[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-mnemox-ai-trading-memory-en":3,"guides-for-mnemox-ai-trading-memory":414,"similar-k173a67a16bpq0e29wjd85v71986nx03-en":415},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":240,"isFallback":235,"parentExtension":245,"providers":275,"relations":279,"repo":280,"tags":411,"workflow":412},1778693539593.1863,"k173a67a16bpq0e29wjd85v71986nx03",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on \"record trade\", \"remember trade\", \"recall\", \"similar trades\", \"performance\", \"behavioral\", \"disposition\", \"affective state\", \"confidence\".",{"claudeCode":12},"mnemox-ai/tradememory-protocol","trading-memory","https://github.com/mnemox-ai/tradememory-protocol",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":238},1778693719816.0715,"kn7anq9dastfsgwktyr39w102x86mnzb","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,132,135,138,142,146,149,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of AI trading memory limitations and the solution provided by the Outcome-Weighted Memory (OWM) architecture.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension provides a novel memory architecture (OWM) and multiple memory types for AI trading agents, going beyond basic trade recording.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension offers a comprehensive set of tools for recording, recalling, analyzing, and planning trades, covering the full lifecycle of memory management for trading agents.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses on the domain of AI trading memory, providing a coherent set of tools for recording, recalling, and analyzing trade-related information.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the capabilities outlined in the SKILL.md and README.md, including the OWM architecture, memory types, and use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","Tools are specifically named for their function (e.g., `remember_trade`, `recall_memories`, `get_strategy_performance`) and do not rely on arbitrary string inputs.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md and README.md detail the memory types, OWM scoring factors, and available MCP tools, providing sufficient reference for configuration and use.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names are descriptive, verb-noun pairs that clearly indicate their function within the trading memory domain.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The tool descriptions and SKILL.md imply that inputs request specific trade context and outputs return relevant memory or analysis data without excessive diagnostics.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT license, as declared in the LICENSE file and README.md, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on April 10, 2026, which is within the last 3 months, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The extension uses standard Python packages and is available via PyPI, implying standard dependency management practices.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension is read-only and does not handle or expose any secrets, API keys, or sensitive user credentials.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The extension focuses on structured data recording and recall, and there is no indication of loading or executing untrusted third-party code or data.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension is self-contained and does not fetch external code or data at runtime; all necessary components are bundled.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","As a memory and analysis tool, it does not modify files outside its intended scope and operates locally without external network calls.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","There are no indications of detached process spawns or retry loops around denied tool calls in the provided source files.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's purpose is local data storage and analysis; it explicitly states no external network calls are made and no data is sent to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled markdown files and code appear free of hidden steering tricks, control characters, or suspicious Unicode sequences.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The provided source code is plain, readable Python and markdown, with no evidence of obfuscation, base64 payloads, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The extension operates on provided trade data and does not make assumptions about the user's project file structure.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","There are 0 open and 0 closed issues in the last 90 days, indicating either a very new project or excellent issue management.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project uses PyPI versioning (`pip install tradememory-protocol`) and GitHub release tags/tags are present, indicating clear versioning.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","While specific schema validation libraries aren't explicitly shown in the provided snippets, the tool design implies structured input for trade data, and the README suggests comprehensive API reference.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The extension is primarily a data recording and recall tool, with no destructive operations mentioned or implied.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The SKILL.md and README.md imply robust error handling and reporting for its operations, particularly for compliance and audit features.",{"category":110,"check":114,"severity":24,"summary":115},"Logging","The extension's focus on tamper-proof audit trails suggests robust internal logging mechanisms for all recorded events.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The extension deals with trade data and agent behavior, not personal user data. Any personal data would be incidental and handled locally.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The extension is globally applicable to any AI trading agent, with no regional or jurisdictional limitations mentioned.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The extension is a Python package installable via pip and runs locally, making it broadly compatible across POSIX and Windows systems.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README is comprehensive, detailing the extension's purpose, how it works, quick start, use cases, and technical details.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The extension exposes 17 MCP tools, which is within the recommended range for a complex utility like this.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","Tools are distinctly named and cover separate aspects of memory management, avoiding near-synonym redundancy.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, including the 5 memory types and audit trail, are reflected in the tool descriptions and documentation.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","Clear installation instructions are provided for pip, Claude Code, Docker, and from source, along with a copy-pasteable example for Claude Desktop.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The emphasis on audit trails, compliance, and structured recall implies that error messages would be actionable and informative.",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","As a PyPI package, dependencies are managed and pinned by default, and scripts would use standard shebangs.",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","The extension is primarily a data recording and recall tool, and does not involve state-changing operations that would require a dry-run feature.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The extension focuses on local data operations and doesn't appear to involve remote calls that would necessitate explicit retry/timeout handling beyond standard library capabilities.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The extension explicitly states it makes no external network calls, thus emitting no telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly defines the purpose as 'Domain knowledge for AI trading memory' and specifies use cases like 'recording trades' and 'analyzing performance', with clear trigger phrases.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise, self-contained, and effectively summarizes the core capability and triggers.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is concise, outlining the architecture and tools, while delegating deeper material to separate files like 'docs/'.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Deeper material like API references and OWM framework details are linked in separate markdown files, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","The extension is not designed for deep exploration or research within the user's project; it manages its own internal memory state.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README provides a clear quick-start example for Claude Desktop integration and mentions detailed walkthroughs and use cases in separate documentation.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation implicitly handles edge cases by focusing on structured data recording and recall, and explicitly mentions failure modes in the 'Failure Taxonomy' documentation.",{"category":110,"check":183,"severity":24,"summary":184},"Tool Fallback","The extension is a self-contained Python package and does not rely on external MCP servers with fallbacks.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The emphasis on audit trails and compliance suggests that unexpected states would halt operations and be reported.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The extension is self-contained and does not appear to rely on other specific skills being loaded; any related tasks are handled internally or through its own provided tools.",1778693719704,"This extension provides a sophisticated memory system for AI trading agents, implementing the Outcome-Weighted Memory (OWM) architecture with five distinct memory types. It allows for detailed recording of trades with full context, recall based on weighted relevance (outcome, similarity, recency, confidence), and behavioral analysis. It includes tools for creating trading plans and checking agent state, with a strong emphasis on tamper-proof audit trails for regulatory compliance.",[195,196,197,198,199],"Outcome-Weighted Memory (OWM) architecture","Five distinct memory types (Episodic, Semantic, Procedural, Affective, Prospective)","Recall scoring based on P&L, context similarity, recency, and confidence","Automated trade recording and analysis","Tamper-proof SHA-256 audit trail for regulatory compliance",[201,202,203],"Executing trades or accessing user funds/wallets.","Providing real-time market data feeds (though it uses market context).","Replacing a core trading execution platform; it's a memory layer.","3.0.0","4.4.0","To equip AI trading agents with a persistent, intelligent memory that learns from past trades to inform future decisions, improve performance, and meet regulatory documentation requirements.","All checks passed, indicating a high-quality, well-documented, and secure extension.",100,"A robust and well-documented AI trading memory system with advanced OWM architecture and compliance features.",[211,212,213,214,215],"trading","ai","memory","finance","python","global","verified",[219,220,221,222],"Recording every trade with full context for later analysis.","Recalling similar past trading situations to inform current decisions.","Analyzing trading performance per strategy and identifying behavioral patterns.","Setting up trading plans with conditional triggers and risk parameters.",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":234,"testCoverage":237},{"hasLockfile":225},true,1778693700818,{"descriptionLength":228,"readmeSize":229},400,10941,{"closedIssues90d":8,"forks":231,"hasChangelog":225,"openIssues90d":8,"pushedAt":232,"stars":233},116,1775836242000,877,{"hasNpmPackage":235,"license":236,"smitheryVerified":235},false,"MIT",{"hasCi":225,"hasTests":225},{"updatedAt":239},1778693719816,{"basePath":241,"githubOwner":242,"githubRepo":243,"locale":18,"slug":13,"type":244},"tradememory-plugin/skills/trading-memory","mnemox-ai","tradememory-protocol","skill",{"_creationTime":246,"_id":247,"community":248,"display":249,"identity":253,"parentExtension":256,"providers":257,"relations":268,"tags":270,"workflow":271},1778693539593.1846,"k170vxkqee48k2xq1v55a025nh86nzn7",{"reviewCount":8},{"description":250,"installMethods":251,"name":252,"sourceUrl":14},"Persistent memory + autonomous strategy evolution for AI traders. 200+ trading MCP servers execute. None remember. TradeMemory does.",{"claudeCode":252},"tradememory",{"basePath":254,"githubOwner":242,"githubRepo":243,"locale":18,"slug":254,"type":255},"tradememory-plugin","plugin",null,{"evaluate":258,"extract":263},{"promptVersionExtension":204,"promptVersionScoring":205,"score":259,"tags":260,"targetMarket":216,"tier":217},98,[211,212,213,261,214,262],"strategy","automation",{"commitSha":264,"plugin":265},"HEAD",{"mcpCount":8,"provider":266,"skillCount":267},"classify",3,{"repoId":269},"kd73z11kfekksxyrs8ds0snacs86ncdy",[212,262,214,213,261,211],{"evaluatedAt":272,"extractAt":273,"updatedAt":274},1778693569977,1778693539593,1778693832100,{"evaluate":276,"extract":278},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":277,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":264},{"parentExtensionId":247,"repoId":269},{"_creationTime":281,"_id":269,"identity":282,"providers":283,"workflow":407},1778693533831.6553,{"githubOwner":242,"githubRepo":243,"sourceUrl":14},{"classify":284,"discover":393,"github":396},{"commitSha":264,"extensions":285},[286,316,325,337,345,353,361,369,374],{"basePath":254,"description":250,"displayName":252,"installMethods":287,"rationale":288,"selectedPaths":289,"source":315,"sourceLanguage":18,"type":255},{"claudeCode":252},"plugin manifest at tradememory-plugin/.claude-plugin/plugin.json",[290,293,295,298,300,302,304,307,309,311,313],{"path":291,"priority":292},".claude-plugin/plugin.json","mandatory",{"path":294,"priority":292},"README.md",{"path":296,"priority":297},"skills/evolution-engine/SKILL.md","medium",{"path":299,"priority":297},"skills/risk-management/SKILL.md",{"path":301,"priority":297},"skills/trading-memory/SKILL.md",{"path":303,"priority":292},".mcp.json",{"path":305,"priority":306},"commands/daily-review.md","high",{"path":308,"priority":306},"commands/evolve.md",{"path":310,"priority":306},"commands/performance.md",{"path":312,"priority":306},"commands/recall.md",{"path":314,"priority":306},"commands/record-trade.md","rule",{"basePath":317,"description":318,"displayName":319,"installMethods":320,"rationale":321,"selectedPaths":322,"source":315,"sourceLanguage":18,"type":244},".skills/strategy-validator","Validate trading strategies for overfitting using 4 statistical tests (DSR, Walk-Forward, Regime, CPCV)","strategy-validator",{"claudeCode":12},"SKILL.md frontmatter at .skills/strategy-validator/SKILL.md",[323],{"path":324,"priority":292},"SKILL.md",{"basePath":326,"description":327,"displayName":252,"installMethods":328,"rationale":329,"selectedPaths":330,"source":315,"sourceLanguage":18,"type":244},".skills/tradememory","AI trading memory with outcome-weighted recall and autonomous strategy evolution. 17 MCP tools, 1,233 tests, works with any trading platform.",{"claudeCode":12},"SKILL.md frontmatter at .skills/tradememory/SKILL.md",[331,332,335],{"path":324,"priority":292},{"path":333,"priority":334},"scripts/install.sh","low",{"path":336,"priority":334},"scripts/setup_mt5.sh",{"basePath":338,"description":339,"displayName":340,"installMethods":341,"rationale":342,"selectedPaths":343,"source":315,"sourceLanguage":18,"type":244},"skills/binance-skills-hub/trade-memory","Compliance-grade decision audit trail for AI trading agents. Records every trading decision with full context (conditions, filters, indicators, risk state), SHA-256 tamper detection, and structured export for MiFID II / EU AI Act readiness. Works alongside Binance Spot, Futures, and Web3 skills — they execute trades, TradeMemory records why.","trade-memory",{"claudeCode":12},"SKILL.md frontmatter at skills/binance-skills-hub/trade-memory/SKILL.md",[344],{"path":324,"priority":292},{"basePath":346,"description":347,"displayName":348,"installMethods":349,"rationale":350,"selectedPaths":351,"source":315,"sourceLanguage":18,"type":244},"skills/tradememory-bridge","Bridge between Binance trading events and TradeMemory Protocol.\nAutomatically journals trades, recalls similar past setups, detects behavioral biases,\nand provides outcome-weighted recall for AI trading agents.\nUse this skill after executing Binance spot trades to build persistent memory.\n","tradememory-bridge",{"claudeCode":12},"SKILL.md frontmatter at skills/tradememory-bridge/SKILL.md",[352],{"path":324,"priority":292},{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":315,"sourceLanguage":18,"type":244},"tradememory-plugin/skills/evolution-engine","Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or reviewing evolution logs. Triggers on \"evolve\", \"discover patterns\", \"backtest\", \"evolution\", \"strategy generation\", \"candidate strategy\".","evolution-engine",{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/evolution-engine/SKILL.md",[360],{"path":324,"priority":292},{"basePath":362,"description":363,"displayName":364,"installMethods":365,"rationale":366,"selectedPaths":367,"source":315,"sourceLanguage":18,"type":244},"tradememory-plugin/skills/risk-management","Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on \"risk\", \"drawdown\", \"tilt\", \"position size\", \"lot size\", \"confidence\", \"revenge trading\", \"overtrading\", \"discipline\".","risk-management",{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/risk-management/SKILL.md",[368],{"path":324,"priority":292},{"basePath":241,"description":10,"displayName":13,"installMethods":370,"rationale":371,"selectedPaths":372,"source":315,"sourceLanguage":18,"type":244},{"claudeCode":12},"SKILL.md frontmatter at tradememory-plugin/skills/trading-memory/SKILL.md",[373],{"path":324,"priority":292},{"basePath":375,"displayName":243,"installMethods":376,"rationale":377,"selectedPaths":378,"source":315,"sourceLanguage":18,"type":392},"",{"pypi":243},"server.json with namespace/server name at server.json",[379,381,383,384,386,388,390],{"path":380,"priority":292},"server.json",{"path":382,"priority":292},"pyproject.toml",{"path":294,"priority":292},{"path":385,"priority":306},"LICENSE",{"path":387,"priority":297},"src/tradememory/cli.py",{"path":389,"priority":297},"src/tradememory/server.py",{"path":391,"priority":334},"hosted/server.py","mcp",{"sources":394},[395],"manual",{"closedIssues90d":8,"description":397,"forks":231,"homepage":398,"license":236,"openIssues90d":8,"pushedAt":232,"readmeSize":229,"stars":233,"topics":399},"Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.","https://mnemox.ai/tradememory/",[400,401,392,213,402,211,403,404,356,405,406],"claude","forex","mt5","ai-agents","crypto","mcp-server","outcome-weighted-memory",{"classifiedAt":408,"discoverAt":409,"extractAt":410,"githubAt":410,"updatedAt":408},1778693539413,1778693533831,1778693537570,[212,214,213,215,211],{"evaluatedAt":239,"extractAt":273,"updatedAt":413},1778693833320,[],[416,445,465,484,506,527],{"_creationTime":417,"_id":418,"community":419,"display":420,"identity":426,"providers":431,"relations":438,"tags":441,"workflow":442},1778696691708.3274,"k170az7r02e9e2v47mpy80kx6n86nff3",{"reviewCount":8},{"description":421,"installMethods":422,"name":424,"sourceUrl":425},"Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy",{"claudeCode":423},"ruvnet/ruflo","Trader Regime","https://github.com/ruvnet/ruflo",{"basePath":427,"githubOwner":428,"githubRepo":429,"locale":18,"slug":430,"type":244},"plugins/ruflo-neural-trader/skills/trader-regime","ruvnet","ruflo","trader-regime",{"evaluate":432,"extract":437},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":433,"targetMarket":216,"tier":217},[214,211,434,212,435,436],"market-analysis","typescript","cli",{"commitSha":264,"license":236},{"parentExtensionId":439,"repoId":440},"k17drge8h1fgzchr0p4jaeg33n86mwmy","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[212,436,214,434,211,435],{"evaluatedAt":443,"extractAt":444,"updatedAt":443},1778701108877,1778696691708,{"_creationTime":446,"_id":447,"community":448,"display":449,"identity":452,"providers":453,"relations":460,"tags":461,"workflow":462},1778693539593.1858,"k171p5pgbfbm5g4k5sa3y4cj9s86m6hk",{"reviewCount":8},{"description":355,"installMethods":450,"name":451,"sourceUrl":14},{"claudeCode":12},"TradeMemory Protocol",{"basePath":354,"githubOwner":242,"githubRepo":243,"locale":18,"slug":356,"type":244},{"evaluate":454,"extract":459},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":455,"targetMarket":216,"tier":217},[211,212,213,456,457,458],"audit","compliance","llm",{"commitSha":264,"license":236},{"parentExtensionId":247,"repoId":269},[212,456,457,458,213,211],{"evaluatedAt":463,"extractAt":273,"updatedAt":464},1778693678813,1778693832942,{"_creationTime":466,"_id":467,"community":468,"display":469,"identity":472,"providers":473,"relations":479,"tags":480,"workflow":481},1778693539593.186,"k17bgwvhb6h29py715de1cm9xd86msq6",{"reviewCount":8},{"description":363,"installMethods":470,"name":471,"sourceUrl":14},{"claudeCode":12},"Risk Management",{"basePath":362,"githubOwner":242,"githubRepo":243,"locale":18,"slug":364,"type":244},{"evaluate":474,"extract":478},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":475,"targetMarket":216,"tier":217},[211,364,476,477,214],"ai-agent","behavioral-analysis",{"commitSha":264,"license":236},{"parentExtensionId":247,"repoId":269},[476,477,214,364,211],{"evaluatedAt":482,"extractAt":273,"updatedAt":483},1778693700524,1778693833120,{"_creationTime":485,"_id":486,"community":487,"display":488,"identity":492,"providers":494,"relations":502,"tags":503,"workflow":504},1778696691708.2983,"k17c6tkghtgnr7jnsh6gf5mf9h86nk00",{"reviewCount":8},{"description":489,"installMethods":490,"name":491,"sourceUrl":425},"Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.",{"claudeCode":423},"agentdb-memory-patterns",{"basePath":493,"githubOwner":428,"githubRepo":429,"locale":18,"slug":491,"type":244},".claude/skills/agentdb-memory-patterns",{"evaluate":495,"extract":501},{"promptVersionExtension":204,"promptVersionScoring":205,"score":496,"tags":497,"targetMarket":216,"tier":217},99,[212,498,213,499,435,500],"agent","database","nodejs",{"commitSha":264},{"repoId":440},[498,212,499,213,500,435],{"evaluatedAt":505,"extractAt":444,"updatedAt":505},1778698807267,{"_creationTime":507,"_id":508,"community":509,"display":510,"identity":514,"providers":516,"relations":523,"tags":524,"workflow":525},1778696691708.328,"k172nv5vbyw1c60vavz8f9esw186m2q7",{"reviewCount":8},{"description":511,"installMethods":512,"name":513,"sourceUrl":425},"Generate trading signals using npx neural-trader anomaly detection engine with Z-score scoring and neural prediction",{"claudeCode":423},"trader-signal",{"basePath":515,"githubOwner":428,"githubRepo":429,"locale":18,"slug":513,"type":244},"plugins/ruflo-neural-trader/skills/trader-signal",{"evaluate":517,"extract":522},{"promptVersionExtension":204,"promptVersionScoring":205,"score":496,"tags":518,"targetMarket":216,"tier":217},[211,214,519,520,521],"anomaly-detection","machine-learning","prediction",{"commitSha":264},{"parentExtensionId":439,"repoId":440},[519,214,520,521,211],{"evaluatedAt":526,"extractAt":444,"updatedAt":526},1778701148958,{"_creationTime":528,"_id":529,"community":530,"display":531,"identity":533,"providers":534,"relations":539,"tags":540,"workflow":541},1778693539593.1855,"k17em57x7pnqhv6x3a2s5g5wv586mjq6",{"reviewCount":8},{"description":347,"installMethods":532,"name":348,"sourceUrl":14},{"claudeCode":12},{"basePath":346,"githubOwner":242,"githubRepo":243,"locale":18,"slug":348,"type":244},{"evaluate":535,"extract":538},{"promptVersionExtension":204,"promptVersionScoring":205,"score":496,"tags":536,"targetMarket":216,"tier":217},[211,214,213,537,476],"journaling",{"commitSha":264},{"repoId":269},[476,214,537,213,211],{"evaluatedAt":542,"extractAt":273,"updatedAt":543},1778693660212,1778693832747]