[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-PleasePrompto-notebooklm-skill-en":3,"guides-for-PleasePrompto-notebooklm-skill":329,"similar-k17a2m4gyjvxe0gagyj92v85b986mdw8-en":330},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":251,"isFallback":234,"parentExtension":256,"providers":257,"relations":262,"repo":264,"tags":325,"workflow":326},1778695552536.5713,"k17a2m4gyjvxe0gagyj92v85b986mdw8",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.",{"claudeCode":12},"PleasePrompto/notebooklm-skill","NotebookLM Skill","https://github.com/PleasePrompto/notebooklm-skill",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":232,"workflow":249},1778695578542.2625,"kn74stswn23t4w3895t1g1rvk586mma7","en",{"checks":20,"evaluatedAt":191,"extensionSummary":192,"features":193,"nonGoals":201,"practices":206,"prerequisites":207,"promptVersionExtension":211,"promptVersionScoring":212,"purpose":213,"rationale":214,"score":215,"summary":216,"tags":217,"targetMarket":225,"tier":226,"useCases":227},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,89,93,97,101,105,108,112,115,119,122,125,128,131,134,137,141,145,148,152,156,159,162,165,168,172,175,178,181,184,188],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of manual copy-pasting and token consumption when interacting with documentation, and positions NotebookLM as the solution.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over a simple prompt by enabling direct interaction with NotebookLM's knowledge base, providing source-grounded answers and drastically reducing hallucinations.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill appears production-ready, covering authentication, notebook management, querying, and a robust follow-up mechanism, all managed through a clear workflow and scripts.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on interacting with NotebookLM for document-based queries, managing notebooks, and handling authentication, adhering to a single responsibility.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's functionality, highlighting its purpose, core features like browser automation and persistent auth, and benefits like reduced hallucinations.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes a set of well-defined, narrow-scoped tools like `auth_manager.py`, `notebook_manager.py`, and `ask_question.py` managed via a `run.py` wrapper, avoiding a single generalist command.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All parameters for commands like `add_notebook` and `ask_question.py` are clearly documented in the SKILL.md and README.md, including requirements and examples.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool scripts (`auth_manager.py`, `notebook_manager.py`, `ask_question.py`) have descriptive, kebab-cased names that clearly indicate their function.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Input parameters are well-defined (e.g., URL, question, ID) and outputs are structured text answers, requesting only necessary data and returning promised payloads.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The MIT license is clearly provided in a dedicated LICENSE file, which is permissive and usable for redistribution.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The latest commit was in November 2025, which is within the last 3 months, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The skill uses a `requirements.txt` file and `run.py` script for automatic dependency installation, ensuring a managed environment.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","Authentication data is stored locally in `~/.claude/skills/notebooklm/data/` and protected by `.gitignore`, with clear warnings against committing it. No resolved secrets are echoed.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill executes Python scripts within a controlled environment and uses Playwright for browser automation, which handles input sanitization and does not execute arbitrary code from loaded data.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill bundles its dependencies and installs them locally via `pip`, ensuring all code is committed and avoiding runtime fetching of external scripts or data.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill operates within its own virtual environment and uses Playwright with specific configurations to manage browser contexts, ensuring isolation and not modifying files outside its designated data directory.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The Python scripts do not appear to use detached process spawns or retry loops around denied tool calls, operating within the expected execution boundaries.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","Authentication data is stored locally and protected. The skill interacts with Google NotebookLM via browser automation, and all outbound calls are to documented services.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and descriptions appear free of hidden text tricks, control characters, or other obfuscation methods.",{"category":65,"check":87,"severity":24,"summary":88},"Opaque code execution","The Python scripts are plain, readable source code, and dependencies are installed locally, avoiding obfuscation or runtime code fetching.",{"category":90,"check":91,"severity":24,"summary":92},"Portability","Structural Assumption","The skill manages its own environment and data storage within the skill directory, avoiding assumptions about the user's project structure.",{"category":94,"check":95,"severity":24,"summary":96},"Trust","Issues Attention","With 4 open and 1 closed issues in the last 90 days, the closure rate is below 50% but the total number of issues is low, suggesting reasonable maintainer engagement.",{"category":98,"check":99,"severity":24,"summary":100},"Versioning","Release Management","The project has a CHANGELOG.md and uses semantic versioning with release tags, clearly indicating new versions.",{"category":102,"check":103,"severity":24,"summary":104},"Execution","Validation","The script arguments are handled by `argparse`, and Playwright interacts with web elements, implying a level of input validation inherent in these tools.",{"category":65,"check":106,"severity":24,"summary":107},"Unguarded Destructive Operations","The skill is primarily read-only concerning user data. Cleanup operations require explicit `--confirm` flags, and destructive actions are not present.",{"category":109,"check":110,"severity":24,"summary":111},"Code Execution","Error Handling","The scripts include error handling for authentication, browser interactions, and dependency management, providing informative messages and exiting non-zero on failure.",{"category":109,"check":113,"severity":24,"summary":114},"Logging","The scripts provide informative print statements for actions and errors, serving as a form of audit trail for execution within the skill's context.",{"category":116,"check":117,"severity":24,"summary":118},"Compliance","GDPR","The skill only interacts with Google NotebookLM via authenticated browser sessions and does not explicitly operate on personal data beyond what is necessary for authentication and querying.",{"category":116,"check":120,"severity":24,"summary":121},"Target market","The skill's functionality is dependent on Google NotebookLM and Chrome browser, but the core logic is not geographically restricted, making it 'global'.",{"category":90,"check":123,"severity":24,"summary":124},"Runtime stability","The skill explicitly manages its Python environment and dependencies, and uses Playwright with Chrome for browser automation, aiming for cross-platform stability.",{"category":44,"check":126,"severity":24,"summary":127},"README","The README is comprehensive, detailing installation, usage, technical architecture, and benefits, serving as a clear guide.",{"category":33,"check":129,"severity":24,"summary":130},"Tool surface size","The skill exposes several scripts but they are well-defined components of a coherent workflow, not an excessive number of unrelated tools.",{"category":40,"check":132,"severity":24,"summary":133},"Overlapping near-synonym tools","The exposed scripts have distinct functionalities (authentication, notebook management, querying) and do not appear to have overlapping near-synonym names.",{"category":44,"check":135,"severity":24,"summary":136},"Phantom features","All advertised features, such as browser automation, persistent auth, and library management, are implemented and reflected in the scripts and documentation.",{"category":138,"check":139,"severity":24,"summary":140},"Install","Installation instruction","Installation instructions are clear in the README, detailing cloning the repository and the automatic setup process, with copy-pasteable commands.",{"category":142,"check":143,"severity":24,"summary":144},"Errors","Actionable error messages","Error messages in the scripts provide context (e.g., authentication required, notebook not found) and suggest remediation steps (e.g., run setup, check ID).",{"category":102,"check":146,"severity":24,"summary":147},"Pinned dependencies","The `requirements.txt` file and the `run.py` script ensure that dependencies are installed, and the `setup_environment.py` script aims to install them within the venv.",{"category":33,"check":149,"severity":150,"summary":151},"Dry-run preview","not_applicable","The skill is primarily analytical and does not perform destructive operations that would necessitate a dry-run preview.",{"category":153,"check":154,"severity":24,"summary":155},"Protocol","Idempotent retry & timeouts","While not explicitly described as idempotent mutations, the query operations have defined timeouts, and the stateless design between calls mitigates retry issues.",{"category":116,"check":157,"severity":24,"summary":158},"Telemetry opt-in","The skill does not appear to emit any telemetry; all operations are local and user-initiated.",{"category":40,"check":160,"severity":24,"summary":161},"Precise Purpose","The purpose is precisely stated: query Google NotebookLM notebooks directly from Claude Code for source-grounded answers, with clear triggers and boundaries outlined.",{"category":40,"check":163,"severity":24,"summary":164},"Concise Frontmatter","The frontmatter in SKILL.md is concise and directly states the core capability and triggers, suitable for precise routing.",{"category":44,"check":166,"severity":24,"summary":167},"Concise Body","The SKILL.md and README.md are detailed but well-structured with clear sections and links to reference files, keeping the main body concise.",{"category":169,"check":170,"severity":24,"summary":171},"Context","Progressive Disclosure","The skill uses `references/` files for extended documentation like API reference and usage patterns, demonstrating progressive disclosure.",{"category":169,"check":173,"severity":150,"summary":174},"Forked exploration","The skill does not involve deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":176,"severity":24,"summary":177},"Usage examples","The SKILL.md, README.md, and `references/usage_patterns.md` provide numerous end-to-end examples with clear inputs, invocations, and expected outcomes.",{"category":22,"check":179,"severity":24,"summary":180},"Edge cases","The `Troubleshooting Guide` and `FAQ` sections address edge cases like authentication failures, browser crashes, rate limits, and environmental issues with specific recovery steps.",{"category":109,"check":182,"severity":150,"summary":183},"Tool Fallback","The skill does not rely on external MCP servers or tools that would require a fallback path; it's self-contained.",{"category":185,"check":186,"severity":24,"summary":187},"Safety","Halt on unexpected state","The skill manages its own environment and data, and error handling scripts report issues and exit non-zero, effectively halting workflows on unexpected states.",{"category":90,"check":189,"severity":24,"summary":190},"Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills. It focuses solely on NotebookLM interaction.",1778695578345,"This Python-based Claude Code skill integrates with Google NotebookLM using browser automation. It allows users to query their NotebookLM notebooks, manage notebooks in a library, and handle authentication, all within an isolated virtual environment.",[194,195,196,197,198,199,200],"Query NotebookLM notebooks directly","Source-grounded, citation-backed answers","Browser automation for interaction","Persistent authentication management","Notebook library management (add, list, search, activate)","Automated virtual environment setup","Reduced hallucinations through document-only responses",[202,203,204,205],"Performing general web searches outside of NotebookLM","Modifying or creating NotebookLM notebooks directly (only management via URL)","Replacing NotebookLM itself; it requires a NotebookLM account and uploaded documents","Running in the Claude web UI (requires local Claude Code installation)",[],[208,209,210],"Local Claude Code installation","Google account for NotebookLM access","Google Chrome browser (installed automatically)","3.0.0","4.4.0","To enable direct, source-grounded querying of Google NotebookLM notebooks from Claude Code, drastically reducing hallucinations and eliminating manual copy-pasting for research and development tasks.","The skill is exceptionally well-documented, robustly implemented with strong error handling and security practices, and provides significant practical utility. The only minor finding relates to issue engagement being slightly below the highest threshold, but overall quality is outstanding.",99,"A highly polished and robust skill for interacting with Google NotebookLM, offering source-grounded answers and efficient documentation management.",[218,219,220,221,222,223,224],"notebooklm","google","documentation","research","qa","browser-automation","python","global","verified",[228,229,230,231],"Asking specific questions about documentation stored in NotebookLM","Getting code implementation details or best practices from uploaded docs","Comparing information across multiple notebooks","Using your documentation as a reliable knowledge base for coding tasks",{"codeQuality":233,"collectedAt":235,"documentation":236,"maintenance":239,"security":246,"testCoverage":248},{"hasLockfile":234},false,1778695554074,{"descriptionLength":237,"readmeSize":238},265,15901,{"closedIssues90d":240,"forks":241,"hasChangelog":242,"openIssues90d":243,"pushedAt":244,"stars":245},1,713,true,4,1763746932000,6438,{"hasNpmPackage":234,"license":247,"smitheryVerified":234},"MIT",{"hasCi":234,"hasTests":234},{"updatedAt":250},1778695578542,{"basePath":252,"githubOwner":253,"githubRepo":254,"locale":18,"slug":254,"type":255},"","PleasePrompto","notebooklm-skill","skill",null,{"evaluate":258,"extract":260},{"promptVersionExtension":211,"promptVersionScoring":212,"score":215,"tags":259,"targetMarket":225,"tier":226},[218,219,220,221,222,223,224],{"commitSha":261,"license":247},"HEAD",{"repoId":263},"kd77gpjgrb75m8vdz999898gfx86nmyk",{"_creationTime":265,"_id":263,"identity":266,"providers":267,"workflow":321},1778695537323.5908,{"githubOwner":253,"githubRepo":254,"sourceUrl":14},{"classify":268,"discover":315,"github":318},{"commitSha":261,"extensions":269},[270],{"basePath":252,"description":10,"displayName":218,"installMethods":271,"rationale":272,"selectedPaths":273,"source":314,"sourceLanguage":18,"type":255},{"claudeCode":12},"SKILL.md frontmatter at SKILL.md",[274,277,280,282,285,287,289,291,293,296,298,300,302,304,306,308,310,312],{"path":275,"priority":276},"SKILL.md","mandatory",{"path":278,"priority":279},"README.md","high",{"path":281,"priority":279},"LICENSE",{"path":283,"priority":284},"AUTHENTICATION.md","medium",{"path":286,"priority":284},"CHANGELOG.md",{"path":288,"priority":284},"references/api_reference.md",{"path":290,"priority":284},"references/troubleshooting.md",{"path":292,"priority":284},"references/usage_patterns.md",{"path":294,"priority":295},"scripts/__init__.py","low",{"path":297,"priority":295},"scripts/ask_question.py",{"path":299,"priority":295},"scripts/auth_manager.py",{"path":301,"priority":295},"scripts/browser_session.py",{"path":303,"priority":295},"scripts/browser_utils.py",{"path":305,"priority":295},"scripts/cleanup_manager.py",{"path":307,"priority":295},"scripts/config.py",{"path":309,"priority":295},"scripts/notebook_manager.py",{"path":311,"priority":295},"scripts/run.py",{"path":313,"priority":295},"scripts/setup_environment.py","rule",{"sources":316},[317],"manual",{"closedIssues90d":240,"description":319,"forks":241,"license":247,"openIssues90d":243,"pushedAt":244,"readmeSize":238,"stars":245,"topics":320},"Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your uploaded documents and get source-grounded, citation-backed answers from Gemini. Features browser automation, library management, persistent authentication, and answers exclusively from your own knowledge base.",[],{"classifiedAt":322,"discoverAt":323,"extractAt":324,"githubAt":324,"updatedAt":322},1778695550270,1778695537323,1778695539447,[223,220,219,218,224,222,221],{"evaluatedAt":250,"extractAt":327,"updatedAt":328},1778695552536,1778695613439,[],[331,360,388,415,444,466],{"_creationTime":332,"_id":333,"community":334,"display":335,"identity":341,"providers":345,"relations":353,"tags":356,"workflow":357},1778699234184.6135,"k175frmf44tn80mcd6gvw1c1th86ngq9",{"reviewCount":8},{"description":336,"installMethods":337,"name":339,"sourceUrl":340},"Invoke parallel document-specialist agents for external web searches and documentation lookup",{"claudeCode":338},"Yeachan-Heo/oh-my-claudecode","external-context","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":342,"githubOwner":343,"githubRepo":344,"locale":18,"slug":339,"type":255},"skills/external-context","Yeachan-Heo","oh-my-claudecode",{"evaluate":346,"extract":352},{"promptVersionExtension":211,"promptVersionScoring":212,"score":347,"tags":348,"targetMarket":225,"tier":226},100,[349,220,221,350,351],"search","information-retrieval","multi-agent",{"commitSha":261},{"parentExtensionId":354,"repoId":355},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[220,350,351,221,349],{"evaluatedAt":358,"extractAt":359,"updatedAt":358},1778699449790,1778699234184,{"_creationTime":361,"_id":362,"community":363,"display":364,"identity":370,"providers":374,"relations":381,"tags":384,"workflow":385},1778697513812.0674,"k174b6b0gkvp2r318akg2twggd86nrwj",{"reviewCount":8},{"description":365,"installMethods":366,"name":368,"sourceUrl":369},"UI/UX design intelligence with searchable style, palette, typography, and chart databases. Use when designing UI components, choosing colors/fonts, reviewing code for UX issues, building landing pages, or implementing responsive layouts.",{"claudeCode":367},"spartan-stratos/spartan-ai-toolkit","ui-ux-pro-max","https://github.com/spartan-stratos/spartan-ai-toolkit",{"basePath":371,"githubOwner":372,"githubRepo":373,"locale":18,"slug":368,"type":255},"toolkit/skills/ui-ux-pro-max","spartan-stratos","spartan-ai-toolkit",{"evaluate":375,"extract":380},{"promptVersionExtension":211,"promptVersionScoring":212,"score":347,"tags":376,"targetMarket":225,"tier":226},[377,378,379,220,224],"ui-ux","design-system","frontend",{"commitSha":261},{"parentExtensionId":382,"repoId":383},"k178krwbqrnxn4xscs4htpjvxd86m4kj","kd73rjj0rnrv7y0rz9qc3psn0586n75g",[378,220,379,224,377],{"evaluatedAt":386,"extractAt":387,"updatedAt":386},1778698073321,1778697513812,{"_creationTime":389,"_id":390,"community":391,"display":392,"identity":398,"providers":402,"relations":408,"tags":411,"workflow":412},1778696833339.6226,"k17ckxne6mhyf23n1jfyqktpqd86nfz4",{"reviewCount":8},{"description":393,"installMethods":394,"name":396,"sourceUrl":397},"Interact with Google Docs - create documents, search by title, read content, and edit text.\nUse when user asks to: create a Google Doc, find a document, read doc content, add text to a doc,\nor replace text in a document. Lightweight alternative to full Google Workspace MCP server with\nstandalone OAuth authentication.\n",{"claudeCode":395},"sanjay3290/ai-skills","google-docs","https://github.com/sanjay3290/ai-skills",{"basePath":399,"githubOwner":400,"githubRepo":401,"locale":18,"slug":396,"type":255},"skills/google-docs","sanjay3290","ai-skills",{"evaluate":403,"extract":407},{"promptVersionExtension":211,"promptVersionScoring":212,"score":347,"tags":404,"targetMarket":225,"tier":226},[396,405,220,406,224],"api","oauth",{"commitSha":261},{"parentExtensionId":409,"repoId":410},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[405,220,396,406,224],{"evaluatedAt":413,"extractAt":414,"updatedAt":413},1778696994497,1778696833339,{"_creationTime":416,"_id":417,"community":418,"display":419,"identity":425,"providers":430,"relations":437,"tags":440,"workflow":441},1778686640222.7986,"k173npg49t3qa1x72jhc9vqadn86mvsq",{"reviewCount":8},{"description":420,"installMethods":421,"name":423,"sourceUrl":424},"Run browser tests on pages affected by current PR or branch",{"claudeCode":422},"EveryInc/compound-engineering-plugin","Compound Engineering Browser Test","https://github.com/EveryInc/compound-engineering-plugin",{"basePath":426,"githubOwner":427,"githubRepo":428,"locale":18,"slug":429,"type":255},"plugins/compound-engineering/skills/ce-test-browser","EveryInc","compound-engineering-plugin","ce-test-browser",{"evaluate":431,"extract":436},{"promptVersionExtension":211,"promptVersionScoring":212,"score":215,"tags":432,"targetMarket":225,"tier":226},[433,223,434,222,435],"testing","cli","ci",{"commitSha":261,"license":247},{"parentExtensionId":438,"repoId":439},"k17d893df4em0e3pn8f55h1dxn86n09e","kd7e40my1b5g70tg0f60qg85ch86nn08",[223,435,434,222,433],{"evaluatedAt":442,"extractAt":443,"updatedAt":442},1778687496344,1778686640222,{"_creationTime":445,"_id":446,"community":447,"display":448,"identity":451,"providers":453,"relations":462,"tags":463,"workflow":464},1778696833339.625,"k178pwpzxsgvbvhcd3rvvqnd5s86mtcj",{"reviewCount":8},{"description":449,"installMethods":450,"name":13,"sourceUrl":397},"Query and manage Google NotebookLM notebooks with persistent profile auth, source sync, batch/multi queries, and structured exports. Use when user asks to query NotebookLM, 'ask my notebook', shares NotebookLM notebook URLs, wants to list/create notebooks, manage sources, do bulk folder sync, dedupe, or audit exports.",{"claudeCode":395},{"basePath":452,"githubOwner":400,"githubRepo":401,"locale":18,"slug":218,"type":255},"skills/notebooklm",{"evaluate":454,"extract":460},{"promptVersionExtension":211,"promptVersionScoring":212,"score":215,"tags":455,"targetMarket":225,"tier":226},[218,219,456,457,458,459],"productivity","llm","automation","browser",{"commitSha":261,"license":461},"Apache-2.0",{"parentExtensionId":409,"repoId":410},[458,459,219,457,218,456],{"evaluatedAt":465,"extractAt":414,"updatedAt":465},1778697155637,{"_creationTime":467,"_id":468,"community":469,"display":470,"identity":476,"providers":480,"relations":485,"tags":487,"workflow":488},1778697205743.894,"k17ej9360g7468qswf3svnrx9186m1ng",{"reviewCount":8},{"description":471,"installMethods":472,"name":474,"sourceUrl":475},"Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.",{"claudeCode":473},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":477,"githubOwner":478,"githubRepo":479,"locale":18,"slug":474,"type":255},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":481,"extract":484},{"promptVersionExtension":211,"promptVersionScoring":212,"score":347,"tags":482,"targetMarket":225,"tier":226},[223,483,433,434,458],"web-scraping",{"commitSha":261},{"repoId":486},"kd74710g49kxgwbfjxeb7s132d86myxr",[458,223,434,433,483],{"evaluatedAt":489,"extractAt":490,"updatedAt":491},1778697222051,1778697205743,1778697438718]