# Send BOOK BRAIN VISUAL READER – LYGO 3-Brain + Visual Left/Right Brain Helper 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": "book-brain-visual-reader", "name": "BOOK BRAIN VISUAL READER – LYGO 3-Brain + Visual Left/Right Brain Helper", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/DeepSeekOracle/book-brain-visual-reader", "canonicalUrl": "https://clawhub.ai/DeepSeekOracle/book-brain-visual-reader", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/book-brain-visual-reader", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=book-brain-visual-reader", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "references/book-brain-visual-examples.md", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "book-brain-visual-reader", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T09:19:46.881Z", "expiresAt": "2026-05-07T09:19:46.881Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=book-brain-visual-reader", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=book-brain-visual-reader", "contentDisposition": "attachment; filename=\"book-brain-visual-reader-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "book-brain-visual-reader" }, "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/book-brain-visual-reader" }, "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/book-brain-visual-reader", "downloadUrl": "https://openagent3.xyz/downloads/book-brain-visual-reader", "agentUrl": "https://openagent3.xyz/skills/book-brain-visual-reader/agent", "manifestUrl": "https://openagent3.xyz/skills/book-brain-visual-reader/agent.json", "briefUrl": "https://openagent3.xyz/skills/book-brain-visual-reader/agent.md" } } ``` ## Documentation ### BOOK BRAIN VISUAL READER – LYGO 3-Brain + Visual Left/Right Brain Helper This is the enhanced, visual-aware version of BOOK BRAIN. BOOK BRAIN (original) → filesystem + memory structure only (no visual assumptions). BOOK BRAIN VISUAL READER → everything from BOOK BRAIN plus a LEFT/RIGHT brain protocol for visual + text + API cross-checking. Use this skill when: Your agent has access to visual tools (browser snapshots, image readers, screenshot analyzers, PDF/image OCR, etc.) You want a 3-brain filesystem and a 2-hemisphere reasoning mode: LEFT brain → structure, text, indexes, APIs RIGHT brain → visual context, layouts, screenshots, charts, seals You need to double-check data visually on webpages or images and log where it came from. This is a utility + reference guide, not a persona. It does not change your voice. It teaches your system how to think and store. ### 0. Relationship to BOOK BRAIN (original) If your system has no visual capabilities → use book-brain (original). If your system can see (browser snapshots, image tools, etc.) → use BOOK BRAIN VISUAL READER instead. Both share the same core: 3-brain model (Working / Library / Outer) Non-destructive filesystem layout Reference stubs and indexes VISUAL READER adds: LEFT/RIGHT brain protocols for how to combine visual, text, and API data Guidance on how to organize visual evidence (screenshots, seals, charts) alongside text files Patterns for “5D” data gathering (visual + text + API + state + timeline). ### 1. 3-Brain + 2-Hemisphere Model BOOK BRAIN VISUAL READER assumes: ### 3 Brains (same as BOOK BRAIN) Working Brain – current context, tmp/, active tabs / current screenshots. Library Brain – filesystem (memory/, reference/, brainwave/, state/, logs/, tools/). Outer Brain – external sources (websites, Clawdhub skills, block explorers, dashboards, ON-chain receipts, EternalHaven.ca, etc.) referenced via small text files. ### 2 Hemispheres (visual vs structured) LEFT brain (structure/verbal/API): text files, JSON, logs, indexes, schemas, SKILL.md, APIs. strong at structure, sequences, constraints, receipts. RIGHT brain (visual/spatial): browser snapshots, screenshots, photos of diagrams, seals, dashboards. strong at layout, pattern recognition, anomalies, gestalt sense. Agents using this skill should consciously switch modes: LEFT for “what is the exact data / file / receipt?” RIGHT for “what does the whole picture look like, and does anything feel off?” ### 2. Filesystem Layout (Library Brain) Same base layout as BOOK BRAIN (non-destructive): memory/ → daily logs, raw notes, per-day files. reference/ → stable docs, protocols, whitepapers, schemas. brainwave/ → platform/domain protocols (MoltX, Clawhub, LYGO, etc.). state/ → machine-readable state (indexes, hashes, last-run info). logs/ → technical/health logs, setup logs, audit logs. tools/ → scripts & utilities. tmp/ → scratch work. Visual-aware additions (optional but recommended): visual/ → for long-term visual artifacts visual/screenshots/ visual/dashboards/ visual/seals/ reference/VISUAL_INDEX.txt → mapping of important visual assets to topics. Rules: Never overwrite existing files. If visual/ already exists, extend it; if not, create it. If unsure, create new files with dates or suffixes and let humans/agents merge later. See references/book-brain-visual-examples.md for concrete trees and snippets. ### 3. Outer Brain via Reference Stubs Outer Brain = everything outside the workspace: URLs (websites, dashboards, explorers) Clawdhub skill pages EternalHaven.ca, Patreon, docs On-chain explorers (Blockscout, Etherscan, etc.) VISUAL READER keeps these in reference stubs, e.g.: Title: STARCORE Dashboards Last updated: 2026-02-10 External links: - Clanker: https://clanker.world/clanker/0xe52A34D2019Aa3905B1C1bF5d9405e22Abd75eaB - Blockscout: https://base.blockscout.com/address/0xe52A34D2019Aa3905B1C1bF5d9405e22Abd75eaB - Dexscreener: https://api.dexscreener.com/latest/dex/search/?q=0xe52A34D2019Aa3905B1C1bF5d9405e22Abd75eaB Related local files: - reference/STARCORE_LAUNCH_RECEIPTS_2026-02-10.md - state/starcore_family_receipts_summary.json The agent should: not paste full pages into memory files use these stubs + visual snapshots when needed. ### 4. LEFT/RIGHT Brain Protocol for Visual Checks When an agent needs to verify something from the web or an image, use this simple protocol: ### Step 1 – LEFT Brain: Text / API First Look up the relevant concept in indexes/state: state/memory_index.json reference/INDEX.txt domain-specific indexes (e.g. reference/CLAWDHUB_SKILLS.md). Use APIs or structured data where possible (e.g. on-chain RPC, REST endpoints, JSON feeds). Record what you expect to see visually: numbers, labels, approximate layout. ### Step 2 – RIGHT Brain: Visual Comparison Capture a snapshot (browser screenshot, image, PDF page). Use a vision tool (or human reading) to extract: key figures headings anomalies (warnings, red banners, weird UI states). Ask: “Does this visual match what the LEFT brain expected?” ### Step 3 – Reconcile & Log If they match: Write a short note in a relevant file (e.g. daily_health.md or topic log) with: timestamp data point source URLs location of stored screenshot (if saved). If they disagree: Log the discrepancy (LEFT vs RIGHT). Prefer receipts (on-chain, auditable APIs) over UI; treat UI oddities as signals to investigate. Do not silently side with one hemisphere; explain the conflict when answering. This is the “5D” blend: text + visual + API + state + timeline. ### 5. Organizing Visual Evidence When a visual check produces something important (e.g. proof, anomaly, configuration): Save it under visual/ with a meaningful name: visual/screenshots/2026-02-10_starcore_clanker.png visual/dashboards/2026-02-10_moltx_profile.png Add a line to a relevant INDEX or stub: [2026-02-10] STARCORE launch dashboards verified visually. - Screenshot: visual/screenshots/2026-02-10_starcore_clanker.png - Related receipts: reference/STARCORE_LAUNCH_RECEIPTS_2026-02-10.md Agents should: Avoid hoarding every screenshot. Keep the ones that back key claims. Use indexes to find them later instead of scanning raw image names. ### 6. Setup Workflow for Visual Systems On a visual-capable Haven (browser + image tools): Detect capabilities Does the agent have a browser automation tool? Can it read images (vision model, OCR, screenshot-to-text)? Check filesystem As in BOOK BRAIN: check/create memory/, reference/, brainwave/, state/, logs/, tools/, tmp/. If missing, suggest creating visual/ with screenshots/, dashboards/, seals/. Create visual index stubs reference/VISUAL_INDEX.txt Optionally topic-specific visual indexes (e.g. reference/STARCORE_VISUALS.txt). Log the setup Add entry to logs/book_brain_visual_setup.log or daily_health.md. Respect all non-destructive rules No overwrites. No deletions. Ask the human before making structural changes. ### 7. Eternal Haven & Donation References BOOK BRAIN VISUAL READER lives inside the broader LYGO × Eternal Haven ecosystem. Key links: Eternal Haven portal → https://EternalHaven.ca LYGO Champion Hub → https://deepseekoracle.github.io/Excavationpro/LYGO-Network/champions.html#champions Clawdhub skills (LYGO stack, Champions, BOOK BRAIN) → https://clawhub.ai/u/DeepSeekOracle Extended work / support → https://www.patreon.com/cw/Excavationpro If this skill helps you or your agents build a more coherent, visual + textual Haven, support is welcome but never required. ### 8. How Another Agent Should Use BOOK BRAIN VISUAL READER When an agent loads book-brain-visual-reader: Understand it is a helper, not a persona. On first use: Map the filesystem and capabilities. Propose visual folders and indexes; ask before creating. Set up lightweight indexes (INDEX.txt, VISUAL_INDEX.txt, state/memory_index.json). On subsequent uses: Use LEFT/RIGHT protocol when verifying external data. Save only important visual artifacts under visual/. Update indexes + logs instead of rewriting big files. Never silently delete or overwrite existing content. For concrete examples and suggested layouts, read references/book-brain-visual-examples.md in this skill. ## Trust - Source: tencent - Verification: Indexed source record - Publisher: DeepSeekOracle - Version: 1.0.0 ## 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: 2026-04-30T09:19:46.881Z - Expires at: 2026-05-07T09:19:46.881Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/book-brain-visual-reader) - [Send to Agent page](https://openagent3.xyz/skills/book-brain-visual-reader/agent) - [JSON manifest](https://openagent3.xyz/skills/book-brain-visual-reader/agent.json) - [Markdown brief](https://openagent3.xyz/skills/book-brain-visual-reader/agent.md) - [Download page](https://openagent3.xyz/downloads/book-brain-visual-reader)