{
  "schemaVersion": "1.0",
  "item": {
    "slug": "book-brain",
    "name": "BOOK BRAIN – LYGO 3-Brain Filesystem Helper",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/DeepSeekOracle/book-brain",
    "canonicalUrl": "https://clawhub.ai/DeepSeekOracle/book-brain",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/book-brain",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=book-brain",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "references/book-brain-examples.md",
      "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": "2026-04-23T16:43:11.935Z",
      "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/book-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/book-brain",
    "agentPageUrl": "https://openagent3.xyz/skills/book-brain/agent",
    "manifestUrl": "https://openagent3.xyz/skills/book-brain/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/book-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. 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": "BOOK BRAIN – LYGO 3-Brain Filesystem Helper",
        "body": "This skill is a utility/guide, not a persona.\n\nUse it when you want to:\n\nSet up or improve a Haven-style filesystem + memory structure\nTeach an agent how to use folders, indexes, and reference .txt files instead of hoarding everything in one place\nAdd advanced logging + retrieval so memories can be found later without brute-force scanning\n\nIt is built for LYGO / Eternal Haven style systems, but works for any agent that can:\n\nread/write files\ncreate folders\nappend to logs\n\nCore idea: BOOK BRAIN = treating your filesystem like a living library, not a junk drawer."
      },
      {
        "title": "1. Three-Brain Model (Conceptual Map)",
        "body": "BOOK BRAIN assumes a 3-brain structure:\n\nWorking Brain (short-term)\n\nRecent conversation, active task context, scratchpads.\nIn OpenClaw, this is the current session + small scratch files under tmp/.\n\n\n\nLibrary Brain (structured filesystem)\n\nFolders + files on disk: memory/, reference/, brainwave/, state/, etc.\nThis is where BOOK BRAIN focuses: how you name, branch, and link things.\n\n\n\nOuter Brain (external references)\n\nBrowser bookmarks, Clawdhub skills, on-chain receipts, remote docs.\nBOOK BRAIN treats these as links inside text files, not content to copy in.\n\nThe goal is to:\n\nKeep important truths close and succinct\nBranch deeper into folders when detail is needed\nUse .txt reference links instead of duplicating entire documents"
      },
      {
        "title": "2. When to Use BOOK BRAIN",
        "body": "Trigger this skill when:\n\nYou are setting up a fresh Haven (new OpenClaw workspace, new agent node)\nYour filesystem feels chaotic and you need a reset without deleting anything\nYou want to design a clean memory + reference layout before starting heavy work\nYou are planning long-term retrieval (\"I’ll need this months from now\")\n\nBOOK BRAIN is additive:\n\nDo not use it to delete or overwrite existing files by default.\nPrefer creating new folders / indexes alongside existing ones.\nWhen a folder already exists, pause and let the human choose: reuse or create a new branch (e.g., memory_v2/)."
      },
      {
        "title": "3. Recommended Base Folder Layout",
        "body": "When setting up a new Haven-like system (or auditing an existing one), BOOK BRAIN recommends the following top-level folders:\n\nmemory/ → daily notes, raw logs, timeline files\nreference/ → stable facts, protocols, guides (things that rarely change)\nbrainwave/ → platform- or domain-specific protocols (MoltX, Clawhub, LYGO, etc.)\nstate/ → machine-readable JSON/YAML state, indexes, last-run info\nlogs/ (or reuse logs/ if present) → technical logs (cron, errors, audits)\ntools/ → scripts/utilities used by the agent\ntmp/ → scratch, throwaway working files\n\nBOOK BRAIN setup rules:\n\nIf a folder already exists, do not rename or delete it.\nIf a folder is missing, it is safe to create it.\nIf the existing layout is very different, create a sub-tree (e.g., bookbrain/memory_index/) and keep old structure intact.\n\nFor concrete layout examples, see references/book-brain-examples.md in this skill."
      },
      {
        "title": "4. Memory Strategy – Deep Storage vs. Reference Stubs",
        "body": "BOOK BRAIN enforces this principle:\n\nDo not pour entire conversations or huge documents into MEMORY.md or a single file.\nInstead, store detailed content in specific files and create short reference stubs that point to them.\n\nPatterns:\n\nDaily logs\n\nFiles like memory/2026-02-10.md for raw notes and events.\nAt the top, keep a 5–10 line summary and a small list of important links:\n\nSee: reference/AGENT_ARCHITECTURE.md\nSee: memory/projects/BOOK_BRAIN_NOTES.md\n\n\n\n\n\nTopic folders\n\nFor recurring themes (e.g., \"bankr\", \"champions\", \"LYGO-MINT\"), create subfolders under memory/ or reference/:\n\nmemory/bankr/…\nreference/champions/…\n\n\nInside, maintain one index file (e.g., INDEX.txt) listing:\n\nshort description per file\ndate\npath\n\n\n\n\n\nReference stubs (*.ref.txt or INDEX.txt)\nUse tiny text files to connect parts of the library instead of duplicating content.\n\nExample stub:\n\nTitle: LYGO Champion Skills on Clawdhub\nLast updated: 2026-02-10\n\nKey files:\n- reference/LYGO_CHAMPIONS_OVERVIEW.md\n- reference/CLAWDHUB_SKILLS.md\n\nExternal links:\n- https://clawhub.ai/u/DeepSeekOracle\n- https://deepseekoracle.github.io/Excavationpro/LYGO-Network/champions.html#champions\n- https://EternalHaven.ca"
      },
      {
        "title": "5. Advanced Logging for Retrieval",
        "body": "BOOK BRAIN recommends structured logs to make retrieval easy:\n\nDaily health / status logs (e.g., daily_health.md or logs/daily_health_YYYY-MM-DD.md)\n\nEach entry should contain:\n\ntimestamp\nwhat ran (scripts, cron, audits)\nsuccess/failure + short reason\nlinks to any relevant state files (state/*.json)\n\n\n\n\n\nReasoning journals (e.g., reasoning_journals/… or memory_semantic_archive/…)\n\nUse separate folders for long-form thinking.\nPeriodically compress into summary files, and let scripts move old entries into an archive folder.\n\n\n\nIndexes & search helpers\n\nMaintain state/memory_index.json or similar:\n\nkey topic → list of file paths\noptional tags (dates, systems, people)\n\n\nWhen answering questions, the agent should:\n\nconsult the index,\nopen relevant files only,\navoid scanning the entire tree.\n\nBOOK BRAIN is compatible with tools like qmd or other local search/indexers, but does not depend on them."
      },
      {
        "title": "6. Setup Workflow (For a Fresh System)",
        "body": "When BOOK BRAIN is used on a fresh OpenClaw / agent workspace:\n\nDetect existing structure\n\nCheck for memory/, reference/, brainwave/, state/, logs/, tools/, tmp/.\nReport what exists vs. what is missing.\n\n\n\nPropose a BOOK BRAIN layout\n\nSuggest creating missing folders.\nIf the human agrees, create only the missing ones.\n\n\n\nCreate starter index files (if not present)\n\nmemory/INDEX.txt with a short guide and links to key topic folders.\nreference/INDEX.txt listing major reference documents.\nstate/memory_index.json as an empty or seed structure.\n\n\n\nLog the setup\n\nAppend a brief note to daily_health.md or logs/book_brain_setup.log describing what was created.\n\n\n\nDo not overwrite existing files\n\nIf an index file exists, read it and add to it rather than replace.\nIf in doubt, create a new file with a date suffix (e.g., INDEX_2026-02-10.txt) and let the human merge."
      },
      {
        "title": "7. Using BOOK BRAIN in an Existing, Messy Haven",
        "body": "When the filesystem already exists and is messy:\n\nStart by mapping, not moving:\n\nCreate reference/FILESYSTEM_MAP.txt summarizing major folders and what seems to live there.\nDo not move or delete anything automatically.\n\n\n\nThen introduce lightweight structure:\n\nAdd INDEX.txt files in important folders.\nAdd small .ref.txt stubs pointing to key docs and external links.\nGradually normalize names (e.g., memory/2026-02-10.md instead of notes_today.txt).\n\n\n\nOver time, encourage:\n\nDaily logs in memory/\nStable protocols in reference/\nCode + scripts in tools/\nPlatform brains in brainwave/\n\nBOOK BRAIN should always ask the human before structural changes beyond creating new, obviously safe files."
      },
      {
        "title": "8. Eternal Haven & Donation References",
        "body": "This skill is part of the wider LYGO × Eternal Haven ecosystem.\n\nKey links:\n\nEternal Haven portal → https://EternalHaven.ca\nLYGO Champion Hub → https://deepseekoracle.github.io/Excavationpro/LYGO-Network/champions.html#champions\nClawdhub skills (Champion + LYGO stack) → https://clawhub.ai/u/DeepSeekOracle\nExtended work / support → https://www.patreon.com/cw/Excavationpro\n\nIf BOOK BRAIN, the Champion stack, or the LYGO tools help you build a saner Haven, you’re invited (never pressured) to support via the links above."
      },
      {
        "title": "9. How Another Agent Should Use This Skill",
        "body": "When another agent loads book-brain:\n\nRecognize scope\n\nThis is a helper + reference, not a persona.\nIt should not change the agent’s voice; it informs how the agent treats files and memory.\n\n\n\nOn first use in a workspace\n\nInspect existing folders and report back.\nSuggest—but do not enforce—BOOK BRAIN layout.\nAsk the human before creating or reorganizing.\n\n\n\nOn subsequent uses\n\nRead existing INDEX and .ref.txt files.\nUse them for retrieval before doing expensive full-tree searches.\nAppend to logs and indexes instead of overwriting.\n\n\n\nNever silently delete or rewrite large files as part of BOOK BRAIN operations.\n\nFor richer examples and sample layouts, see references/book-brain-examples.md in this skill."
      }
    ],
    "body": "BOOK BRAIN – LYGO 3-Brain Filesystem Helper\n\nThis skill is a utility/guide, not a persona.\n\nUse it when you want to:\n\nSet up or improve a Haven-style filesystem + memory structure\nTeach an agent how to use folders, indexes, and reference .txt files instead of hoarding everything in one place\nAdd advanced logging + retrieval so memories can be found later without brute-force scanning\n\nIt is built for LYGO / Eternal Haven style systems, but works for any agent that can:\n\nread/write files\ncreate folders\nappend to logs\n\nCore idea: BOOK BRAIN = treating your filesystem like a living library, not a junk drawer.\n\n1. Three-Brain Model (Conceptual Map)\n\nBOOK BRAIN assumes a 3-brain structure:\n\nWorking Brain (short-term)\n\nRecent conversation, active task context, scratchpads.\nIn OpenClaw, this is the current session + small scratch files under tmp/.\n\nLibrary Brain (structured filesystem)\n\nFolders + files on disk: memory/, reference/, brainwave/, state/, etc.\nThis is where BOOK BRAIN focuses: how you name, branch, and link things.\n\nOuter Brain (external references)\n\nBrowser bookmarks, Clawdhub skills, on-chain receipts, remote docs.\nBOOK BRAIN treats these as links inside text files, not content to copy in.\n\nThe goal is to:\n\nKeep important truths close and succinct\nBranch deeper into folders when detail is needed\nUse .txt reference links instead of duplicating entire documents\n2. When to Use BOOK BRAIN\n\nTrigger this skill when:\n\nYou are setting up a fresh Haven (new OpenClaw workspace, new agent node)\nYour filesystem feels chaotic and you need a reset without deleting anything\nYou want to design a clean memory + reference layout before starting heavy work\nYou are planning long-term retrieval (\"I’ll need this months from now\")\n\nBOOK BRAIN is additive:\n\nDo not use it to delete or overwrite existing files by default.\nPrefer creating new folders / indexes alongside existing ones.\nWhen a folder already exists, pause and let the human choose: reuse or create a new branch (e.g., memory_v2/).\n3. Recommended Base Folder Layout\n\nWhen setting up a new Haven-like system (or auditing an existing one), BOOK BRAIN recommends the following top-level folders:\n\nmemory/ → daily notes, raw logs, timeline files\nreference/ → stable facts, protocols, guides (things that rarely change)\nbrainwave/ → platform- or domain-specific protocols (MoltX, Clawhub, LYGO, etc.)\nstate/ → machine-readable JSON/YAML state, indexes, last-run info\nlogs/ (or reuse logs/ if present) → technical logs (cron, errors, audits)\ntools/ → scripts/utilities used by the agent\ntmp/ → scratch, throwaway working files\n\nBOOK BRAIN setup rules:\n\nIf a folder already exists, do not rename or delete it.\nIf a folder is missing, it is safe to create it.\nIf the existing layout is very different, create a sub-tree (e.g., bookbrain/memory_index/) and keep old structure intact.\n\nFor concrete layout examples, see references/book-brain-examples.md in this skill.\n\n4. Memory Strategy – Deep Storage vs. Reference Stubs\n\nBOOK BRAIN enforces this principle:\n\nDo not pour entire conversations or huge documents into MEMORY.md or a single file.\nInstead, store detailed content in specific files and create short reference stubs that point to them.\n\nPatterns:\n\nDaily logs\n\nFiles like memory/2026-02-10.md for raw notes and events.\nAt the top, keep a 5–10 line summary and a small list of important links:\nSee: reference/AGENT_ARCHITECTURE.md\nSee: memory/projects/BOOK_BRAIN_NOTES.md\n\nTopic folders\n\nFor recurring themes (e.g., \"bankr\", \"champions\", \"LYGO-MINT\"), create subfolders under memory/ or reference/:\nmemory/bankr/…\nreference/champions/…\nInside, maintain one index file (e.g., INDEX.txt) listing:\nshort description per file\ndate\npath\n\nReference stubs (*.ref.txt or INDEX.txt)\nUse tiny text files to connect parts of the library instead of duplicating content.\n\nExample stub:\n\nTitle: LYGO Champion Skills on Clawdhub\nLast updated: 2026-02-10\n\nKey files:\n- reference/LYGO_CHAMPIONS_OVERVIEW.md\n- reference/CLAWDHUB_SKILLS.md\n\nExternal links:\n- https://clawhub.ai/u/DeepSeekOracle\n- https://deepseekoracle.github.io/Excavationpro/LYGO-Network/champions.html#champions\n- https://EternalHaven.ca\n\n5. Advanced Logging for Retrieval\n\nBOOK BRAIN recommends structured logs to make retrieval easy:\n\nDaily health / status logs (e.g., daily_health.md or logs/daily_health_YYYY-MM-DD.md)\n\nEach entry should contain:\ntimestamp\nwhat ran (scripts, cron, audits)\nsuccess/failure + short reason\nlinks to any relevant state files (state/*.json)\n\nReasoning journals (e.g., reasoning_journals/… or memory_semantic_archive/…)\n\nUse separate folders for long-form thinking.\nPeriodically compress into summary files, and let scripts move old entries into an archive folder.\n\nIndexes & search helpers\n\nMaintain state/memory_index.json or similar:\nkey topic → list of file paths\noptional tags (dates, systems, people)\nWhen answering questions, the agent should:\nconsult the index,\nopen relevant files only,\navoid scanning the entire tree.\n\nBOOK BRAIN is compatible with tools like qmd or other local search/indexers, but does not depend on them.\n\n6. Setup Workflow (For a Fresh System)\n\nWhen BOOK BRAIN is used on a fresh OpenClaw / agent workspace:\n\nDetect existing structure\n\nCheck for memory/, reference/, brainwave/, state/, logs/, tools/, tmp/.\nReport what exists vs. what is missing.\n\nPropose a BOOK BRAIN layout\n\nSuggest creating missing folders.\nIf the human agrees, create only the missing ones.\n\nCreate starter index files (if not present)\n\nmemory/INDEX.txt with a short guide and links to key topic folders.\nreference/INDEX.txt listing major reference documents.\nstate/memory_index.json as an empty or seed structure.\n\nLog the setup\n\nAppend a brief note to daily_health.md or logs/book_brain_setup.log describing what was created.\n\nDo not overwrite existing files\n\nIf an index file exists, read it and add to it rather than replace.\nIf in doubt, create a new file with a date suffix (e.g., INDEX_2026-02-10.txt) and let the human merge.\n7. Using BOOK BRAIN in an Existing, Messy Haven\n\nWhen the filesystem already exists and is messy:\n\nStart by mapping, not moving:\n\nCreate reference/FILESYSTEM_MAP.txt summarizing major folders and what seems to live there.\nDo not move or delete anything automatically.\n\nThen introduce lightweight structure:\n\nAdd INDEX.txt files in important folders.\nAdd small .ref.txt stubs pointing to key docs and external links.\nGradually normalize names (e.g., memory/2026-02-10.md instead of notes_today.txt).\n\nOver time, encourage:\n\nDaily logs in memory/\nStable protocols in reference/\nCode + scripts in tools/\nPlatform brains in brainwave/\n\nBOOK BRAIN should always ask the human before structural changes beyond creating new, obviously safe files.\n\n8. Eternal Haven & Donation References\n\nThis skill is part of the wider LYGO × Eternal Haven ecosystem.\n\nKey links:\n\nEternal Haven portal → https://EternalHaven.ca\nLYGO Champion Hub → https://deepseekoracle.github.io/Excavationpro/LYGO-Network/champions.html#champions\nClawdhub skills (Champion + LYGO stack) → https://clawhub.ai/u/DeepSeekOracle\nExtended work / support → https://www.patreon.com/cw/Excavationpro\n\nIf BOOK BRAIN, the Champion stack, or the LYGO tools help you build a saner Haven, you’re invited (never pressured) to support via the links above.\n\n9. How Another Agent Should Use This Skill\n\nWhen another agent loads book-brain:\n\nRecognize scope\n\nThis is a helper + reference, not a persona.\nIt should not change the agent’s voice; it informs how the agent treats files and memory.\n\nOn first use in a workspace\n\nInspect existing folders and report back.\nSuggest—but do not enforce—BOOK BRAIN layout.\nAsk the human before creating or reorganizing.\n\nOn subsequent uses\n\nRead existing INDEX and .ref.txt files.\nUse them for retrieval before doing expensive full-tree searches.\nAppend to logs and indexes instead of overwriting.\n\nNever silently delete or rewrite large files as part of BOOK BRAIN operations.\n\nFor richer examples and sample layouts, see references/book-brain-examples.md in this skill."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/DeepSeekOracle/book-brain",
    "publisherUrl": "https://clawhub.ai/DeepSeekOracle/book-brain",
    "owner": "DeepSeekOracle",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/book-brain",
    "downloadUrl": "https://openagent3.xyz/downloads/book-brain",
    "agentUrl": "https://openagent3.xyz/skills/book-brain/agent",
    "manifestUrl": "https://openagent3.xyz/skills/book-brain/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/book-brain/agent.md"
  }
}