrieval
Search Hivemind's curated Web3 marketing knowledge base (RAG) for practitioner insights, frameworks, playbooks, and case studies. Use this skill when: (1) an...
skill openclawclawhub Free
Search Hivemind's curated Web3 marketing knowledge base (RAG) for practitioner insights, frameworks, playbooks, and case studies. Use this skill when: (1) an...
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
- hivemind-search.mjs, SKILL.md
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
- 1.0.1
Provenance
- Publisher
- divine-comedian
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Hivemind Knowledge API
Search Hivemind's curated knowledge base of Web3 marketing intelligence โ practitioner insights, frameworks, playbooks, and case studies from 100+ operators in the Myosin network.
When to Use This Skill
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.
Trigger Conditions
Use this skill when the conversation involves ANY of: Strategy questions โ "How should I launch my token?", "What's a good GTM for DeFi?" Framework requests โ "What framework should I use for community building?" Tactical advice โ "How do I grow on CT?", "Best Discord strategies?" Audit/analysis โ Evaluating a project's marketing approach Content creation โ Writing posts, threads, or analysis grounded in real knowledge Competitive research โ Understanding what works in specific verticals Counterarguments โ When you need evidence to challenge a founder's assumptions Deep dives โ Any topic where surface-level AI knowledge isn't enough
When NOT to Use
Simple factual questions ("What is DeFi?") Casual conversation or greetings Questions unrelated to marketing/growth/Web3 strategy When you already retrieved relevant knowledge in this session
CLI Tool: hivemind-search.mjs
The preferred way to query the knowledge base. Located alongside this skill file.
Authentication
The script automatically resolves credentials in this order: Shell environment variables โ set by the runtime or exported in your shell ~/.openclaw/.env โ dotenv file in the OpenClaw config directory ~/.openclaw/openclaw.json โ env object โ inline env config in the OpenClaw JSON config Three variables are required: HIVEMIND_API_URL, HIVEMIND_API_KEY, HIVEMIND_VERCEL_BYPASS. API keys are issued at the discretion of Myosin. To request access, email product@myosin.xyz.
Quick Start
node hivemind-search.mjs -q "token launch marketing strategies"
Usage
hivemind-search --query <text> [options] Options: -q, --query <text> Search query (required) -p, --persona <id> Persona (see below) -t, --threshold <0-1> Relevance threshold (default: 0.4) -m, --max <1-25> Max results (default: 10) --intent Enable intent filtering --objective Enable objective filtering --no-rerank Disable LLM reranking --no-boost Disable metadata boosting --raw Output raw JSON response -h, --help Show help
Personas
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
Strategy Questions
When a founder asks about strategy, positioning, or narrative: node hivemind-search.mjs \ -q "narrative positioning for DeFi protocol launch" \ -p genius-strategist \ -m 12 \ --objective
Tactical / Execution Questions
When someone needs specific how-to guidance: node hivemind-search.mjs \ -q "Discord community launch first 30 days playbook" \ -p gtm-architect \ -m 10 \ --intent
Content Creation
When drafting posts, threads, or marketing copy: node hivemind-search.mjs \ -q "bear market marketing tactics that build long-term community" \ -p ghostwriter \ -t 0.3 \ -m 8
Broad Research
When exploring a topic or doing competitive analysis: node hivemind-search.mjs \ -q "KOL influencer strategy crypto" \ -t 0.3 \ -m 15
Raw JSON Output
When you need the full API response for further processing: node hivemind-search.mjs \ -q "token launch strategies" \ -p genius-strategist \ --raw
Response Format
The CLI outputs a human-readable summary by default. Each result includes: --- [1] Title (relevance%) --- Author: ... Meta: doc_type, objective, industry, channels Chunk content... With --raw, the full JSON response is returned: { "success": true, "data": { "chunks": [ { "title": "Token Launch Playbook", "author": "Marketing Team", "content": "Full chunk content...", "objective": "TGE (Token Generation Event)", "doc_type": "playbook", "audience": ["retail", "developers"], "geography": ["global"], "industry": ["defi"], "marketing_verticals": ["growth", "content"], "channels": ["twitter", "discord"], "score": 0.87, "relevance": "87%" } ], "total_results": 5, "query": "your search query", "metrics": { "searchTime": 234, "relevanceScore": 0.82 } } }
How to Use Results
Read the chunks โ each contains practitioner knowledge relevant to the query Note the metadata โ doc_type, objective, channels, and industry give context Synthesize, don't regurgitate โ combine multiple chunks into a coherent, opinionated response Cite the source โ when appropriate, mention insights come from "practitioner intelligence from the Hivemind network" Challenge with evidence โ use retrieved knowledge to push back on weak strategies
Error Handling
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 Rate limit: 30 requests/minute.
Guidelines
Search before advising. If a founder asks a substantive marketing question, search first. Multiple queries are fine. If the topic is broad, run 2-3 searches with different angles. Low threshold for broad topics. Use -t 0.3 when exploring. Use -t 0.5 or higher when you need precision. Pick the right persona. Strategy = genius-strategist. Execution = gtm-architect. Content = ghostwriter. Unsure = general-assistant. Don't dump raw results. Synthesize knowledge into your own voice and framing. Graceful degradation. If the API is down or returns no results, fall back to your training โ but note that you couldn't access the knowledge base.
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
1 Docs1 Scripts
- SKILL.md
- hivemind-search.mjs