{ "schemaVersion": "1.0", "item": { "slug": "dual-brain", "name": "Dual-Brain", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/Dannydvm/dual-brain", "canonicalUrl": "https://clawhub.ai/Dannydvm/dual-brain", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/dual-brain", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=dual-brain", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "BUILD-SUMMARY.md", "CHANGELOG.md", "QUICKSTART.md", "README.md", "SKILL.md", "bin/dual-brain.js" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/dual-brain" }, "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/dual-brain", "agentPageUrl": "https://openagent3.xyz/skills/dual-brain/agent", "manifestUrl": "https://openagent3.xyz/skills/dual-brain/agent.json", "briefUrl": "https://openagent3.xyz/skills/dual-brain/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Dual-Brain Skill", "body": "What it does: Provides cognitive diversity by automatically generating perspectives from a secondary LLM (different from your primary model) for every user message." }, { "title": "For Agents", "body": "Before responding to any user message, check for a dual-brain perspective:\n\ncat ~/.dual-brain/perspectives/{your-agent-id}-latest.md\n\nIf the file exists and contains a recent perspective (check timestamp in comment), consider it alongside your own reasoning. The perspective may highlight:\n\nAngles you might miss\nAlternative approaches\nImportant things to verify\n\nIntegration:\n\nPerspectives are generated automatically by a background daemon\nNo manual action required on your part\nSimply read the file before forming your response\nSynthesize both viewpoints (yours + the secondary LLM's)\n\nExample workflow:\n\nUser sends message\nDaemon intercepts, sends to secondary LLM (e.g., Kimi, GPT-4, Llama)\nSecondary LLM generates 2-3 sentence perspective\nWritten to ~/.dual-brain/perspectives/{agent-id}-latest.md\nYou (primary agent) read it before responding\nYou synthesize both perspectives into your answer" }, { "title": "For Humans", "body": "Setup:\n\nnpm install -g openclaw-dual-brain\ndual-brain setup # Interactive configuration\ndual-brain start # Start daemon\n\nProviders:\n\nollama - Local models (zero cost, requires Ollama)\nmoonshot - Kimi/Moonshot API (Chinese LLM, fast)\nopenai - GPT-4o, GPT-4-turbo, etc.\ngroq - Fast inference with Llama models\n\nCommands:\n\ndual-brain setup - Configure provider, model, API key\ndual-brain start - Run daemon (foreground)\ndual-brain stop - Stop daemon\ndual-brain status - Check running status\ndual-brain logs - View recent activity\ndual-brain install-daemon - Install as system service\n\nConfig location: ~/.dual-brain/config.json\n\nPerspectives location: ~/.dual-brain/perspectives/" }, { "title": "Architecture", "body": "User Message → OpenClaw Session (JSONL)\n ↓\n Dual-Brain Daemon (polling)\n ↓\n Secondary LLM Provider\n (ollama/moonshot/openai/groq)\n ↓\n Perspective Generated (2-3 sentences)\n ↓\n ~/.dual-brain/perspectives/{agent}-latest.md\n ↓\n Primary Agent reads & synthesizes\n ↓\n Response to User" }, { "title": "Benefits", "body": "Cognitive diversity - Two AI models = broader perspective\nBias mitigation - Different training data/approaches\nQuality assurance - Second opinion catches issues\nZero agent overhead - Runs in background, <1s latency\nProvider flexibility - Choose cost vs. quality tradeoff" }, { "title": "Optional: Engram Integration", "body": "If Engram (semantic memory) is running on localhost:3400, perspectives are also stored as memories for long-term recall.\n\nSource: https://github.com/yourusername/openclaw-dual-brain" } ], "body": "Dual-Brain Skill\n\nWhat it does: Provides cognitive diversity by automatically generating perspectives from a secondary LLM (different from your primary model) for every user message.\n\nFor Agents\n\nBefore responding to any user message, check for a dual-brain perspective:\n\ncat ~/.dual-brain/perspectives/{your-agent-id}-latest.md\n\n\nIf the file exists and contains a recent perspective (check timestamp in comment), consider it alongside your own reasoning. The perspective may highlight:\n\nAngles you might miss\nAlternative approaches\nImportant things to verify\n\nIntegration:\n\nPerspectives are generated automatically by a background daemon\nNo manual action required on your part\nSimply read the file before forming your response\nSynthesize both viewpoints (yours + the secondary LLM's)\n\nExample workflow:\n\nUser sends message\nDaemon intercepts, sends to secondary LLM (e.g., Kimi, GPT-4, Llama)\nSecondary LLM generates 2-3 sentence perspective\nWritten to ~/.dual-brain/perspectives/{agent-id}-latest.md\nYou (primary agent) read it before responding\nYou synthesize both perspectives into your answer\nFor Humans\n\nSetup:\n\nnpm install -g openclaw-dual-brain\ndual-brain setup # Interactive configuration\ndual-brain start # Start daemon\n\n\nProviders:\n\nollama - Local models (zero cost, requires Ollama)\nmoonshot - Kimi/Moonshot API (Chinese LLM, fast)\nopenai - GPT-4o, GPT-4-turbo, etc.\ngroq - Fast inference with Llama models\n\nCommands:\n\ndual-brain setup - Configure provider, model, API key\ndual-brain start - Run daemon (foreground)\ndual-brain stop - Stop daemon\ndual-brain status - Check running status\ndual-brain logs - View recent activity\ndual-brain install-daemon - Install as system service\n\nConfig location: ~/.dual-brain/config.json\n\nPerspectives location: ~/.dual-brain/perspectives/\n\nArchitecture\nUser Message → OpenClaw Session (JSONL)\n ↓\n Dual-Brain Daemon (polling)\n ↓\n Secondary LLM Provider\n (ollama/moonshot/openai/groq)\n ↓\n Perspective Generated (2-3 sentences)\n ↓\n ~/.dual-brain/perspectives/{agent}-latest.md\n ↓\n Primary Agent reads & synthesizes\n ↓\n Response to User\n\nBenefits\nCognitive diversity - Two AI models = broader perspective\nBias mitigation - Different training data/approaches\nQuality assurance - Second opinion catches issues\nZero agent overhead - Runs in background, <1s latency\nProvider flexibility - Choose cost vs. quality tradeoff\nOptional: Engram Integration\n\nIf Engram (semantic memory) is running on localhost:3400, perspectives are also stored as memories for long-term recall.\n\nSource: https://github.com/yourusername/openclaw-dual-brain" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Dannydvm/dual-brain", "publisherUrl": "https://clawhub.ai/Dannydvm/dual-brain", "owner": "Dannydvm", "version": "0.1.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/dual-brain", "downloadUrl": "https://openagent3.xyz/downloads/dual-brain", "agentUrl": "https://openagent3.xyz/skills/dual-brain/agent", "manifestUrl": "https://openagent3.xyz/skills/dual-brain/agent.json", "briefUrl": "https://openagent3.xyz/skills/dual-brain/agent.md" } }