[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-cdeust-cortex-recall-en":3,"guides-for-cdeust-cortex-recall":790,"similar-k173wax2wbgse1sszqwg4x8wz186nhjq-en":791},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":259,"isFallback":255,"parentExtension":264,"providers":320,"relations":324,"repo":325,"tags":788,"workflow":789},1778683562157.8772,"k173wax2wbgse1sszqwg4x8wz186nhjq",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Search and retrieve memories from Cortex persistent memory. Use when the user asks 'what did we decide about X', 'do you remember', 'what was the fix for', 'find that thing about', 'search memories', 'what do we know about', 'have we seen this before', or when you need context about past decisions, patterns, bugs, or architecture choices. Also use proactively when working on something that likely has relevant historical context.",{"claudeCode":12},"cdeust/Cortex","Cortex","https://github.com/cdeust/Cortex",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":239,"workflow":257},1778683785037.8438,"kn7492mhcjxpm2832b3q8zbrqn86n652","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"practices":205,"prerequisites":210,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"targetMarket":226,"tier":227,"useCases":228,"workflow":233},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of losing context and knowledge between sessions and proposes Cortex as a solution to persistent memory for AI agents.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","Cortex offers a unique selling proposition by implementing a neuroscience-inspired memory system with features like rate-distortion optimal forgetting, predictive coding gating, and retrieval-induced reconsolidation, going beyond simple context dumps.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension is production-ready, offering a complete lifecycle for memory management, including installation, setup, verification, and various tools for retrieval and organization.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on persistent memory retrieval and management for AI agents, with related tools and concepts tightly integrated around this core purpose.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description in SKILL.md accurately reflects the extension's functionality and purpose, clearly stating what it does and when to use it.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The tools provided, such as `cortex:recall`, `cortex:recall_hierarchical`, `cortex:navigate_memory`, and `cortex:get_causal_chain`, are narrowly scoped verb-noun specialists.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","Optional filters and parameters for recall functions are clearly documented in SKILL.md, including their purpose and example usage.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names like `cortex:recall` and `cortex:recall_hierarchical` are descriptive and clearly indicate their function.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Tool parameters are structured (e.g., JSON objects with specific keys like `query`, `limit`, `domain`), requesting only necessary data, and outputs are focused on relevant memory content.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is distributed under the MIT license, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits, with the latest push on 2026-05-13, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","Dependencies are managed via a lockfile (`hasLockfile: true`), and the project uses Python 3.10+, with setup scripts and Docker support suggesting good dependency management practices.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension runs locally with no data leaving the machine and no exposed secrets mentioned in the documentation or code structure.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The extension processes natural language queries and structured parameters; there's no indication of loading untrusted third-party data as instructions.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","All code and dependencies appear to be bundled within the repository or managed through standard package installations, with no runtime downloads of external code.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The extension runs locally, interacting with PostgreSQL on localhost and not modifying files outside its defined scope or project folders.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls were observed in the provided documentation or file structure.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension operates locally and does not submit confidential data to any third party; all data processing is contained within the user's environment.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and documentation do not appear to contain hidden steering tricks, invisible Unicode characters, or other obfuscation methods.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The provided code and documentation do not show any signs of obfuscated code execution, such as base64 payloads or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The setup scripts handle environment configuration and PostgreSQL installation, minimizing assumptions about the user's project structure.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 0 issues opened and 16 closed in the last 90 days, the maintainers are actively addressing issues and have a high closure rate.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project clearly indicates its version (v3.15.0) in the README and release notes, and uses a semver scheme.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Input parameters for tools are structured as JSON objects, implying validation and sanitization, though explicit schema library usage isn't detailed.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The extension is primarily focused on reading and retrieving memories; no destructive operations are apparent that would require guarding.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The SKILL.md details different query types and optional filters, implying robust error handling for incorrect inputs or states, though explicit error structures aren't detailed.",{"category":110,"check":114,"severity":115,"summary":116},"Logging","not_applicable","As this extension is primarily a local data retrieval and processing tool, explicit audit logging to a local file is not a standard requirement or feature.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The extension operates locally on user data and does not submit personal data to third parties, thus adhering to GDPR principles.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The extension is designed for local execution and general-purpose memory retrieval, with no regional or jurisdictional restrictions detected.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The extension specifies Python 3.10+ and provides Docker support, indicating good cross-platform compatibility and clear runtime requirements.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README provides an excellent overview of the project, its capabilities, benchmarks, science, and installation instructions.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The skill exposes a focused set of tools (`recall`, `recall_hierarchical`, `navigate_memory`, `get_causal_chain`) suitable for its memory retrieval purpose.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The exposed tools have distinct functionalities (`recall` for basic retrieval, `recall_hierarchical` for broad topics, `navigate_memory` for related knowledge, `get_causal_chain` for cause-and-effect).",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features, such as memory retrieval, hierarchical recall, and causal chain tracing, are supported by corresponding tools and documented functionalities.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for both plugin marketplace and cloning, along with verification steps.",{"category":144,"check":145,"severity":146,"summary":147},"Errors","Actionable error messages","info","While the SKILL.md outlines error paths conceptually, specific actionable error messages with remediation steps are not explicitly detailed.",{"category":103,"check":149,"severity":24,"summary":150},"Pinned dependencies","The project utilizes a lockfile and specifies Python 3.10+, indicating pinned dependencies and interpreter versions.",{"category":33,"check":152,"severity":115,"summary":153},"Dry-run preview","The extension is primarily read-only for memory retrieval, so a dry-run preview is not applicable.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","The extension operates locally and tool calls are likely designed to be idempotent or have retry mechanisms handled by the agent framework; specific timeouts are not detailed but implied by local execution.",{"category":118,"check":159,"severity":24,"summary":160},"Telemetry opt-in","The extension emphasizes local execution and privacy, with no mention of telemetry, implying it is either absent or strictly opt-in.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly states the artifact (Cortex persistent memory) and the user intent (search and retrieve memories) with specific trigger phrases.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter in SKILL.md is concise, self-contained, and accurately summarizes the core capability with relevant trigger phrases.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md content is well-structured and delegates deeper material to separate files (e.g., documentation, papers) while keeping the main procedure concise.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","Deeper scientific explanations, benchmarks, and architectural details are appropriately deferred to separate files and links, following progressive disclosure.",{"category":171,"check":175,"severity":115,"summary":176},"Forked exploration","This skill is focused on direct memory retrieval and does not involve deep code exploration or multi-file inspection that would necessitate `context: fork`.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","SKILL.md and README provide clear usage examples for `cortex:recall`, `cortex:recall_hierarchical`, and other core functionalities, showing input and expected parameters.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","SKILL.md mentions using specific filters and being precise with queries, implying handling of different retrieval scenarios and implicitly addressing edge cases like broad vs. specific queries.",{"category":91,"check":184,"severity":115,"summary":185},"Tool Fallback","The extension does not rely on external MCP servers or tools that would require a fallback; it is self-contained and runs locally.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The local nature of the tool and its focus on retrieval minimize the risk of unexpected states that would halt workflows. Clear query formulation is emphasized.",{"category":91,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The extension is self-contained for memory retrieval and does not implicitly rely on other skills; it provides tools for interaction rather than assuming their presence.",1778683784918,"Cortex provides a local, persistent memory engine for AI agents, leveraging neuroscience principles for intelligent consolidation, retrieval, and context reconstruction. It includes tools for searching memories, navigating relationships, and tracing causal chains, running on PostgreSQL with pgvector.",[196,197,198,199,200],"Intelligent memory retrieval using WRRF engine","Structured context assembly for long-horizon conversations","Neuroscience-inspired memory mechanisms (forgetting, gating, reconsolidation)","Local execution with PostgreSQL and pgvector backend","Tools for hierarchical recall, causal chain tracing, and knowledge graph navigation",[202,203,204],"Storing memories in a proprietary format or external cloud service.","Replacing the core LLM's reasoning capabilities; it augments them with memory.","Providing general-purpose database functionality beyond memory management.",[206,207,208,209],"Memory Management","Context Reconstruction","AI Agent Augmentation","Local Data Processing",[211,212,213],"PostgreSQL 15+ with pgvector extension","Python 3.10+","Local execution environment","3.0.0","4.4.0","To provide AI agents with a persistent, intelligent memory that reconstructs relevant context from past interactions and decisions, enhancing continuity and understanding across sessions.","The extension is exceptionally well-documented, feature-rich, and robust, with a strong focus on security and user experience. Minor informational findings related to explicit error message structure and dry-run applicability do not detract from its overall high quality.",99,"A highly advanced and well-engineered persistent memory system for AI agents, deeply integrated with neuroscience principles.",[221,222,223,224,225],"memory","retrieval","ai-agent","knowledge-management","local","global","verified",[229,230,231,232],"Use when needing context about past decisions, patterns, or fixes.","Use proactively when starting work on a topic with likely historical context.","Use to reconstruct agent context after session compaction or restarts.","Use to explore project history and relationships via the knowledge graph.",[234,235,236,237,238],"Formulate a natural language query for memory retrieval.","Optionally, specify filters like domain, tags, time range, or store type.","Execute retrieval using `cortex:recall` or `cortex:recall_hierarchical`.","Navigate related memories using `cortex:navigate_memory`.","Trace causal chains using `cortex:get_causal_chain`.",{"codeQuality":240,"collectedAt":242,"documentation":243,"maintenance":246,"popularity":251,"security":253,"testCoverage":256},{"hasLockfile":241},true,1778683769408,{"descriptionLength":244,"readmeSize":245},432,36381,{"closedIssues90d":247,"forks":248,"hasChangelog":241,"openIssues90d":8,"pushedAt":249,"stars":250},16,8,1778675198000,33,{"npmDownloads":252},14,{"hasNpmPackage":241,"license":254,"smitheryVerified":255},"NOASSERTION",false,{"hasCi":241,"hasTests":241},{"updatedAt":258},1778683785037,{"basePath":260,"githubOwner":261,"githubRepo":13,"locale":18,"slug":262,"type":263},"skills/cortex-recall","cdeust","cortex-recall","skill",{"_creationTime":265,"_id":266,"community":267,"display":268,"identity":271,"parentExtension":274,"providers":308,"relations":316,"tags":317,"workflow":318},1778683562157.8752,"k1739s9t9kj9bmjq1z4byk17g986mv7x",{"reviewCount":8},{"description":269,"installMethods":270,"name":13,"sourceUrl":14},"Persistent memory and cognitive profiling for Claude Code — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. 47 MCP tools with enriched schemas. PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. Curated wiki (ADRs, specs, lessons) with audit-artefact filtering. Consolidate is set-based SQL batched — decay/plasticity/pruning run 100-500× faster on large stores. Workflow graph with caller-qualified CALLS chains rendering full method-to-method dependencies (native tree-sitter, no AP required). Side panel humanized for non-technical users. Ingests codebase analysis (ai-automatised-pipeline) and PRDs (prd-spec-generator) into wiki + memory + knowledge graph. Docker image available.",{"claudeCode":13},{"basePath":272,"githubOwner":261,"githubRepo":13,"locale":18,"slug":13,"type":273},"","plugin",{"_creationTime":275,"_id":276,"community":277,"display":278,"identity":282,"providers":284,"relations":302,"tags":304,"workflow":305},1778683562157.875,"k174pnm5ch9ab6fr1etef2f2b586m74b",{"reviewCount":8},{"description":279,"installMethods":280,"name":281,"sourceUrl":14},"Persistent memory and cognitive profiling plugins for Claude Code",{"claudeCode":12},"cortex-plugins",{"basePath":272,"githubOwner":261,"githubRepo":13,"locale":18,"slug":13,"type":283},"marketplace",{"evaluate":285,"extract":296},{"promptVersionExtension":286,"promptVersionScoring":215,"score":287,"tags":288,"targetMarket":226,"tier":227},"3.1.0",100,[221,289,290,291,292,293,294,295],"cognitive-profiling","mcp","claude-code","knowledge-graph","codebase-analysis","postgresql","pgvector",{"commitSha":297,"marketplace":298,"plugin":300},"HEAD",{"name":281,"pluginCount":299},1,{"mcpCount":8,"provider":301,"skillCount":8},"classify",{"repoId":303},"kd79gxpemvkr09a7zsb3h8kmah86nvgf",[291,293,289,292,290,221,295,294],{"evaluatedAt":306,"extractAt":307,"updatedAt":306},1778683583007,1778683562157,{"evaluate":309,"extract":313},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":310,"targetMarket":226,"tier":227},[221,311,292,289,294,295,312],"persistence","developer-tools",{"commitSha":297,"license":314,"plugin":315},"MIT",{"mcpCount":8,"provider":301,"skillCount":252},{"parentExtensionId":276,"repoId":303},[289,312,292,221,311,295,294],{"evaluatedAt":319,"extractAt":307,"updatedAt":319},1778683602463,{"evaluate":321,"extract":323},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":322,"targetMarket":226,"tier":227},[221,222,223,224,225],{"commitSha":297,"license":314},{"parentExtensionId":266,"repoId":303},{"_creationTime":326,"_id":303,"identity":327,"providers":328,"workflow":783},1778683544930.988,{"githubOwner":261,"githubRepo":13,"sourceUrl":14},{"classify":329,"discover":755,"extract":758,"github":759,"npm":782},{"commitSha":297,"extensions":330},[331,344,357,366,374,382,390,398,406,414,419,427,435,443,451,459,467],{"basePath":272,"description":279,"displayName":281,"installMethods":332,"rationale":333,"selectedPaths":334,"source":343,"sourceLanguage":18,"type":283},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[335,338,340],{"path":336,"priority":337},".claude-plugin/marketplace.json","mandatory",{"path":339,"priority":337},"README.md",{"path":341,"priority":342},"LICENSE","high","rule",{"basePath":272,"description":269,"displayName":345,"installMethods":346,"rationale":347,"selectedPaths":348,"source":343,"sourceLanguage":18,"type":273},"cortex",{"claudeCode":13},"inline plugin source from marketplace.json at /",[349,350,351,353,355],{"path":339,"priority":337},{"path":341,"priority":342},{"path":352,"priority":337},".mcp.json",{"path":354,"priority":342},"agents/cortex-wiki-groomer.md",{"path":356,"priority":342},"commands/methodology.md",{"basePath":358,"description":359,"displayName":360,"installMethods":361,"rationale":362,"selectedPaths":363,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-automate","Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to automate memory behavior based on conditions.","cortex-automate",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-automate/SKILL.md",[364],{"path":365,"priority":337},"SKILL.md",{"basePath":367,"description":368,"displayName":369,"installMethods":370,"rationale":371,"selectedPaths":372,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-consolidate","Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or periodically to keep the memory system healthy. Also use after importing many memories or at the end of a long session.","cortex-consolidate",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-consolidate/SKILL.md",[373],{"path":365,"priority":337},{"basePath":375,"description":376,"displayName":377,"installMethods":378,"rationale":379,"selectedPaths":380,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-debug-memory","Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality', 'rate this memory', 'restore checkpoint', 'undo', or when memories are returning incorrect or stale results.","cortex-debug-memory",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-debug-memory/SKILL.md",[381],{"path":365,"priority":337},{"basePath":383,"description":384,"displayName":385,"installMethods":386,"rationale":387,"selectedPaths":388,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-explore-memory","Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you need to understand the state of stored knowledge before a task.","cortex-explore-memory",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-explore-memory/SKILL.md",[389],{"path":365,"priority":337},{"basePath":391,"description":392,"displayName":393,"installMethods":394,"rationale":395,"selectedPaths":396,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-import","Import memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories', 'import ChatGPT history', 'import from Gemini', 'transfer memories', or when Cortex detects another memory system is installed.","cortex-import",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-import/SKILL.md",[397],{"path":365,"priority":337},{"basePath":399,"description":400,"displayName":401,"installMethods":402,"rationale":403,"selectedPaths":404,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-navigate-knowledge","Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what caused X', 'drill down into', 'explore connections', or when you need to understand the web of relationships between concepts, entities, and memories.","cortex-navigate-knowledge",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-navigate-knowledge/SKILL.md",[405],{"path":365,"priority":337},{"basePath":407,"description":408,"displayName":409,"installMethods":410,"rationale":411,"selectedPaths":412,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-profile","View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile' to rescan all session history, or 'list domains' to see all tracked project domains.","cortex-profile",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-profile/SKILL.md",[413],{"path":365,"priority":337},{"basePath":260,"description":10,"displayName":262,"installMethods":415,"rationale":416,"selectedPaths":417,"source":343,"sourceLanguage":18,"type":263},{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-recall/SKILL.md",[418],{"path":365,"priority":337},{"basePath":420,"description":421,"displayName":422,"installMethods":423,"rationale":424,"selectedPaths":425,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-recall-global","Search and retrieve global memories — knowledge that applies across all projects. Use when the user asks 'what are our coding standards', 'what conventions do we follow', 'what's our infrastructure setup', 'do we have a rule about', 'what applies to all projects', 'shared knowledge', 'global rules', or when you need cross-project context like architecture decisions, server configs, or team policies.","cortex-recall-global",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-recall-global/SKILL.md",[426],{"path":365,"priority":337},{"basePath":428,"description":429,"displayName":430,"installMethods":431,"rationale":432,"selectedPaths":433,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-remember","Store important decisions, patterns, errors, lessons, and context into Cortex persistent memory. Use when the user says 'remember this', 'save this', 'store this for later', 'note this down', 'don't forget', 'this is important', 'bookmark this', or when a significant decision, bug fix, architecture choice, or lesson learned occurs during a session. Also use after resolving tricky bugs, making technology choices, or discovering important patterns.","cortex-remember",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-remember/SKILL.md",[434],{"path":365,"priority":337},{"basePath":436,"description":437,"displayName":438,"installMethods":439,"rationale":440,"selectedPaths":441,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-remember-global","Store a global memory that is visible across all projects. Use when the user shares architecture rules, coding conventions, infrastructure facts, security policies, team agreements, or any knowledge that applies beyond a single project. Triggers on 'remember this everywhere', 'this applies to all projects', 'global rule', 'shared convention', 'infrastructure note', 'cross-project', or when the content is clearly universal (clean architecture, SOLID, deployment configs, server addresses).","cortex-remember-global",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-remember-global/SKILL.md",[442],{"path":365,"priority":337},{"basePath":444,"description":445,"displayName":446,"installMethods":447,"rationale":448,"selectedPaths":449,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-setup-project","Bootstrap Cortex for a new project or import existing session history. Use when the user says 'set up Cortex', 'seed this project', 'import my history', 'backfill memories', 'bootstrap memory', 'initialize Cortex for this project', or when starting to use Cortex on an existing codebase that already has Claude Code conversation history.","cortex-setup-project",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-setup-project/SKILL.md",[450],{"path":365,"priority":337},{"basePath":452,"description":453,"displayName":454,"installMethods":455,"rationale":456,"selectedPaths":457,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-visualize","Launch the interactive unified neural graph visualization. Use when the user says 'show visualization', 'show me the graph', 'visualize memories', 'show memory map', 'open neural graph', or when a visual overview of the memory system or cognitive profile would be helpful.","cortex-visualize",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-visualize/SKILL.md",[458],{"path":365,"priority":337},{"basePath":460,"description":461,"displayName":462,"installMethods":463,"rationale":464,"selectedPaths":465,"source":343,"sourceLanguage":18,"type":263},"skills/cortex-wiki-author","Author first-class wiki pages (ADRs, specs, file docs, notes) that live alongside Cortex memory. Use when the user says 'this is an ADR', 'document this decision', 'write an ADR', 'add a spec', 'spec this out', 'document this file', 'add a note about', 'link these pages', 'bookmark this as a spec', or when finalizing a design decision that should persist as a human-readable document.","cortex-wiki-author",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-wiki-author/SKILL.md",[466],{"path":365,"priority":337},{"basePath":272,"description":468,"displayName":469,"installMethods":470,"license":314,"rationale":471,"selectedPaths":472,"source":343,"sourceLanguage":18,"type":290},"Persistent memory and cognitive profiling for Claude Code","neuro-cortex-memory",{"pypi":469},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[473,475,477,478,479,482,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745,747,749,751,753],{"path":474,"priority":337},"package.json",{"path":476,"priority":337},"pyproject.toml",{"path":339,"priority":337},{"path":341,"priority":342},{"path":480,"priority":481},"mcp_server/doctor.py","medium",{"path":483,"priority":484},"mcp_server/__main__.py","low",{"path":486,"priority":484},"mcp_server/handlers/__init__.py",{"path":488,"priority":484},"mcp_server/handlers/_telemetry_wrap.py",{"path":490,"priority":484},"mcp_server/handlers/_tool_meta.py",{"path":492,"priority":484},"mcp_server/handlers/add_rule.py",{"path":494,"priority":484},"mcp_server/handlers/admission.py",{"path":496,"priority":484},"mcp_server/handlers/anchor.py",{"path":498,"priority":484},"mcp_server/handlers/assess_coverage.py",{"path":500,"priority":484},"mcp_server/handlers/backfill_helpers.py",{"path":502,"priority":484},"mcp_server/handlers/backfill_memories.py",{"path":504,"priority":484},"mcp_server/handlers/change_impact.py",{"path":506,"priority":484},"mcp_server/handlers/checkpoint.py",{"path":508,"priority":484},"mcp_server/handlers/codebase_analyze.py",{"path":510,"priority":484},"mcp_server/handlers/codebase_analyze_helpers.py",{"path":512,"priority":484},"mcp_server/handlers/consolidate.py",{"path":514,"priority":484},"mcp_server/handlers/consolidation/__init__.py",{"path":516,"priority":484},"mcp_server/handlers/consolidation/cascade.py",{"path":518,"priority":484},"mcp_server/handlers/consolidation/cls.py",{"path":520,"priority":484},"mcp_server/handlers/consolidation/compression.py",{"path":522,"priority":484},"mcp_server/handlers/consolidation/decay.py",{"path":524,"priority":484},"mcp_server/handlers/consolidation/homeostatic.py",{"path":526,"priority":484},"mcp_server/handlers/consolidation/memify.py",{"path":528,"priority":484},"mcp_server/handlers/consolidation/plasticity.py",{"path":530,"priority":484},"mcp_server/handlers/consolidation/pruning.py",{"path":532,"priority":484},"mcp_server/handlers/consolidation/sleep.py",{"path":534,"priority":484},"mcp_server/handlers/consolidation/transfer.py",{"path":536,"priority":484},"mcp_server/handlers/create_trigger.py",{"path":538,"priority":484},"mcp_server/handlers/detect_domain.py",{"path":540,"priority":484},"mcp_server/handlers/detect_gaps.py",{"path":542,"priority":484},"mcp_server/handlers/drill_down.py",{"path":544,"priority":484},"mcp_server/handlers/explore_features.py",{"path":546,"priority":484},"mcp_server/handlers/forget.py",{"path":548,"priority":484},"mcp_server/handlers/get_causal_chain.py",{"path":550,"priority":484},"mcp_server/handlers/get_methodology_graph.py",{"path":552,"priority":484},"mcp_server/handlers/get_project_story.py",{"path":554,"priority":484},"mcp_server/handlers/get_rules.py",{"path":556,"priority":484},"mcp_server/handlers/get_telemetry.py",{"path":558,"priority":484},"mcp_server/handlers/import_sessions.py",{"path":560,"priority":484},"mcp_server/handlers/ingest_codebase.py",{"path":562,"priority":484},"mcp_server/handlers/ingest_codebase_cypher.py",{"path":564,"priority":484},"mcp_server/handlers/ingest_codebase_graph.py",{"path":566,"priority":484},"mcp_server/handlers/ingest_codebase_pages.py",{"path":568,"priority":484},"mcp_server/handlers/ingest_codebase_schema.py",{"path":570,"priority":484},"mcp_server/handlers/ingest_codebase_writers.py",{"path":572,"priority":484},"mcp_server/handlers/ingest_helpers.py",{"path":574,"priority":484},"mcp_server/handlers/ingest_prd.py",{"path":576,"priority":484},"mcp_server/handlers/latency_class.py",{"path":578,"priority":484},"mcp_server/handlers/list_domains.py",{"path":580,"priority":484},"mcp_server/handlers/memories_facets.py",{"path":582,"priority":484},"mcp_server/handlers/memories_page.py",{"path":584,"priority":484},"mcp_server/handlers/memory_stats.py",{"path":586,"priority":484},"mcp_server/handlers/narrative.py",{"path":588,"priority":484},"mcp_server/handlers/navigate_memory.py",{"path":590,"priority":484},"mcp_server/handlers/open_visualization.py",{"path":592,"priority":484},"mcp_server/handlers/quadtree_handler.py",{"path":594,"priority":484},"mcp_server/handlers/query_methodology.py",{"path":596,"priority":484},"mcp_server/handlers/query_workflow_graph.py",{"path":598,"priority":484},"mcp_server/handlers/rate_memory.py",{"path":600,"priority":484},"mcp_server/handlers/rebuild_profiles.py",{"path":602,"priority":484},"mcp_server/handlers/recall.py",{"path":604,"priority":484},"mcp_server/handlers/recall_helpers.py",{"path":606,"priority":484},"mcp_server/handlers/recall_hierarchical.py",{"path":608,"priority":484},"mcp_server/handlers/recompute_layout.py",{"path":610,"priority":484},"mcp_server/handlers/record_session_end.py",{"path":612,"priority":484},"mcp_server/handlers/remember.py",{"path":614,"priority":484},"mcp_server/handlers/remember_helpers.py",{"path":616,"priority":484},"mcp_server/handlers/remember_response.py",{"path":618,"priority":484},"mcp_server/handlers/seed_project.py",{"path":620,"priority":484},"mcp_server/handlers/seed_project_constants.py",{"path":622,"priority":484},"mcp_server/handlers/seed_project_stages.py",{"path":624,"priority":484},"mcp_server/handlers/sync_instructions.py",{"path":626,"priority":484},"mcp_server/handlers/tile_handler.py",{"path":628,"priority":484},"mcp_server/handlers/unified_search.py",{"path":630,"priority":484},"mcp_server/handlers/validate_memory.py",{"path":632,"priority":484},"mcp_server/handlers/wiki_adr.py",{"path":634,"priority":484},"mcp_server/handlers/wiki_api.py",{"path":636,"priority":484},"mcp_server/handlers/wiki_compile.py",{"path":638,"priority":484},"mcp_server/handlers/wiki_consolidate.py",{"path":640,"priority":484},"mcp_server/handlers/wiki_curate.py",{"path":642,"priority":484},"mcp_server/handlers/wiki_emerge.py",{"path":644,"priority":484},"mcp_server/handlers/wiki_export.py",{"path":646,"priority":484},"mcp_server/handlers/wiki_extract.py",{"path":648,"priority":484},"mcp_server/handlers/wiki_link.py",{"path":650,"priority":484},"mcp_server/handlers/wiki_list.py",{"path":652,"priority":484},"mcp_server/handlers/wiki_migrate.py",{"path":654,"priority":484},"mcp_server/handlers/wiki_pipeline.py",{"path":656,"priority":484},"mcp_server/handlers/wiki_purge.py",{"path":658,"priority":484},"mcp_server/handlers/wiki_read.py",{"path":660,"priority":484},"mcp_server/handlers/wiki_refine.py",{"path":662,"priority":484},"mcp_server/handlers/wiki_reindex.py",{"path":664,"priority":484},"mcp_server/handlers/wiki_rename.py",{"path":666,"priority":484},"mcp_server/handlers/wiki_resolve.py",{"path":668,"priority":484},"mcp_server/handlers/wiki_seed_codebase.py",{"path":670,"priority":484},"mcp_server/handlers/wiki_synthesize.py",{"path":672,"priority":484},"mcp_server/handlers/wiki_verify.py",{"path":674,"priority":484},"mcp_server/handlers/wiki_view.py",{"path":676,"priority":484},"mcp_server/handlers/wiki_write.py",{"path":678,"priority":484},"mcp_server/handlers/workflow_graph.py",{"path":680,"priority":484},"tests_py/handlers/__init__.py",{"path":682,"priority":484},"tests_py/handlers/test_a3_homeostatic_scalar.py",{"path":684,"priority":484},"tests_py/handlers/test_admission.py",{"path":686,"priority":484},"tests_py/handlers/test_backfill_discover_files_issue15.py",{"path":688,"priority":484},"tests_py/handlers/test_backfill_heat.py",{"path":690,"priority":484},"tests_py/handlers/test_beam_anticheat.py",{"path":692,"priority":484},"tests_py/handlers/test_checkpoint.py",{"path":694,"priority":484},"tests_py/handlers/test_cls_diagnostics.py",{"path":696,"priority":484},"tests_py/handlers/test_codebase_analyze_rglob.py",{"path":698,"priority":484},"tests_py/handlers/test_consolidate.py",{"path":700,"priority":484},"tests_py/handlers/test_consolidate_telemetry.py",{"path":702,"priority":484},"tests_py/handlers/test_detect_domain.py",{"path":704,"priority":484},"tests_py/handlers/test_explore_features.py",{"path":706,"priority":484},"tests_py/handlers/test_get_methodology_graph.py",{"path":708,"priority":484},"tests_py/handlers/test_get_telemetry.py",{"path":710,"priority":484},"tests_py/handlers/test_import_sessions.py",{"path":712,"priority":484},"tests_py/handlers/test_import_sessions_stream.py",{"path":714,"priority":484},"tests_py/handlers/test_ingest_codebase.py",{"path":716,"priority":484},"tests_py/handlers/test_ingest_prd.py",{"path":718,"priority":484},"tests_py/handlers/test_latency_class.py",{"path":720,"priority":484},"tests_py/handlers/test_list_domains.py",{"path":722,"priority":484},"tests_py/handlers/test_memify_diagnostics.py",{"path":724,"priority":484},"tests_py/handlers/test_memory_stats.py",{"path":726,"priority":484},"tests_py/handlers/test_open_visualization.py",{"path":728,"priority":484},"tests_py/handlers/test_query_methodology.py",{"path":730,"priority":484},"tests_py/handlers/test_query_workflow_graph.py",{"path":732,"priority":484},"tests_py/handlers/test_rebuild_profiles.py",{"path":734,"priority":484},"tests_py/handlers/test_recall.py",{"path":736,"priority":484},"tests_py/handlers/test_recall_enhancements.py",{"path":738,"priority":484},"tests_py/handlers/test_recall_hierarchical_bounded.py",{"path":740,"priority":484},"tests_py/handlers/test_recall_low_signal_filter.py",{"path":742,"priority":484},"tests_py/handlers/test_record_session_end.py",{"path":744,"priority":484},"tests_py/handlers/test_registry.py",{"path":746,"priority":484},"tests_py/handlers/test_remember.py",{"path":748,"priority":484},"tests_py/handlers/test_seed_project.py",{"path":750,"priority":484},"tests_py/handlers/test_wiki_redirect_handlers.py",{"path":752,"priority":484},"tests_py/handlers/test_wiki_seed_codebase.py",{"path":754,"priority":484},"tests_py/handlers/test_wiki_sync_errors.py",{"sources":756},[757],"manual",{"npmPackage":469},{"closedIssues90d":247,"description":760,"forks":248,"homepage":761,"license":254,"openIssues90d":8,"pushedAt":249,"readmeSize":245,"stars":250,"topics":762},"Persistent memory for Claude Code — 41 neuroscience papers, 26 biological mechanisms with paper-bearing per-mechanism ablation evidence (E1 v3). LongMemEval R@10 98.4% / MRR 0.9124 (n=500). LoCoMo R@10 94.2% / MRR 0.8278 (n=1986). BEAM-10M +33.4% over flat retrieval. PostgreSQL + pgvector. Verified via 31-row two-benchmark ablation campaign.","https://ai-architect.tools",[763,764,765,766,291,767,768,769,770,771,772,773,774,775,776,777,778,779,780,781],"mcp-server","model-context-protocol","agent-memory-system","causal-inference","claude-code-plugin","cognitive-architecture","cognitive-science","neuroscience","persistent-memory","predictive-coding","retrieval-augmented-generation","vector-search","hopfield-network","long-term-memory","episodic-memory","llm-memory","anthropic","artificial-intelligence","claude",{"downloads":252},{"classifiedAt":784,"discoverAt":785,"extractAt":786,"githubAt":786,"npmAt":787,"updatedAt":784},1778683561790,1778683544931,1778683554398,1778683559402,[223,224,225,221,222],{"evaluatedAt":258,"extractAt":307,"updatedAt":258},[],[792,820,848,866,892,909],{"_creationTime":793,"_id":794,"community":795,"display":796,"identity":802,"providers":806,"relations":813,"tags":816,"workflow":817},1778696595410.5657,"k17bk9m02r7jkbzzqapbzfvq8h86m6qn",{"reviewCount":8},{"description":797,"installMethods":798,"name":800,"sourceUrl":801},"Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.",{"claudeCode":799},"rohitg00/pro-workflow","orchestrate","https://github.com/rohitg00/pro-workflow",{"basePath":803,"githubOwner":804,"githubRepo":805,"locale":18,"slug":800,"type":263},"skills/orchestrate","rohitg00","pro-workflow",{"evaluate":807,"extract":812},{"promptVersionExtension":214,"promptVersionScoring":215,"score":287,"tags":808,"targetMarket":226,"tier":227},[809,810,811,221,224],"llm-ops","agent","workflow",{"commitSha":297},{"parentExtensionId":814,"repoId":815},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[810,224,809,221,811],{"evaluatedAt":818,"extractAt":819,"updatedAt":818},1778696881233,1778696595410,{"_creationTime":821,"_id":822,"community":823,"display":824,"identity":830,"providers":834,"relations":841,"tags":844,"workflow":845},1778675056600.238,"k17bzapecn7k6jdgt1ag6rda2s86m06p",{"reviewCount":8},{"description":825,"installMethods":826,"name":828,"sourceUrl":829},"Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.",{"claudeCode":827},"alirezarezvani/claude-skills","rag-architect","https://github.com/alirezarezvani/claude-skills",{"basePath":831,"githubOwner":832,"githubRepo":833,"locale":18,"slug":828,"type":263},"engineering/skills/rag-architect","alirezarezvani","claude-skills",{"evaluate":835,"extract":840},{"promptVersionExtension":214,"promptVersionScoring":215,"score":287,"tags":836,"targetMarket":226,"tier":227},[837,838,839,774,222,224],"rag","llm","embedding",{"commitSha":297},{"parentExtensionId":842,"repoId":843},"k173223hfbd6c4mx6r1jdx23wn86mbpb","kd7ff9s1w43mfyy1n7hf87816186m6px",[839,224,838,837,222,774],{"evaluatedAt":846,"extractAt":847,"updatedAt":846},1778678924736,1778675056600,{"_creationTime":849,"_id":850,"community":851,"display":852,"identity":855,"providers":856,"relations":862,"tags":863,"workflow":864},1778683562157.876,"k1773yt8sw9dadgz7yjmazhcsn86nzzr",{"reviewCount":8},{"description":376,"installMethods":853,"name":854,"sourceUrl":14},{"claudeCode":12},"Cortex Debug Memory",{"basePath":375,"githubOwner":261,"githubRepo":13,"locale":18,"slug":377,"type":263},{"evaluate":857,"extract":861},{"promptVersionExtension":214,"promptVersionScoring":215,"score":287,"tags":858,"targetMarket":226,"tier":227},[221,859,222,860,345],"debugging","management",{"commitSha":297,"license":314},{"parentExtensionId":266,"repoId":303},[345,859,860,221,222],{"evaluatedAt":865,"extractAt":307,"updatedAt":865},1778683671375,{"_creationTime":867,"_id":868,"community":869,"display":870,"identity":876,"providers":880,"relations":886,"tags":888,"workflow":889},1778696691708.3027,"k174mp6hf33cptbna2p91t2ts586n4ad",{"reviewCount":8},{"description":871,"installMethods":872,"name":874,"sourceUrl":875},"AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.\n",{"claudeCode":873},"ruvnet/ruflo","memory-management","https://github.com/ruvnet/ruflo",{"basePath":877,"githubOwner":878,"githubRepo":879,"locale":18,"slug":874,"type":263},".agents/skills/memory-management","ruvnet","ruflo",{"evaluate":881,"extract":885},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":882,"targetMarket":226,"tier":227},[221,774,224,883,884],"agentdb","hnsw",{"commitSha":297},{"repoId":887},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[883,884,224,221,774],{"evaluatedAt":890,"extractAt":891,"updatedAt":890},1778699160670,1778696691708,{"_creationTime":893,"_id":894,"community":895,"display":896,"identity":898,"providers":899,"relations":905,"tags":906,"workflow":907},1778683562157.878,"k174wwq1x9t40ph56hj32705bh86n96x",{"reviewCount":8},{"description":437,"installMethods":897,"name":438,"sourceUrl":14},{"claudeCode":12},{"basePath":436,"githubOwner":261,"githubRepo":13,"locale":18,"slug":438,"type":263},{"evaluate":900,"extract":904},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":901,"targetMarket":226,"tier":227},[221,224,311,902,225,903],"llm-context","cli",{"commitSha":297},{"parentExtensionId":266,"repoId":303},[903,224,902,225,221,311],{"evaluatedAt":908,"extractAt":307,"updatedAt":908},1778683871550,{"_creationTime":910,"_id":911,"community":912,"display":913,"identity":919,"providers":922,"relations":930,"tags":932,"workflow":933},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":914,"installMethods":915,"name":917,"sourceUrl":918},"Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.",{"claudeCode":916},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":920,"githubOwner":921,"githubRepo":917,"locale":18,"slug":917,"type":263},"skills/lean-ctx","yvgude",{"evaluate":923,"extract":929},{"promptVersionExtension":214,"promptVersionScoring":215,"score":287,"tags":924,"targetMarket":226,"tier":227},[925,223,926,312,927,928],"context-compression","cli-tools","rust","code-analysis",{"commitSha":297},{"repoId":931},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[223,926,928,925,312,927],{"evaluatedAt":934,"extractAt":935,"updatedAt":936},1778699456179,1778699438912,1778699517795]