[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-cdeust-cortex-navigate-knowledge-de":3,"guides-for-cdeust-cortex-navigate-knowledge":789,"similar-k17bvewsqg5vj2gcn8pypyztz586mxs5-de":790},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":257,"isFallback":239,"parentExtension":263,"providers":319,"relations":323,"repo":324,"tags":787,"workflow":788},1778683562157.8767,"k17bvewsqg5vj2gcn8pypyztz586mxs5",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"cdeust/Cortex","Cortex Navigate Knowledge","https://github.com/cdeust/Cortex",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":237,"workflow":255},1778683735122.4893,"kn70vywkf8235k8xa8cqpm049d86mqr2","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":209,"promptVersionExtension":213,"promptVersionScoring":214,"purpose":215,"rationale":216,"score":217,"summary":218,"tags":219,"targetMarket":225,"tier":226,"useCases":227,"workflow":232},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of navigating complex knowledge graphs and explicitly lists user intents and scenarios where this skill is useful.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","This skill offers significant value over default LLM behavior by providing structured traversal of a persistent knowledge graph, going beyond simple retrieval with specialized tools for causal chains and co-access paths.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill appears fully implemented with clear workflow steps, documented tools, and a comprehensive setup process, indicating it can be used in production.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on knowledge graph navigation and exploration, with no adjacent unrelated capabilities.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's capabilities and usage scenarios, is concise, and easy to understand.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill uses narrowly scoped, verb-noun tools like `get_causal_chain`, `navigate_memory`, `recall_hierarchical`, and `drill_down`, which are easy for the agent to select and less prone to misuse.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All tool parameters, including optional ones like `direction`, `max_depth`, `levels`, and `domain`, are clearly documented within the SKILL.md, along with their expected types and default behaviors.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names like `get_causal_chain`, `navigate_memory`, `recall_hierarchical`, and `drill_down` are descriptive, in kebab-case, and clearly indicate their domain-specific actions.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Tool inputs are specific and typed (e.g., entity strings, IDs, levels), and outputs are structured graph or list data relevant to the specific navigation task, avoiding unnecessary data dumps.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT license, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The latest commit was on May 13, 2026, indicating recent maintenance activity.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses a lockfile (`hasLockfile: true`) and appears to have tests and CI, suggesting a reasonable approach to dependency management.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The skill operates locally and does not appear to handle or expose secrets; its primary function is data traversal.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill's tools operate on structured graph data and do not appear to execute arbitrary code or load untrusted external content as instructions.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill does not fetch remote content or execute code from external sources; all operations are local to the knowledge graph.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill's operations are confined to querying and traversing a local knowledge graph, with no indications of writing to or modifying files outside its designated scope.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No evidence of detached process spawns or deny-retry loops in the skill's scripts or tool definitions.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The skill operates on a local knowledge graph and does not make outbound calls to submit confidential data.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and descriptions appear free of hidden steering tricks, control characters, or invisible Unicode tags.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The skill's operations are based on direct tool calls and graph traversal, with no signs of obfuscated or dynamically executed code.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill operates on an internal knowledge graph and makes no assumptions about the user's project file structure.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","The repository has 0 open issues and 16 closed issues in the last 90 days, indicating excellent maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The extension has a version (v3.15.0) and a CHANGELOG, indicating clear release management.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Tool parameters are typed and specific (e.g., entity names, IDs, levels), suggesting validation is handled internally by the MCP framework or the skill's design.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The skill is read-only and focuses on knowledge graph traversal, making it inherently non-destructive.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The skill's tools interact with a local database and graph structure, implying robust error handling for graph traversal and data retrieval is likely implemented within the MCP framework.",{"category":110,"check":114,"severity":115,"summary":116},"Logging","not_applicable","The skill is primarily analytical and read-only, so local audit logging is not a typical requirement.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The skill operates on a local knowledge graph and does not process personal data, thus GDPR compliance is not a concern.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill operates on local data and graph structures, with no regional or jurisdictional logic detected, making it globally applicable.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The skill relies on standard Python and PostgreSQL, making it portable across POSIX-compliant systems and Windows.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README provides extensive details about the project's science, benchmarks, installation, and features, serving as excellent documentation.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The skill exposes a focused set of 4 tools (`get_causal_chain`, `navigate_memory`, `recall_hierarchical`, `drill_down`), which is within the ideal range.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The tools are distinct in their function: `get_causal_chain`, `navigate_memory`, `recall_hierarchical`, and `drill_down` each perform unique graph traversal operations.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features, such as tracing causal chains and exploring memory clusters, are directly supported by the documented tools in SKILL.md.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","Clear installation instructions are provided in the README, including `claude plugin marketplace add` and `claude plugin install` commands, along with verification steps.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","While not explicitly shown, the structured nature of the tools and the project's focus on production readiness suggest that errors would be actionable within the MCP framework.",{"category":103,"check":148,"severity":24,"summary":149},"Pinned dependencies","The project uses Poetry and `poetry.lock`, indicating pinned dependencies. The README also mentions Python 3.10+.",{"category":33,"check":151,"severity":115,"summary":152},"Dry-run preview","This skill is purely read-only, performing analysis and traversal of an existing knowledge graph; there are no state-changing operations that would require a dry-run mode.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The skill's operations are read-only graph queries, which are inherently idempotent. The MCP framework likely enforces timeouts.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The project emphasizes local execution and privacy, with no mention of telemetry collection. If any exists, it would likely be opt-in.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill clearly defines its purpose as navigating knowledge graphs for tracing relationships and causal chains, with explicit use cases and non-goals.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly states the core capability, and provides relevant keywords and trigger phrases.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured, uses progressive disclosure via links to deeper explanations, and avoids excessive inline material.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines procedures and links to external resources like the science paper and detailed setup instructions, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":115,"summary":175},"Forked exploration","This skill performs focused graph traversal rather than deep exploration that would flood the conversation, so `context: fork` is not applicable.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md provides clear, ready-to-use examples for each tool, demonstrating input, invocation, and expected output format.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation implicitly handles edge cases by specifying parameters like `max_depth` and `levels`, guiding users to explore within defined bounds.",{"category":110,"check":183,"severity":115,"summary":184},"Tool Fallback","This skill uses only Claude-internal tools and does not rely on external MCP servers that would require fallback mechanisms.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill operates on a local knowledge graph and is read-only, so unexpected states would likely result in graceful query failures rather than requiring explicit halt procedures.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill operates independently on its local knowledge graph and does not implicitly rely on other skills being loaded.",1778683734623,"This skill enables users to navigate and explore a local knowledge graph, trace entity relationships and causal chains, examine memory clusters, and analyze co-access patterns using specialized tools.",[195,196,197,198,199],"Trace entity relationships and causal chains","Explore co-access paths between memories","Drill into fractal memory clusters","Detect structural gaps in the knowledge graph","Visualize the knowledge graph and project structure",[201,202,203,204],"Modifying the knowledge graph","External data ingestion or processing","Performing general web searches","Executing arbitrary code",[206,207,208],"Knowledge graph exploration","Data relationship analysis","Causal chain tracing",[210,211,212],"Claude Code environment","PostgreSQL with pgvector extension","Python 3.10+","3.0.0","4.4.0","To provide deep, structured exploration of connected knowledge, enabling users to understand complex relationships and causal links within their data.","The extension is exceptionally well-documented, robust, and provides a unique, valuable capability. Its only minor area for consideration is the lack of explicit error handling documentation for edge cases, which is offset by its read-only nature.",99,"A highly polished and robust skill for exploring complex knowledge graphs and tracing relationships.",[220,221,222,223,224],"knowledge-graph","graph-traversal","causal-chains","memory-exploration","data-analysis","global","verified",[228,229,230,231],"Understanding relationships between concepts","Tracing cause-and-effect chains","Exploring a topic area systematically","Debugging complex systems with contextual memory",[233,234,235,236,198],"Trace causal chains through the knowledge graph","Navigate co-access paths between memories","Explore memories hierarchically","Drill down into specific memory clusters",{"codeQuality":238,"collectedAt":240,"documentation":241,"maintenance":244,"popularity":249,"security":251,"testCoverage":254},{"hasLockfile":239},true,1778683713991,{"descriptionLength":242,"readmeSize":243},425,36381,{"closedIssues90d":245,"forks":246,"hasChangelog":239,"openIssues90d":8,"pushedAt":247,"stars":248},16,8,1778675198000,33,{"npmDownloads":250},14,{"hasNpmPackage":239,"license":252,"smitheryVerified":253},"NOASSERTION",false,{"hasCi":239,"hasTests":239},{"updatedAt":256},1778683735122,{"basePath":258,"githubOwner":259,"githubRepo":260,"locale":18,"slug":261,"type":262},"skills/cortex-navigate-knowledge","cdeust","Cortex","cortex-navigate-knowledge","skill",{"_creationTime":264,"_id":265,"community":266,"display":267,"identity":270,"parentExtension":273,"providers":307,"relations":315,"tags":316,"workflow":317},1778683562157.8752,"k1739s9t9kj9bmjq1z4byk17g986mv7x",{"reviewCount":8},{"description":268,"installMethods":269,"name":260,"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":260},{"basePath":271,"githubOwner":259,"githubRepo":260,"locale":18,"slug":260,"type":272},"","plugin",{"_creationTime":274,"_id":275,"community":276,"display":277,"identity":281,"providers":283,"relations":301,"tags":303,"workflow":304},1778683562157.875,"k174pnm5ch9ab6fr1etef2f2b586m74b",{"reviewCount":8},{"description":278,"installMethods":279,"name":280,"sourceUrl":14},"Persistent memory and cognitive profiling plugins for Claude Code",{"claudeCode":12},"cortex-plugins",{"basePath":271,"githubOwner":259,"githubRepo":260,"locale":18,"slug":260,"type":282},"marketplace",{"evaluate":284,"extract":295},{"promptVersionExtension":285,"promptVersionScoring":214,"score":286,"tags":287,"targetMarket":225,"tier":226},"3.1.0",100,[288,289,290,291,220,292,293,294],"memory","cognitive-profiling","mcp","claude-code","codebase-analysis","postgresql","pgvector",{"commitSha":296,"marketplace":297,"plugin":299},"HEAD",{"name":280,"pluginCount":298},1,{"mcpCount":8,"provider":300,"skillCount":8},"classify",{"repoId":302},"kd79gxpemvkr09a7zsb3h8kmah86nvgf",[291,292,289,220,290,288,294,293],{"evaluatedAt":305,"extractAt":306,"updatedAt":305},1778683583007,1778683562157,{"evaluate":308,"extract":312},{"promptVersionExtension":213,"promptVersionScoring":214,"score":217,"tags":309,"targetMarket":225,"tier":226},[288,310,220,289,293,294,311],"persistence","developer-tools",{"commitSha":296,"license":313,"plugin":314},"MIT",{"mcpCount":8,"provider":300,"skillCount":250},{"parentExtensionId":275,"repoId":302},[289,311,220,288,310,294,293],{"evaluatedAt":318,"extractAt":306,"updatedAt":318},1778683602463,{"evaluate":320,"extract":322},{"promptVersionExtension":213,"promptVersionScoring":214,"score":217,"tags":321,"targetMarket":225,"tier":226},[220,221,222,223,224],{"commitSha":296,"license":313},{"parentExtensionId":265,"repoId":302},{"_creationTime":325,"_id":302,"identity":326,"providers":327,"workflow":782},1778683544930.988,{"githubOwner":259,"githubRepo":260,"sourceUrl":14},{"classify":328,"discover":754,"extract":757,"github":758,"npm":781},{"commitSha":296,"extensions":329},[330,343,356,365,373,381,389,397,402,410,418,426,434,442,450,458,466],{"basePath":271,"description":278,"displayName":280,"installMethods":331,"rationale":332,"selectedPaths":333,"source":342,"sourceLanguage":18,"type":282},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[334,337,339],{"path":335,"priority":336},".claude-plugin/marketplace.json","mandatory",{"path":338,"priority":336},"README.md",{"path":340,"priority":341},"LICENSE","high","rule",{"basePath":271,"description":268,"displayName":344,"installMethods":345,"rationale":346,"selectedPaths":347,"source":342,"sourceLanguage":18,"type":272},"cortex",{"claudeCode":260},"inline plugin source from marketplace.json at /",[348,349,350,352,354],{"path":338,"priority":336},{"path":340,"priority":341},{"path":351,"priority":336},".mcp.json",{"path":353,"priority":341},"agents/cortex-wiki-groomer.md",{"path":355,"priority":341},"commands/methodology.md",{"basePath":357,"description":358,"displayName":359,"installMethods":360,"rationale":361,"selectedPaths":362,"source":342,"sourceLanguage":18,"type":262},"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",[363],{"path":364,"priority":336},"SKILL.md",{"basePath":366,"description":367,"displayName":368,"installMethods":369,"rationale":370,"selectedPaths":371,"source":342,"sourceLanguage":18,"type":262},"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",[372],{"path":364,"priority":336},{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":342,"sourceLanguage":18,"type":262},"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",[380],{"path":364,"priority":336},{"basePath":382,"description":383,"displayName":384,"installMethods":385,"rationale":386,"selectedPaths":387,"source":342,"sourceLanguage":18,"type":262},"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",[388],{"path":364,"priority":336},{"basePath":390,"description":391,"displayName":392,"installMethods":393,"rationale":394,"selectedPaths":395,"source":342,"sourceLanguage":18,"type":262},"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",[396],{"path":364,"priority":336},{"basePath":258,"description":10,"displayName":261,"installMethods":398,"rationale":399,"selectedPaths":400,"source":342,"sourceLanguage":18,"type":262},{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-navigate-knowledge/SKILL.md",[401],{"path":364,"priority":336},{"basePath":403,"description":404,"displayName":405,"installMethods":406,"rationale":407,"selectedPaths":408,"source":342,"sourceLanguage":18,"type":262},"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",[409],{"path":364,"priority":336},{"basePath":411,"description":412,"displayName":413,"installMethods":414,"rationale":415,"selectedPaths":416,"source":342,"sourceLanguage":18,"type":262},"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",[417],{"path":364,"priority":336},{"basePath":419,"description":420,"displayName":421,"installMethods":422,"rationale":423,"selectedPaths":424,"source":342,"sourceLanguage":18,"type":262},"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",[425],{"path":364,"priority":336},{"basePath":427,"description":428,"displayName":429,"installMethods":430,"rationale":431,"selectedPaths":432,"source":342,"sourceLanguage":18,"type":262},"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",[433],{"path":364,"priority":336},{"basePath":435,"description":436,"displayName":437,"installMethods":438,"rationale":439,"selectedPaths":440,"source":342,"sourceLanguage":18,"type":262},"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",[441],{"path":364,"priority":336},{"basePath":443,"description":444,"displayName":445,"installMethods":446,"rationale":447,"selectedPaths":448,"source":342,"sourceLanguage":18,"type":262},"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",[449],{"path":364,"priority":336},{"basePath":451,"description":452,"displayName":453,"installMethods":454,"rationale":455,"selectedPaths":456,"source":342,"sourceLanguage":18,"type":262},"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",[457],{"path":364,"priority":336},{"basePath":459,"description":460,"displayName":461,"installMethods":462,"rationale":463,"selectedPaths":464,"source":342,"sourceLanguage":18,"type":262},"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",[465],{"path":364,"priority":336},{"basePath":271,"description":467,"displayName":468,"installMethods":469,"license":313,"rationale":470,"selectedPaths":471,"source":342,"sourceLanguage":18,"type":290},"Persistent memory and cognitive profiling for Claude Code","neuro-cortex-memory",{"pypi":468},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[472,474,476,477,478,481,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752],{"path":473,"priority":336},"package.json",{"path":475,"priority":336},"pyproject.toml",{"path":338,"priority":336},{"path":340,"priority":341},{"path":479,"priority":480},"mcp_server/doctor.py","medium",{"path":482,"priority":483},"mcp_server/__main__.py","low",{"path":485,"priority":483},"mcp_server/handlers/__init__.py",{"path":487,"priority":483},"mcp_server/handlers/_telemetry_wrap.py",{"path":489,"priority":483},"mcp_server/handlers/_tool_meta.py",{"path":491,"priority":483},"mcp_server/handlers/add_rule.py",{"path":493,"priority":483},"mcp_server/handlers/admission.py",{"path":495,"priority":483},"mcp_server/handlers/anchor.py",{"path":497,"priority":483},"mcp_server/handlers/assess_coverage.py",{"path":499,"priority":483},"mcp_server/handlers/backfill_helpers.py",{"path":501,"priority":483},"mcp_server/handlers/backfill_memories.py",{"path":503,"priority":483},"mcp_server/handlers/change_impact.py",{"path":505,"priority":483},"mcp_server/handlers/checkpoint.py",{"path":507,"priority":483},"mcp_server/handlers/codebase_analyze.py",{"path":509,"priority":483},"mcp_server/handlers/codebase_analyze_helpers.py",{"path":511,"priority":483},"mcp_server/handlers/consolidate.py",{"path":513,"priority":483},"mcp_server/handlers/consolidation/__init__.py",{"path":515,"priority":483},"mcp_server/handlers/consolidation/cascade.py",{"path":517,"priority":483},"mcp_server/handlers/consolidation/cls.py",{"path":519,"priority":483},"mcp_server/handlers/consolidation/compression.py",{"path":521,"priority":483},"mcp_server/handlers/consolidation/decay.py",{"path":523,"priority":483},"mcp_server/handlers/consolidation/homeostatic.py",{"path":525,"priority":483},"mcp_server/handlers/consolidation/memify.py",{"path":527,"priority":483},"mcp_server/handlers/consolidation/plasticity.py",{"path":529,"priority":483},"mcp_server/handlers/consolidation/pruning.py",{"path":531,"priority":483},"mcp_server/handlers/consolidation/sleep.py",{"path":533,"priority":483},"mcp_server/handlers/consolidation/transfer.py",{"path":535,"priority":483},"mcp_server/handlers/create_trigger.py",{"path":537,"priority":483},"mcp_server/handlers/detect_domain.py",{"path":539,"priority":483},"mcp_server/handlers/detect_gaps.py",{"path":541,"priority":483},"mcp_server/handlers/drill_down.py",{"path":543,"priority":483},"mcp_server/handlers/explore_features.py",{"path":545,"priority":483},"mcp_server/handlers/forget.py",{"path":547,"priority":483},"mcp_server/handlers/get_causal_chain.py",{"path":549,"priority":483},"mcp_server/handlers/get_methodology_graph.py",{"path":551,"priority":483},"mcp_server/handlers/get_project_story.py",{"path":553,"priority":483},"mcp_server/handlers/get_rules.py",{"path":555,"priority":483},"mcp_server/handlers/get_telemetry.py",{"path":557,"priority":483},"mcp_server/handlers/import_sessions.py",{"path":559,"priority":483},"mcp_server/handlers/ingest_codebase.py",{"path":561,"priority":483},"mcp_server/handlers/ingest_codebase_cypher.py",{"path":563,"priority":483},"mcp_server/handlers/ingest_codebase_graph.py",{"path":565,"priority":483},"mcp_server/handlers/ingest_codebase_pages.py",{"path":567,"priority":483},"mcp_server/handlers/ingest_codebase_schema.py",{"path":569,"priority":483},"mcp_server/handlers/ingest_codebase_writers.py",{"path":571,"priority":483},"mcp_server/handlers/ingest_helpers.py",{"path":573,"priority":483},"mcp_server/handlers/ingest_prd.py",{"path":575,"priority":483},"mcp_server/handlers/latency_class.py",{"path":577,"priority":483},"mcp_server/handlers/list_domains.py",{"path":579,"priority":483},"mcp_server/handlers/memories_facets.py",{"path":581,"priority":483},"mcp_server/handlers/memories_page.py",{"path":583,"priority":483},"mcp_server/handlers/memory_stats.py",{"path":585,"priority":483},"mcp_server/handlers/narrative.py",{"path":587,"priority":483},"mcp_server/handlers/navigate_memory.py",{"path":589,"priority":483},"mcp_server/handlers/open_visualization.py",{"path":591,"priority":483},"mcp_server/handlers/quadtree_handler.py",{"path":593,"priority":483},"mcp_server/handlers/query_methodology.py",{"path":595,"priority":483},"mcp_server/handlers/query_workflow_graph.py",{"path":597,"priority":483},"mcp_server/handlers/rate_memory.py",{"path":599,"priority":483},"mcp_server/handlers/rebuild_profiles.py",{"path":601,"priority":483},"mcp_server/handlers/recall.py",{"path":603,"priority":483},"mcp_server/handlers/recall_helpers.py",{"path":605,"priority":483},"mcp_server/handlers/recall_hierarchical.py",{"path":607,"priority":483},"mcp_server/handlers/recompute_layout.py",{"path":609,"priority":483},"mcp_server/handlers/record_session_end.py",{"path":611,"priority":483},"mcp_server/handlers/remember.py",{"path":613,"priority":483},"mcp_server/handlers/remember_helpers.py",{"path":615,"priority":483},"mcp_server/handlers/remember_response.py",{"path":617,"priority":483},"mcp_server/handlers/seed_project.py",{"path":619,"priority":483},"mcp_server/handlers/seed_project_constants.py",{"path":621,"priority":483},"mcp_server/handlers/seed_project_stages.py",{"path":623,"priority":483},"mcp_server/handlers/sync_instructions.py",{"path":625,"priority":483},"mcp_server/handlers/tile_handler.py",{"path":627,"priority":483},"mcp_server/handlers/unified_search.py",{"path":629,"priority":483},"mcp_server/handlers/validate_memory.py",{"path":631,"priority":483},"mcp_server/handlers/wiki_adr.py",{"path":633,"priority":483},"mcp_server/handlers/wiki_api.py",{"path":635,"priority":483},"mcp_server/handlers/wiki_compile.py",{"path":637,"priority":483},"mcp_server/handlers/wiki_consolidate.py",{"path":639,"priority":483},"mcp_server/handlers/wiki_curate.py",{"path":641,"priority":483},"mcp_server/handlers/wiki_emerge.py",{"path":643,"priority":483},"mcp_server/handlers/wiki_export.py",{"path":645,"priority":483},"mcp_server/handlers/wiki_extract.py",{"path":647,"priority":483},"mcp_server/handlers/wiki_link.py",{"path":649,"priority":483},"mcp_server/handlers/wiki_list.py",{"path":651,"priority":483},"mcp_server/handlers/wiki_migrate.py",{"path":653,"priority":483},"mcp_server/handlers/wiki_pipeline.py",{"path":655,"priority":483},"mcp_server/handlers/wiki_purge.py",{"path":657,"priority":483},"mcp_server/handlers/wiki_read.py",{"path":659,"priority":483},"mcp_server/handlers/wiki_refine.py",{"path":661,"priority":483},"mcp_server/handlers/wiki_reindex.py",{"path":663,"priority":483},"mcp_server/handlers/wiki_rename.py",{"path":665,"priority":483},"mcp_server/handlers/wiki_resolve.py",{"path":667,"priority":483},"mcp_server/handlers/wiki_seed_codebase.py",{"path":669,"priority":483},"mcp_server/handlers/wiki_synthesize.py",{"path":671,"priority":483},"mcp_server/handlers/wiki_verify.py",{"path":673,"priority":483},"mcp_server/handlers/wiki_view.py",{"path":675,"priority":483},"mcp_server/handlers/wiki_write.py",{"path":677,"priority":483},"mcp_server/handlers/workflow_graph.py",{"path":679,"priority":483},"tests_py/handlers/__init__.py",{"path":681,"priority":483},"tests_py/handlers/test_a3_homeostatic_scalar.py",{"path":683,"priority":483},"tests_py/handlers/test_admission.py",{"path":685,"priority":483},"tests_py/handlers/test_backfill_discover_files_issue15.py",{"path":687,"priority":483},"tests_py/handlers/test_backfill_heat.py",{"path":689,"priority":483},"tests_py/handlers/test_beam_anticheat.py",{"path":691,"priority":483},"tests_py/handlers/test_checkpoint.py",{"path":693,"priority":483},"tests_py/handlers/test_cls_diagnostics.py",{"path":695,"priority":483},"tests_py/handlers/test_codebase_analyze_rglob.py",{"path":697,"priority":483},"tests_py/handlers/test_consolidate.py",{"path":699,"priority":483},"tests_py/handlers/test_consolidate_telemetry.py",{"path":701,"priority":483},"tests_py/handlers/test_detect_domain.py",{"path":703,"priority":483},"tests_py/handlers/test_explore_features.py",{"path":705,"priority":483},"tests_py/handlers/test_get_methodology_graph.py",{"path":707,"priority":483},"tests_py/handlers/test_get_telemetry.py",{"path":709,"priority":483},"tests_py/handlers/test_import_sessions.py",{"path":711,"priority":483},"tests_py/handlers/test_import_sessions_stream.py",{"path":713,"priority":483},"tests_py/handlers/test_ingest_codebase.py",{"path":715,"priority":483},"tests_py/handlers/test_ingest_prd.py",{"path":717,"priority":483},"tests_py/handlers/test_latency_class.py",{"path":719,"priority":483},"tests_py/handlers/test_list_domains.py",{"path":721,"priority":483},"tests_py/handlers/test_memify_diagnostics.py",{"path":723,"priority":483},"tests_py/handlers/test_memory_stats.py",{"path":725,"priority":483},"tests_py/handlers/test_open_visualization.py",{"path":727,"priority":483},"tests_py/handlers/test_query_methodology.py",{"path":729,"priority":483},"tests_py/handlers/test_query_workflow_graph.py",{"path":731,"priority":483},"tests_py/handlers/test_rebuild_profiles.py",{"path":733,"priority":483},"tests_py/handlers/test_recall.py",{"path":735,"priority":483},"tests_py/handlers/test_recall_enhancements.py",{"path":737,"priority":483},"tests_py/handlers/test_recall_hierarchical_bounded.py",{"path":739,"priority":483},"tests_py/handlers/test_recall_low_signal_filter.py",{"path":741,"priority":483},"tests_py/handlers/test_record_session_end.py",{"path":743,"priority":483},"tests_py/handlers/test_registry.py",{"path":745,"priority":483},"tests_py/handlers/test_remember.py",{"path":747,"priority":483},"tests_py/handlers/test_seed_project.py",{"path":749,"priority":483},"tests_py/handlers/test_wiki_redirect_handlers.py",{"path":751,"priority":483},"tests_py/handlers/test_wiki_seed_codebase.py",{"path":753,"priority":483},"tests_py/handlers/test_wiki_sync_errors.py",{"sources":755},[756],"manual",{"npmPackage":468},{"closedIssues90d":245,"description":759,"forks":246,"homepage":760,"license":252,"openIssues90d":8,"pushedAt":247,"readmeSize":243,"stars":248,"topics":761},"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",[762,763,764,765,291,766,767,768,769,770,771,772,773,774,775,776,777,778,779,780],"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":250},{"classifiedAt":783,"discoverAt":784,"extractAt":785,"githubAt":785,"npmAt":786,"updatedAt":783},1778683561790,1778683544931,1778683554398,1778683559402,[222,224,221,220,223],{"evaluatedAt":256,"extractAt":306,"updatedAt":256},[],[791,821,842,871,900,929],{"_creationTime":792,"_id":793,"community":794,"display":795,"identity":801,"providers":805,"relations":814,"tags":817,"workflow":818},1778695548458.4036,"k171cqe6hd4yd3ktqnf3qy9z5186mmff",{"reviewCount":8},{"description":796,"installMethods":797,"name":799,"sourceUrl":800},"Design and execute insect population surveys covering survey design, sampling methods, field execution, specimen identification, diversity index calculation including Shannon-Wiener and Simpson indices, statistical analysis, and reporting. Covers defining survey objectives, selecting study sites, determining sampling intensity and replication, choosing sampling methods appropriate to target taxa, standardizing collection effort, recording environmental covariates, identifying specimens to the lowest practical taxonomic level, calculating species richness, Shannon-Wiener diversity (H'), Simpson diversity (1-D), evenness, rarefaction curves, multivariate ordination, and producing survey reports with species lists and conservation implications. Use when conducting baseline biodiversity assessments, monitoring insect populations over time, comparing insect communities across habitats or treatments, assessing environmental impact, or supporting conservation planning with quantitative ecological data.\n",{"claudeCode":798},"pjt222/agent-almanac","survey-insect-population","https://github.com/pjt222/agent-almanac",{"basePath":802,"githubOwner":803,"githubRepo":804,"locale":18,"slug":799,"type":262},"skills/survey-insect-population","pjt222","agent-almanac",{"evaluate":806,"extract":813},{"promptVersionExtension":213,"promptVersionScoring":214,"score":286,"tags":807,"targetMarket":225,"tier":226},[808,809,810,811,812,224],"entomology","insects","ecology","biodiversity","survey",{"commitSha":296},{"parentExtensionId":815,"repoId":816},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[811,224,810,808,809,812],{"evaluatedAt":819,"extractAt":820,"updatedAt":819},1778701822946,1778695548458,{"_creationTime":822,"_id":823,"community":824,"display":825,"identity":829,"providers":831,"relations":838,"tags":839,"workflow":840},1778695548458.3613,"k17dx6tyy2yb3z5pp1vgmg46ad86nm18",{"reviewCount":8},{"description":826,"installMethods":827,"name":828,"sourceUrl":800},"Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.\n",{"claudeCode":798},"fit-drift-diffusion-model",{"basePath":830,"githubOwner":803,"githubRepo":804,"locale":18,"slug":828,"type":262},"skills/fit-drift-diffusion-model",{"evaluate":832,"extract":837},{"promptVersionExtension":213,"promptVersionScoring":214,"score":286,"tags":833,"targetMarket":225,"tier":226},[768,834,835,836,224],"modeling","statistics","python",{"commitSha":296},{"parentExtensionId":815,"repoId":816},[768,224,834,836,835],{"evaluatedAt":841,"extractAt":820,"updatedAt":841},1778698191612,{"_creationTime":843,"_id":844,"community":845,"display":846,"identity":852,"providers":856,"relations":864,"tags":867,"workflow":868},1778695720086.7703,"k176r34g5a5fjn1z1a4gq6v88186nje0",{"reviewCount":8},{"description":847,"installMethods":848,"name":850,"sourceUrl":851},"Designs an A/B test or experiment with clear hypothesis, variants, success metrics, sample size, and duration. Use when planning experiments to validate product changes or test hypotheses.",{"claudeCode":849},"product-on-purpose/pm-skills","measure-experiment-design","https://github.com/product-on-purpose/pm-skills",{"basePath":853,"githubOwner":854,"githubRepo":855,"locale":18,"slug":850,"type":262},"skills/measure-experiment-design","product-on-purpose","pm-skills",{"evaluate":857,"extract":863},{"promptVersionExtension":213,"promptVersionScoring":214,"score":286,"tags":858,"targetMarket":225,"tier":226},[859,860,861,862,224],"ab-testing","experimentation","product-management","a-b-testing",{"commitSha":296},{"parentExtensionId":865,"repoId":866},"k1721116hsfj7zg78w03432n8986n6y8","kd78ksv1wjj826ds5j1sh2kqnx86mhqf",[862,859,224,860,861],{"evaluatedAt":869,"extractAt":870,"updatedAt":869},1778696438706,1778695720086,{"_creationTime":872,"_id":873,"community":874,"display":875,"identity":881,"providers":886,"relations":894,"tags":896,"workflow":897},1778691799740.488,"k1707r3f2j67714pvq6wk0r6y186m2zd",{"reviewCount":8},{"description":876,"installMethods":877,"name":879,"sourceUrl":880},"Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.",{"claudeCode":878},"K-Dense-AI/claude-scientific-skills","PyDESeq2","https://github.com/K-Dense-AI/claude-scientific-skills",{"basePath":882,"githubOwner":883,"githubRepo":884,"locale":18,"slug":885,"type":262},"scientific-skills/pydeseq2","K-Dense-AI","claude-scientific-skills","pydeseq2",{"evaluate":887,"extract":893},{"promptVersionExtension":213,"promptVersionScoring":214,"score":286,"tags":888,"targetMarket":225,"tier":226},[889,890,891,892,836,224],"bioinformatics","genomics","rna-seq","deseq2",{"commitSha":296,"license":313},{"repoId":895},"kd79rphh5gexy91xmpxc05h5mh86mm9r",[889,224,892,890,836,891],{"evaluatedAt":898,"extractAt":899,"updatedAt":898},1778693766611,1778691799740,{"_creationTime":901,"_id":902,"community":903,"display":904,"identity":910,"providers":914,"relations":922,"tags":925,"workflow":926},1778692306427.1045,"k17d6kt5pj00skt9795rm9q2dx86nsbt",{"reviewCount":8},{"description":905,"installMethods":906,"name":908,"sourceUrl":909},"YOLO mode. Spawns 4 parallel C-suite agents (CEO, CTO, CFO, COO). Each analyzes the business from their perspective using ALL available data. Produces unfiltered Hard Truths report. After user types YOLO, autonomously runs the business for a day using /loop.",{"claudeCode":907},"Lifecycle-Innovations-Limited/claude-ops","ops-yolo","https://github.com/Lifecycle-Innovations-Limited/claude-ops",{"basePath":911,"githubOwner":912,"githubRepo":913,"locale":18,"slug":908,"type":262},"claude-ops/skills/ops-yolo","Lifecycle-Innovations-Limited","claude-ops",{"evaluate":915,"extract":921},{"promptVersionExtension":213,"promptVersionScoring":214,"score":286,"tags":916,"targetMarket":225,"tier":226},[917,918,919,920,224],"business-operations","ai-agents","automation","c-suite",{"commitSha":296},{"parentExtensionId":923,"repoId":924},"k17d0t6ns7y6t377pfprg128hd86nm89","kd7d52tcek2e34r805zs06b10d86n39v",[918,919,917,920,224],{"evaluatedAt":927,"extractAt":928,"updatedAt":927},1778693076881,1778692306427,{"_creationTime":930,"_id":931,"community":932,"display":933,"identity":939,"providers":944,"relations":953,"tags":955,"workflow":956},1778688112811.7532,"k170sm4mefgrkddcg6yc5d8pk986ncnv",{"reviewCount":8},{"description":934,"installMethods":935,"name":937,"sourceUrl":938},"Generate predictive pipeline forecasts with confidence intervals and scenario modeling for revenue planning",{"claudeCode":936},"guia-matthieu/clawfu-skills","Pipeline Forecasting","https://github.com/guia-matthieu/clawfu-skills",{"basePath":940,"githubOwner":941,"githubRepo":942,"locale":18,"slug":943,"type":262},"skills/revops/pipeline-forecasting","guia-matthieu","clawfu-skills","pipeline-forecasting",{"evaluate":945,"extract":952},{"promptVersionExtension":213,"promptVersionScoring":214,"score":286,"tags":946,"targetMarket":225,"tier":226},[947,948,949,950,224,951],"revenue","forecasting","sales","ops","scenario-planning",{"commitSha":296,"license":313},{"repoId":954},"kd72qvzyvm658ya7pbyh5ey47h86md53",[224,948,950,947,949,951],{"evaluatedAt":957,"extractAt":958,"updatedAt":957},1778690518099,1778688112811]