[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-cdeust-cortex-remember-zh-CN":3,"guides-for-cdeust-cortex-remember":774,"similar-k179k5nma4rnr1eyb1wvh5gzpd86mdas-zh-CN":775},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":225,"parentExtension":248,"providers":304,"relations":308,"repo":309,"tags":772,"workflow":773},1778683562157.8777,"k179k5nma4rnr1eyb1wvh5gzpd86mdas",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"cdeust/Cortex","cortex-remember","https://github.com/cdeust/Cortex",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":241},1778683843680.6116,"kn7eqr7dmz6e4hs2yra8dzg3th86n04z","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},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,112,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states that the skill stores important information into Cortex's memory system, addressing the problem of information loss in AI sessions and the need to retain decisions, bugs, and lessons learned.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over default LLM behavior by providing a persistent memory system with advanced features like a predictive coding gate for filtering noise, deduplication, entity extraction, knowledge graph linking, and intelligent forgetting, which goes beyond simple context storage.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill appears production-ready, with a clear workflow, operational tips, and optional anchoring for critical memories. The accompanying README details advanced features, benchmarks, and setup options, indicating a mature implementation.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on storing and managing information within Cortex's persistent memory system, with clear workflows and related optional features like anchoring and rating memories. It does not extend into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose of storing important decisions, patterns, errors, and context into persistent memory, with clear use-case triggers.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes a single, well-scoped tool `cortex:remember` with clear parameters for content, tags, directory, source, and an optional force flag, adhering to the verb-noun specialist pattern.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md file details the `cortex:remember` tool's parameters (content, tags, directory, source, force) and provides guidelines for content quality and usage, with clear explanations for the optional anchoring tool.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The primary tool `cortex:remember` is descriptively named and adheres to the kebab-case convention.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The `cortex:remember` tool takes structured JSON input for its parameters and returns specific fields like `stored`, `memory_id`, `novelty_score`, and `merged_with`, which are directly related to its function and not diagnostic dumps.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is provided under the MIT license, as indicated in the LICENSE file and README, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository has recent commits, with the last push to the default branch occurring on 2026-05-13, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project lists Python 3.10+ as a requirement and mentions PostgreSQL + pgvector, with a lockfile (`hasLockfile: true`) indicating appropriate dependency management measures are likely in place.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The skill operates locally and manages its own PostgreSQL database, with no indication of handling or echoing sensitive secrets.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill's core functionality is to store provided content as data; there are no indications of loading or executing untrusted external code or data as instructions.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill's operation involves local storage and processing, with no evidence of runtime downloads of uncommitted code or data, or consumption of remote content as instructions.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill operates locally and manages its own data store; there is no indication of it attempting to access or modify files outside its designated project or data directory.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","There are no detected primitives such as detached process spawns or deny-retry loops that would indicate an attempt to escape sandbox limitations.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The skill is designed for local operation and does not submit any user data or confidential information to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content appears to be free of hidden steering tricks, control characters, or invisible Unicode sequences.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The provided source code for the skill and its associated tools appears to be plain, readable, and without obfuscation techniques like base64 encoding or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill operates on provided content and manages its own local data store, not making assumptions about the user's project file structure beyond potentially the working directory for context, which is handled gracefully.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 0 issues opened and 16 closed in the last 90 days, the closure rate is effectively 100%, indicating excellent maintainer engagement with issues.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The project has a clear version number (v3.15.0) in the README and CHANGELOG, indicating a well-managed release process.",{"category":103,"check":104,"severity":24,"summary":105},"Code Execution","Validation","While specific schema validation libraries aren't explicitly detailed in the provided text, the structured JSON input and documented parameter requirements suggest a good level of input validation.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The skill's primary operation is writing to a local database, which is not considered a destructive operation in the context of file system or infrastructure changes, and there are no indications of unguarded destructive primitives.",{"category":103,"check":110,"severity":24,"summary":111},"Error Handling","The skill's workflow and tool descriptions imply structured error handling, with mentions of novelty scores and storage success/failure flags, suggesting it reports errors meaningfully.",{"category":103,"check":113,"severity":114,"summary":115},"Logging","not_applicable","The skill primarily interacts with a local database for memory storage and retrieval; explicit local audit logging is not a standard requirement for this type of operation and is not detailed as a feature.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill operates locally on user-provided content and does not interact with third parties, thus avoiding GDPR concerns related to personal data submission.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill operates locally and processes user-provided content, with no regional or jurisdictional limitations detected, making it globally applicable.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The skill is Python-based and appears to be cross-platform, with no specific OS or shell assumptions beyond standard Python execution environments.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README file is comprehensive, well-structured, and clearly states the extension's purpose, features, and advanced capabilities.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The extension exposes a single primary tool (`cortex:remember`), which is well within the ideal range.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","The extension exposes only one primary tool, so there are no overlapping near-synonym tools.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features, such as memory storage, anchoring, and rating, appear to have corresponding implementations described in the SKILL.md and README.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for Claude Code plugins and Docker, along with verification steps.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The skill's response schema includes fields like `stored: true/false` and provides details on `memory_id` and `novelty_score`, implying structured feedback that aids in understanding the outcome and potential remediation (e.g., content redundancy).",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The presence of a lockfile (`hasLockfile: true`) and explicit version requirements (Python 3.10+) indicate that dependencies are pinned.",{"category":33,"check":151,"severity":114,"summary":152},"Dry-run preview","The skill's primary function is to store data locally and does not involve state-changing operations that would typically benefit from or require a dry-run mode.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The skill operates locally and primarily interacts with its own database. While explicit timeouts and idempotency for database operations are not detailed, the nature of the operation suggests these are likely handled by the underlying PostgreSQL and pgvector setup.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill runs locally and there is no indication of telemetry collection; all operations are contained within the user's environment.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined as storing content into Cortex's persistent memory, with clear triggers like 'remember this' and explicit non-goals implied by its focused functionality.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise and clearly defines the core capability and keywords, providing sufficient information for precise routing without excessive verbosity.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md file is well-structured with clear sections and delegates detailed scientific explanations and benchmarks to separate files, maintaining conciseness.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Detailed scientific explanations and benchmarks are linked or referenced in separate files within the documentation, adhering to progressive disclosure.",{"category":170,"check":174,"severity":114,"summary":175},"Forked exploration","The skill's function is focused on storing memories and does not involve deep exploration or code review that would necessitate a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md provides clear, end-to-end examples for storing memories and anchoring critical ones, showing input, invocation, and expected outcomes.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The SKILL.md addresses edge cases and limitations, such as the novelty gate filtering redundant memories and the option to use a 'force' flag, with clear guidance on when memories might not be stored.",{"category":103,"check":183,"severity":114,"summary":184},"Tool Fallback","This skill does not rely on external MCP servers or custom tools as dependencies; it operates as a self-contained Claude Code skill.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill's design, particularly its use of a novelty gate and clear feedback on storage success/failure, implies a controlled process that would halt or report issues on unexpected states rather than proceeding with potentially corrupt data.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The 'cortex-remember' skill is self-contained and focuses on its memory storage task. Its functionality does not appear to implicitly rely on other skills being loaded, and related skills are referenced explicitly in the broader project documentation.",1778683843557,"This skill allows users to store important decisions, patterns, bugs, and lessons learned into a local, persistent memory system called Cortex. It uses a predictive coding gate to filter noise, handles deduplication, and integrates with a knowledge graph. It also offers optional features like anchoring critical memories and rating their usefulness.",[195,196,197,198,199],"Stores important decisions, patterns, and lessons","Utilizes a predictive coding gate to filter noise","Handles deduplication and knowledge graph linking","Offers optional anchoring for critical memories","Provides feedback on storage success, novelty, and merging",[201,202,203],"Storing trivial or redundant information that is automatically filtered.","Replacing core LLM context management entirely; it enhances it.","Interacting with external services for memory storage or retrieval.","3.0.0","4.4.0","To provide a persistent memory for AI agents, ensuring that important information, decisions, and lessons learned during a session are not lost and can be recalled later, significantly improving context retention and agent effectiveness.","The skill exhibits excellent documentation, security, and maintenance practices. All checks pass or are not applicable, indicating a high-quality extension.",99,"A robust local persistent memory system for AI agents, enhancing context retention and knowledge management.",[211,212,213,214,215],"memory","knowledge-management","persistent-storage","llm-context","ai-productivity","global","verified",[219,220,221,222],"When a significant decision is made during a session.","After resolving a tricky bug or discovering an important pattern.","When the user explicitly asks to remember or save information.","To store context about user preferences or architectural choices.",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"popularity":235,"security":237,"testCoverage":240},{"hasLockfile":225},true,1778683808888,{"descriptionLength":228,"readmeSize":229},450,36381,{"closedIssues90d":231,"forks":232,"hasChangelog":225,"openIssues90d":8,"pushedAt":233,"stars":234},16,8,1778675198000,33,{"npmDownloads":236},14,{"hasNpmPackage":225,"license":238,"smitheryVerified":239},"NOASSERTION",false,{"hasCi":225,"hasTests":225},{"updatedAt":242},1778683843680,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":13,"type":247},"skills/cortex-remember","cdeust","Cortex","skill",{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":255,"parentExtension":258,"providers":292,"relations":300,"tags":301,"workflow":302},1778683562157.8752,"k1739s9t9kj9bmjq1z4byk17g986mv7x",{"reviewCount":8},{"description":253,"installMethods":254,"name":246,"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":246},{"basePath":256,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":257},"","plugin",{"_creationTime":259,"_id":260,"community":261,"display":262,"identity":266,"providers":268,"relations":286,"tags":288,"workflow":289},1778683562157.875,"k174pnm5ch9ab6fr1etef2f2b586m74b",{"reviewCount":8},{"description":263,"installMethods":264,"name":265,"sourceUrl":14},"Persistent memory and cognitive profiling plugins for Claude Code",{"claudeCode":12},"cortex-plugins",{"basePath":256,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":267},"marketplace",{"evaluate":269,"extract":280},{"promptVersionExtension":270,"promptVersionScoring":205,"score":271,"tags":272,"targetMarket":216,"tier":217},"3.1.0",100,[211,273,274,275,276,277,278,279],"cognitive-profiling","mcp","claude-code","knowledge-graph","codebase-analysis","postgresql","pgvector",{"commitSha":281,"marketplace":282,"plugin":284},"HEAD",{"name":265,"pluginCount":283},1,{"mcpCount":8,"provider":285,"skillCount":8},"classify",{"repoId":287},"kd79gxpemvkr09a7zsb3h8kmah86nvgf",[275,277,273,276,274,211,279,278],{"evaluatedAt":290,"extractAt":291,"updatedAt":290},1778683583007,1778683562157,{"evaluate":293,"extract":297},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":294,"targetMarket":216,"tier":217},[211,295,276,273,278,279,296],"persistence","developer-tools",{"commitSha":281,"license":298,"plugin":299},"MIT",{"mcpCount":8,"provider":285,"skillCount":236},{"parentExtensionId":260,"repoId":287},[273,296,276,211,295,279,278],{"evaluatedAt":303,"extractAt":291,"updatedAt":303},1778683602463,{"evaluate":305,"extract":307},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":306,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":281},{"parentExtensionId":250,"repoId":287},{"_creationTime":310,"_id":287,"identity":311,"providers":312,"workflow":767},1778683544930.988,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":313,"discover":739,"extract":742,"github":743,"npm":766},{"commitSha":281,"extensions":314},[315,328,341,350,358,366,374,382,390,398,406,414,419,427,435,443,451],{"basePath":256,"description":263,"displayName":265,"installMethods":316,"rationale":317,"selectedPaths":318,"source":327,"sourceLanguage":18,"type":267},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[319,322,324],{"path":320,"priority":321},".claude-plugin/marketplace.json","mandatory",{"path":323,"priority":321},"README.md",{"path":325,"priority":326},"LICENSE","high","rule",{"basePath":256,"description":253,"displayName":329,"installMethods":330,"rationale":331,"selectedPaths":332,"source":327,"sourceLanguage":18,"type":257},"cortex",{"claudeCode":246},"inline plugin source from marketplace.json at /",[333,334,335,337,339],{"path":323,"priority":321},{"path":325,"priority":326},{"path":336,"priority":321},".mcp.json",{"path":338,"priority":326},"agents/cortex-wiki-groomer.md",{"path":340,"priority":326},"commands/methodology.md",{"basePath":342,"description":343,"displayName":344,"installMethods":345,"rationale":346,"selectedPaths":347,"source":327,"sourceLanguage":18,"type":247},"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",[348],{"path":349,"priority":321},"SKILL.md",{"basePath":351,"description":352,"displayName":353,"installMethods":354,"rationale":355,"selectedPaths":356,"source":327,"sourceLanguage":18,"type":247},"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",[357],{"path":349,"priority":321},{"basePath":359,"description":360,"displayName":361,"installMethods":362,"rationale":363,"selectedPaths":364,"source":327,"sourceLanguage":18,"type":247},"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",[365],{"path":349,"priority":321},{"basePath":367,"description":368,"displayName":369,"installMethods":370,"rationale":371,"selectedPaths":372,"source":327,"sourceLanguage":18,"type":247},"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",[373],{"path":349,"priority":321},{"basePath":375,"description":376,"displayName":377,"installMethods":378,"rationale":379,"selectedPaths":380,"source":327,"sourceLanguage":18,"type":247},"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",[381],{"path":349,"priority":321},{"basePath":383,"description":384,"displayName":385,"installMethods":386,"rationale":387,"selectedPaths":388,"source":327,"sourceLanguage":18,"type":247},"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",[389],{"path":349,"priority":321},{"basePath":391,"description":392,"displayName":393,"installMethods":394,"rationale":395,"selectedPaths":396,"source":327,"sourceLanguage":18,"type":247},"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",[397],{"path":349,"priority":321},{"basePath":399,"description":400,"displayName":401,"installMethods":402,"rationale":403,"selectedPaths":404,"source":327,"sourceLanguage":18,"type":247},"skills/cortex-recall","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.","cortex-recall",{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-recall/SKILL.md",[405],{"path":349,"priority":321},{"basePath":407,"description":408,"displayName":409,"installMethods":410,"rationale":411,"selectedPaths":412,"source":327,"sourceLanguage":18,"type":247},"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",[413],{"path":349,"priority":321},{"basePath":244,"description":10,"displayName":13,"installMethods":415,"rationale":416,"selectedPaths":417,"source":327,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-remember/SKILL.md",[418],{"path":349,"priority":321},{"basePath":420,"description":421,"displayName":422,"installMethods":423,"rationale":424,"selectedPaths":425,"source":327,"sourceLanguage":18,"type":247},"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",[426],{"path":349,"priority":321},{"basePath":428,"description":429,"displayName":430,"installMethods":431,"rationale":432,"selectedPaths":433,"source":327,"sourceLanguage":18,"type":247},"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",[434],{"path":349,"priority":321},{"basePath":436,"description":437,"displayName":438,"installMethods":439,"rationale":440,"selectedPaths":441,"source":327,"sourceLanguage":18,"type":247},"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",[442],{"path":349,"priority":321},{"basePath":444,"description":445,"displayName":446,"installMethods":447,"rationale":448,"selectedPaths":449,"source":327,"sourceLanguage":18,"type":247},"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",[450],{"path":349,"priority":321},{"basePath":256,"description":452,"displayName":453,"installMethods":454,"license":298,"rationale":455,"selectedPaths":456,"source":327,"sourceLanguage":18,"type":274},"Persistent memory and cognitive profiling for Claude Code","neuro-cortex-memory",{"pypi":453},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[457,459,461,462,463,466,469,471,473,475,477,479,481,483,485,487,489,491,493,495,497,499,501,503,505,507,509,511,513,515,517,519,521,523,525,527,529,531,533,535,537,539,541,543,545,547,549,551,553,555,557,559,561,563,565,567,569,571,573,575,577,579,581,583,585,587,589,591,593,595,597,599,601,603,605,607,609,611,613,615,617,619,621,623,625,627,629,631,633,635,637,639,641,643,645,647,649,651,653,655,657,659,661,663,665,667,669,671,673,675,677,679,681,683,685,687,689,691,693,695,697,699,701,703,705,707,709,711,713,715,717,719,721,723,725,727,729,731,733,735,737],{"path":458,"priority":321},"package.json",{"path":460,"priority":321},"pyproject.toml",{"path":323,"priority":321},{"path":325,"priority":326},{"path":464,"priority":465},"mcp_server/doctor.py","medium",{"path":467,"priority":468},"mcp_server/__main__.py","low",{"path":470,"priority":468},"mcp_server/handlers/__init__.py",{"path":472,"priority":468},"mcp_server/handlers/_telemetry_wrap.py",{"path":474,"priority":468},"mcp_server/handlers/_tool_meta.py",{"path":476,"priority":468},"mcp_server/handlers/add_rule.py",{"path":478,"priority":468},"mcp_server/handlers/admission.py",{"path":480,"priority":468},"mcp_server/handlers/anchor.py",{"path":482,"priority":468},"mcp_server/handlers/assess_coverage.py",{"path":484,"priority":468},"mcp_server/handlers/backfill_helpers.py",{"path":486,"priority":468},"mcp_server/handlers/backfill_memories.py",{"path":488,"priority":468},"mcp_server/handlers/change_impact.py",{"path":490,"priority":468},"mcp_server/handlers/checkpoint.py",{"path":492,"priority":468},"mcp_server/handlers/codebase_analyze.py",{"path":494,"priority":468},"mcp_server/handlers/codebase_analyze_helpers.py",{"path":496,"priority":468},"mcp_server/handlers/consolidate.py",{"path":498,"priority":468},"mcp_server/handlers/consolidation/__init__.py",{"path":500,"priority":468},"mcp_server/handlers/consolidation/cascade.py",{"path":502,"priority":468},"mcp_server/handlers/consolidation/cls.py",{"path":504,"priority":468},"mcp_server/handlers/consolidation/compression.py",{"path":506,"priority":468},"mcp_server/handlers/consolidation/decay.py",{"path":508,"priority":468},"mcp_server/handlers/consolidation/homeostatic.py",{"path":510,"priority":468},"mcp_server/handlers/consolidation/memify.py",{"path":512,"priority":468},"mcp_server/handlers/consolidation/plasticity.py",{"path":514,"priority":468},"mcp_server/handlers/consolidation/pruning.py",{"path":516,"priority":468},"mcp_server/handlers/consolidation/sleep.py",{"path":518,"priority":468},"mcp_server/handlers/consolidation/transfer.py",{"path":520,"priority":468},"mcp_server/handlers/create_trigger.py",{"path":522,"priority":468},"mcp_server/handlers/detect_domain.py",{"path":524,"priority":468},"mcp_server/handlers/detect_gaps.py",{"path":526,"priority":468},"mcp_server/handlers/drill_down.py",{"path":528,"priority":468},"mcp_server/handlers/explore_features.py",{"path":530,"priority":468},"mcp_server/handlers/forget.py",{"path":532,"priority":468},"mcp_server/handlers/get_causal_chain.py",{"path":534,"priority":468},"mcp_server/handlers/get_methodology_graph.py",{"path":536,"priority":468},"mcp_server/handlers/get_project_story.py",{"path":538,"priority":468},"mcp_server/handlers/get_rules.py",{"path":540,"priority":468},"mcp_server/handlers/get_telemetry.py",{"path":542,"priority":468},"mcp_server/handlers/import_sessions.py",{"path":544,"priority":468},"mcp_server/handlers/ingest_codebase.py",{"path":546,"priority":468},"mcp_server/handlers/ingest_codebase_cypher.py",{"path":548,"priority":468},"mcp_server/handlers/ingest_codebase_graph.py",{"path":550,"priority":468},"mcp_server/handlers/ingest_codebase_pages.py",{"path":552,"priority":468},"mcp_server/handlers/ingest_codebase_schema.py",{"path":554,"priority":468},"mcp_server/handlers/ingest_codebase_writers.py",{"path":556,"priority":468},"mcp_server/handlers/ingest_helpers.py",{"path":558,"priority":468},"mcp_server/handlers/ingest_prd.py",{"path":560,"priority":468},"mcp_server/handlers/latency_class.py",{"path":562,"priority":468},"mcp_server/handlers/list_domains.py",{"path":564,"priority":468},"mcp_server/handlers/memories_facets.py",{"path":566,"priority":468},"mcp_server/handlers/memories_page.py",{"path":568,"priority":468},"mcp_server/handlers/memory_stats.py",{"path":570,"priority":468},"mcp_server/handlers/narrative.py",{"path":572,"priority":468},"mcp_server/handlers/navigate_memory.py",{"path":574,"priority":468},"mcp_server/handlers/open_visualization.py",{"path":576,"priority":468},"mcp_server/handlers/quadtree_handler.py",{"path":578,"priority":468},"mcp_server/handlers/query_methodology.py",{"path":580,"priority":468},"mcp_server/handlers/query_workflow_graph.py",{"path":582,"priority":468},"mcp_server/handlers/rate_memory.py",{"path":584,"priority":468},"mcp_server/handlers/rebuild_profiles.py",{"path":586,"priority":468},"mcp_server/handlers/recall.py",{"path":588,"priority":468},"mcp_server/handlers/recall_helpers.py",{"path":590,"priority":468},"mcp_server/handlers/recall_hierarchical.py",{"path":592,"priority":468},"mcp_server/handlers/recompute_layout.py",{"path":594,"priority":468},"mcp_server/handlers/record_session_end.py",{"path":596,"priority":468},"mcp_server/handlers/remember.py",{"path":598,"priority":468},"mcp_server/handlers/remember_helpers.py",{"path":600,"priority":468},"mcp_server/handlers/remember_response.py",{"path":602,"priority":468},"mcp_server/handlers/seed_project.py",{"path":604,"priority":468},"mcp_server/handlers/seed_project_constants.py",{"path":606,"priority":468},"mcp_server/handlers/seed_project_stages.py",{"path":608,"priority":468},"mcp_server/handlers/sync_instructions.py",{"path":610,"priority":468},"mcp_server/handlers/tile_handler.py",{"path":612,"priority":468},"mcp_server/handlers/unified_search.py",{"path":614,"priority":468},"mcp_server/handlers/validate_memory.py",{"path":616,"priority":468},"mcp_server/handlers/wiki_adr.py",{"path":618,"priority":468},"mcp_server/handlers/wiki_api.py",{"path":620,"priority":468},"mcp_server/handlers/wiki_compile.py",{"path":622,"priority":468},"mcp_server/handlers/wiki_consolidate.py",{"path":624,"priority":468},"mcp_server/handlers/wiki_curate.py",{"path":626,"priority":468},"mcp_server/handlers/wiki_emerge.py",{"path":628,"priority":468},"mcp_server/handlers/wiki_export.py",{"path":630,"priority":468},"mcp_server/handlers/wiki_extract.py",{"path":632,"priority":468},"mcp_server/handlers/wiki_link.py",{"path":634,"priority":468},"mcp_server/handlers/wiki_list.py",{"path":636,"priority":468},"mcp_server/handlers/wiki_migrate.py",{"path":638,"priority":468},"mcp_server/handlers/wiki_pipeline.py",{"path":640,"priority":468},"mcp_server/handlers/wiki_purge.py",{"path":642,"priority":468},"mcp_server/handlers/wiki_read.py",{"path":644,"priority":468},"mcp_server/handlers/wiki_refine.py",{"path":646,"priority":468},"mcp_server/handlers/wiki_reindex.py",{"path":648,"priority":468},"mcp_server/handlers/wiki_rename.py",{"path":650,"priority":468},"mcp_server/handlers/wiki_resolve.py",{"path":652,"priority":468},"mcp_server/handlers/wiki_seed_codebase.py",{"path":654,"priority":468},"mcp_server/handlers/wiki_synthesize.py",{"path":656,"priority":468},"mcp_server/handlers/wiki_verify.py",{"path":658,"priority":468},"mcp_server/handlers/wiki_view.py",{"path":660,"priority":468},"mcp_server/handlers/wiki_write.py",{"path":662,"priority":468},"mcp_server/handlers/workflow_graph.py",{"path":664,"priority":468},"tests_py/handlers/__init__.py",{"path":666,"priority":468},"tests_py/handlers/test_a3_homeostatic_scalar.py",{"path":668,"priority":468},"tests_py/handlers/test_admission.py",{"path":670,"priority":468},"tests_py/handlers/test_backfill_discover_files_issue15.py",{"path":672,"priority":468},"tests_py/handlers/test_backfill_heat.py",{"path":674,"priority":468},"tests_py/handlers/test_beam_anticheat.py",{"path":676,"priority":468},"tests_py/handlers/test_checkpoint.py",{"path":678,"priority":468},"tests_py/handlers/test_cls_diagnostics.py",{"path":680,"priority":468},"tests_py/handlers/test_codebase_analyze_rglob.py",{"path":682,"priority":468},"tests_py/handlers/test_consolidate.py",{"path":684,"priority":468},"tests_py/handlers/test_consolidate_telemetry.py",{"path":686,"priority":468},"tests_py/handlers/test_detect_domain.py",{"path":688,"priority":468},"tests_py/handlers/test_explore_features.py",{"path":690,"priority":468},"tests_py/handlers/test_get_methodology_graph.py",{"path":692,"priority":468},"tests_py/handlers/test_get_telemetry.py",{"path":694,"priority":468},"tests_py/handlers/test_import_sessions.py",{"path":696,"priority":468},"tests_py/handlers/test_import_sessions_stream.py",{"path":698,"priority":468},"tests_py/handlers/test_ingest_codebase.py",{"path":700,"priority":468},"tests_py/handlers/test_ingest_prd.py",{"path":702,"priority":468},"tests_py/handlers/test_latency_class.py",{"path":704,"priority":468},"tests_py/handlers/test_list_domains.py",{"path":706,"priority":468},"tests_py/handlers/test_memify_diagnostics.py",{"path":708,"priority":468},"tests_py/handlers/test_memory_stats.py",{"path":710,"priority":468},"tests_py/handlers/test_open_visualization.py",{"path":712,"priority":468},"tests_py/handlers/test_query_methodology.py",{"path":714,"priority":468},"tests_py/handlers/test_query_workflow_graph.py",{"path":716,"priority":468},"tests_py/handlers/test_rebuild_profiles.py",{"path":718,"priority":468},"tests_py/handlers/test_recall.py",{"path":720,"priority":468},"tests_py/handlers/test_recall_enhancements.py",{"path":722,"priority":468},"tests_py/handlers/test_recall_hierarchical_bounded.py",{"path":724,"priority":468},"tests_py/handlers/test_recall_low_signal_filter.py",{"path":726,"priority":468},"tests_py/handlers/test_record_session_end.py",{"path":728,"priority":468},"tests_py/handlers/test_registry.py",{"path":730,"priority":468},"tests_py/handlers/test_remember.py",{"path":732,"priority":468},"tests_py/handlers/test_seed_project.py",{"path":734,"priority":468},"tests_py/handlers/test_wiki_redirect_handlers.py",{"path":736,"priority":468},"tests_py/handlers/test_wiki_seed_codebase.py",{"path":738,"priority":468},"tests_py/handlers/test_wiki_sync_errors.py",{"sources":740},[741],"manual",{"npmPackage":453},{"closedIssues90d":231,"description":744,"forks":232,"homepage":745,"license":238,"openIssues90d":8,"pushedAt":233,"readmeSize":229,"stars":234,"topics":746},"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",[747,748,749,750,275,751,752,753,754,755,756,757,758,759,760,761,762,763,764,765],"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":236},{"classifiedAt":768,"discoverAt":769,"extractAt":770,"githubAt":770,"npmAt":771,"updatedAt":768},1778683561790,1778683544931,1778683554398,1778683559402,[215,212,214,211,213],{"evaluatedAt":242,"extractAt":291,"updatedAt":242},[],[776,804,830,847,877,899],{"_creationTime":777,"_id":778,"community":779,"display":780,"identity":786,"providers":790,"relations":797,"tags":800,"workflow":801},1778696595410.5657,"k17bk9m02r7jkbzzqapbzfvq8h86m6qn",{"reviewCount":8},{"description":781,"installMethods":782,"name":784,"sourceUrl":785},"Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.",{"claudeCode":783},"rohitg00/pro-workflow","orchestrate","https://github.com/rohitg00/pro-workflow",{"basePath":787,"githubOwner":788,"githubRepo":789,"locale":18,"slug":784,"type":247},"skills/orchestrate","rohitg00","pro-workflow",{"evaluate":791,"extract":796},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":792,"targetMarket":216,"tier":217},[793,794,795,211,212],"llm-ops","agent","workflow",{"commitSha":281},{"parentExtensionId":798,"repoId":799},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[794,212,793,211,795],{"evaluatedAt":802,"extractAt":803,"updatedAt":802},1778696881233,1778696595410,{"_creationTime":805,"_id":806,"community":807,"display":808,"identity":814,"providers":818,"relations":824,"tags":826,"workflow":827},1778696691708.3027,"k174mp6hf33cptbna2p91t2ts586n4ad",{"reviewCount":8},{"description":809,"installMethods":810,"name":812,"sourceUrl":813},"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":811},"ruvnet/ruflo","memory-management","https://github.com/ruvnet/ruflo",{"basePath":815,"githubOwner":816,"githubRepo":817,"locale":18,"slug":812,"type":247},".agents/skills/memory-management","ruvnet","ruflo",{"evaluate":819,"extract":823},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":820,"targetMarket":216,"tier":217},[211,758,212,821,822],"agentdb","hnsw",{"commitSha":281},{"repoId":825},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[821,822,212,211,758],{"evaluatedAt":828,"extractAt":829,"updatedAt":828},1778699160670,1778696691708,{"_creationTime":831,"_id":832,"community":833,"display":834,"identity":836,"providers":837,"relations":843,"tags":844,"workflow":845},1778683562157.878,"k174wwq1x9t40ph56hj32705bh86n96x",{"reviewCount":8},{"description":421,"installMethods":835,"name":422,"sourceUrl":14},{"claudeCode":12},{"basePath":420,"githubOwner":245,"githubRepo":246,"locale":18,"slug":422,"type":247},{"evaluate":838,"extract":842},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":839,"targetMarket":216,"tier":217},[211,212,295,214,840,841],"local","cli",{"commitSha":281},{"parentExtensionId":250,"repoId":287},[841,212,214,840,211,295],{"evaluatedAt":846,"extractAt":291,"updatedAt":846},1778683871550,{"_creationTime":848,"_id":849,"community":850,"display":851,"identity":857,"providers":862,"relations":870,"tags":873,"workflow":874},1778695116697.199,"k17cex5hqwje7qgvts5evct1d186nd4m",{"reviewCount":8},{"description":852,"installMethods":853,"name":855,"sourceUrl":856},"Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.",{"claudeCode":854},"Orchestra-Research/AI-Research-SKILLs","ARA Research Manager","https://github.com/Orchestra-Research/AI-Research-SKILLs",{"basePath":858,"githubOwner":859,"githubRepo":860,"locale":18,"slug":861,"type":247},"22-agent-native-research-artifact/research-manager","Orchestra-Research","AI-Research-SKILLs","research-manager",{"evaluate":863,"extract":869},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":864,"targetMarket":216,"tier":217},[865,866,212,867,868],"research","provenance","session-logging","ara",{"commitSha":281,"license":298},{"parentExtensionId":871,"repoId":872},"k17155ws9qc0hw7a568bg79sfd86max8","kd70hj1y80mhra5xm5g188j5n586mg18",[868,212,866,865,867],{"evaluatedAt":875,"extractAt":876,"updatedAt":875},1778697541177,1778695116697,{"_creationTime":878,"_id":879,"community":880,"display":881,"identity":885,"providers":887,"relations":895,"tags":896,"workflow":897},1778696595410.5618,"k174h4yhwrcpcmdx62n2g2b88986mx17",{"reviewCount":8},{"description":882,"installMethods":883,"name":884,"sourceUrl":785},"Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.",{"claudeCode":783},"agent-teams",{"basePath":886,"githubOwner":788,"githubRepo":789,"locale":18,"slug":884,"type":247},"skills/agent-teams",{"evaluate":888,"extract":894},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":889,"targetMarket":216,"tier":217},[890,891,212,793,892,893],"ai-workflow","collaboration","productivity","self-correction",{"commitSha":281},{"parentExtensionId":798,"repoId":799},[890,891,212,793,892,893],{"evaluatedAt":898,"extractAt":803,"updatedAt":898},1778696637446,{"_creationTime":900,"_id":901,"community":902,"display":903,"identity":909,"providers":913,"relations":921,"tags":924,"workflow":925},1778692488329.0144,"k1724vjyyetw8qcfh8anb4c3tn86ngy7",{"reviewCount":8},{"description":904,"installMethods":905,"name":907,"sourceUrl":908},"Extract domain knowledge from existing project sources and generate domain rules. Also handles vault sync and domain listing.",{"claudeCode":906},"luiseiman/claude-kit","domain-extract","https://github.com/luiseiman/claude-kit",{"basePath":910,"githubOwner":911,"githubRepo":912,"locale":18,"slug":907,"type":247},"skills/domain-extract","luiseiman","claude-kit",{"evaluate":914,"extract":920},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":915,"targetMarket":216,"tier":217},[916,212,917,918,919],"domain-extraction","rule-generation","code-analysis","automation",{"commitSha":281},{"parentExtensionId":922,"repoId":923},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[919,918,916,212,917],{"evaluatedAt":926,"extractAt":927,"updatedAt":926},1778693090713,1778692488329]