[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-cdeust-cortex-consolidate-en":3,"guides-for-cdeust-cortex-consolidate":775,"similar-k17dkh1rr7yxf6rkxpxfx2515x86ndee-en":776},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":239,"parentExtension":248,"providers":305,"relations":309,"repo":310,"tags":773,"workflow":774},1778683562157.8757,"k17dkh1rr7yxf6rkxpxfx2515x86ndee",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"cdeust/Cortex","cortex-consolidate","https://github.com/cdeust/Cortex",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":241},1778683645625.927,"kn7b3dcrf4qdj0t398arn26jvx86n2r2","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of memory maintenance and evolution, using terms like 'decay old memories', 'compress stale content', and 'consolidate episodic memories' which directly address user pain points.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a unique selling proposition by implementing a biologically-inspired memory maintenance pipeline with specific mechanisms like heat decay, compression stages, CLS consolidation, causal graph discovery, and sleep-like replay, going beyond basic memory storage.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for memory maintenance, including full pipeline execution, review of results, selective operations like forgetting, and checkpointing/restoring, indicating it's ready for production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on memory maintenance and evolution, with clearly defined tools for consolidation, forgetting, and checkpointing, adhering to a single responsibility principle.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's capabilities, clearly outlining the memory maintenance process, its use cases, and benefits.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill exposes narrow, verb-noun specialist tools such as `cortex:consolidate`, `cortex:forget`, and `cortex:checkpoint`, which are well-scoped and prevent arbitrary command execution.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All parameters for `cortex:consolidate`, `cortex:forget`, and `cortex:checkpoint` are clearly documented within the SKILL.md, including optional parameters like `hard` and `force` for `forget`.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Tool names like `consolidate`, `forget`, and `checkpoint` are descriptive, follow kebab-case, and clearly indicate their function within the memory maintenance domain.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The tools `cortex:consolidate`, `cortex:forget`, and `cortex:checkpoint` have well-defined, minimal input schemas and documented outputs that directly correspond to their stated tasks.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT license, which is permissive and suitable for a wide range of uses.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The latest commit was on 2026-05-13, indicating very recent maintenance activity.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project includes a lockfile (`hasLockfile: true`) and CI, indicating good practices for managing dependencies.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The skill does not appear to handle secrets directly; local execution and focus on memory maintenance suggest no sensitive data is exposed.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The skill's tools operate on internal memory structures and do not load or execute third-party data as instructions, mitigating injection risks.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The skill runs locally and does not fetch external content at runtime, eliminating the risk of transitive supply-chain attacks.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The skill operates locally on the user's machine, focusing on memory management within its own scope, with no indications of attempting to modify files outside its designated area.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No detached processes or retry loops around denied tool calls were observed in the skill's scripts or documentation.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The skill operates locally and does not submit any data to third parties, preventing data exfiltration.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content and descriptions are 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 code appears to be plain, readable source, with no evidence of obfuscation techniques like base64 encoding or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill makes no structural assumptions about the user's project organization outside its own internal memory structures.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 0 open issues in the last 90 days and 16 closed issues, the maintainers are actively addressing issues, indicating good engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","A meaningful version number (v3.15.0) is clearly declared in the README and CHANGELOG, facilitating release tracking and management.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Input parameters for the tools are well-defined and documented, suggesting appropriate validation and sanitization.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The skill's operations are focused on memory maintenance and are not destructive; no destructive primitives requiring confirmation were found.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The skill's documentation implies robust error handling for its operations, and the structure suggests errors would be reported meaningfully.",{"category":110,"check":114,"severity":115,"summary":116},"Logging","not_applicable","The skill is read-only in its core function and does not perform destructive actions or outbound calls that would necessitate local audit logging.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The skill operates on local memory structures and does not handle personal data, thus not posing GDPR compliance risks.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The extension operates locally and has no regional restrictions, making it globally applicable.",{"category":91,"check":125,"severity":24,"summary":126},"Runtime stability","The skill appears to be cross-platform compatible, relying on standard Python and PostgreSQL which are widely available.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README is extensive, clearly states the extension's purpose, and provides comprehensive details about its science and capabilities.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","The skill exposes a focused set of three tools (`consolidate`, `forget`, `checkpoint`), which is well within the ideal range.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The exposed tools (`consolidate`, `forget`, `checkpoint`) cover distinct functionalities with no overlapping near-synonym names.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All features described in the README and SKILL.md, such as memory decay and consolidation, are implemented and reflected in the tool definitions.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for Claude Code and a verification command (`python3 -m mcp_server.doctor`).",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","While specific error messages are not detailed, the skill's structure and documentation suggest that errors would be reported with sufficient context for remediation.",{"category":103,"check":148,"severity":24,"summary":149},"Pinned dependencies","The presence of a lockfile and CI suggests dependencies are pinned and managed appropriately.",{"category":33,"check":151,"severity":115,"summary":152},"Dry-run preview","The skill's operations are focused on memory maintenance and are not state-changing in a destructive or outbound manner, making a dry-run feature inapplicable.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The memory maintenance operations are designed to be idempotent or inherently safe for retries, and the underlying infrastructure likely handles timeouts appropriately.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill runs locally and does not emit any telemetry, thus adhering to opt-in principles by default.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly states the purpose (memory maintenance) and its use cases (periodic cleanup, after imports, long sessions), precisely defining what it does and when to use it.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise and self-contained, clearly summarizing the core capability and providing relevant trigger phrases without excessive keyword stuffing.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured, with core instructions and workflow details provided concisely, and deeper scientific explanations or benchmarks linked or deferred.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the main procedure and links to external documents for deeper dives into science and benchmarks, employing progressive disclosure.",{"category":170,"check":174,"severity":115,"summary":175},"Forked exploration","This skill is a direct tool invocation and does not involve deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md provides clear, ready-to-use examples for running the `cortex:consolidate` command and other selective operations, demonstrating input and expected outcome.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses potential edge cases and limitations, such as not over-consolidating and checking stats first, along with recovery steps like checkpointing.",{"category":110,"check":183,"severity":115,"summary":184},"Tool Fallback","This skill does not appear to rely on external MCP servers or tools that would require a fallback mechanism.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The documentation implies that unexpected states, such as needing to check stats before consolidating, would be handled, and the checkpointing feature supports safe operation.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and focuses solely on memory maintenance, with no implicit reliance on other skills being loaded.",1778683645516,"This skill performs comprehensive memory maintenance operations locally, including decaying old memories, compressing stale content, consolidating episodic memories into semantic knowledge, and running sleep-like replay. It utilizes specialized tools for full pipeline execution, selective forgetting, and checkpointing.",[195,196,197,198,199],"Local memory decay and compression","Episodic to semantic memory consolidation","Sleep-like replay for strengthening memories","Selective memory forgetting and permanent deletion","Checkpointing and restoring memory states",[201,202,203],"Performing memory maintenance on remote systems.","Modifying core LLM behavior beyond memory recall.","Storing new memories; focuses solely on maintenance and evolution of existing ones.","3.0.0","4.4.0","To maintain and evolve the AI's memory system by applying biologically-inspired consolidation processes, ensuring healthy and efficient knowledge recall.","The skill exhibits exceptionally high quality across all categories, with no critical or warning findings. Its documentation is thorough, its tools are well-scoped and secure, and its scientific underpinnings are rigorously backed by research.",97,"A robust and scientifically grounded skill for local AI memory maintenance and evolution.",[211,212,213,214,215],"memory","maintenance","consolidation","knowledge-management","ai-agent","global","verified",[219,220,221,222],"When the user requests memory cleanup or consolidation.","Periodically to keep the memory system healthy.","After importing many memories or at the end of a long session.","For targeted deletion of specific memories.",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"popularity":235,"security":237,"testCoverage":240},{"hasLockfile":225},true,1778683620967,{"descriptionLength":228,"readmeSize":229},394,36381,{"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},1778683645625,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":13,"type":247},"skills/cortex-consolidate","cdeust","Cortex","skill",{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":255,"parentExtension":258,"providers":292,"relations":301,"tags":302,"workflow":303},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":298},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":295,"targetMarket":216,"tier":217},99,[211,296,276,273,278,279,297],"persistence","developer-tools",{"commitSha":281,"license":299,"plugin":300},"MIT",{"mcpCount":8,"provider":285,"skillCount":236},{"parentExtensionId":260,"repoId":287},[273,297,276,211,296,279,278],{"evaluatedAt":304,"extractAt":291,"updatedAt":304},1778683602463,{"evaluate":306,"extract":308},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":307,"targetMarket":216,"tier":217},[211,212,213,214,215],{"commitSha":281},{"parentExtensionId":250,"repoId":287},{"_creationTime":311,"_id":287,"identity":312,"providers":313,"workflow":768},1778683544930.988,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":314,"discover":740,"extract":743,"github":744,"npm":767},{"commitSha":281,"extensions":315},[316,329,342,351,356,364,372,380,388,396,404,412,420,428,436,444,452],{"basePath":256,"description":263,"displayName":265,"installMethods":317,"rationale":318,"selectedPaths":319,"source":328,"sourceLanguage":18,"type":267},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[320,323,325],{"path":321,"priority":322},".claude-plugin/marketplace.json","mandatory",{"path":324,"priority":322},"README.md",{"path":326,"priority":327},"LICENSE","high","rule",{"basePath":256,"description":253,"displayName":330,"installMethods":331,"rationale":332,"selectedPaths":333,"source":328,"sourceLanguage":18,"type":257},"cortex",{"claudeCode":246},"inline plugin source from marketplace.json at /",[334,335,336,338,340],{"path":324,"priority":322},{"path":326,"priority":327},{"path":337,"priority":322},".mcp.json",{"path":339,"priority":327},"agents/cortex-wiki-groomer.md",{"path":341,"priority":327},"commands/methodology.md",{"basePath":343,"description":344,"displayName":345,"installMethods":346,"rationale":347,"selectedPaths":348,"source":328,"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",[349],{"path":350,"priority":322},"SKILL.md",{"basePath":244,"description":10,"displayName":13,"installMethods":352,"rationale":353,"selectedPaths":354,"source":328,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at skills/cortex-consolidate/SKILL.md",[355],{"path":350,"priority":322},{"basePath":357,"description":358,"displayName":359,"installMethods":360,"rationale":361,"selectedPaths":362,"source":328,"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",[363],{"path":350,"priority":322},{"basePath":365,"description":366,"displayName":367,"installMethods":368,"rationale":369,"selectedPaths":370,"source":328,"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",[371],{"path":350,"priority":322},{"basePath":373,"description":374,"displayName":375,"installMethods":376,"rationale":377,"selectedPaths":378,"source":328,"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",[379],{"path":350,"priority":322},{"basePath":381,"description":382,"displayName":383,"installMethods":384,"rationale":385,"selectedPaths":386,"source":328,"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",[387],{"path":350,"priority":322},{"basePath":389,"description":390,"displayName":391,"installMethods":392,"rationale":393,"selectedPaths":394,"source":328,"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",[395],{"path":350,"priority":322},{"basePath":397,"description":398,"displayName":399,"installMethods":400,"rationale":401,"selectedPaths":402,"source":328,"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",[403],{"path":350,"priority":322},{"basePath":405,"description":406,"displayName":407,"installMethods":408,"rationale":409,"selectedPaths":410,"source":328,"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",[411],{"path":350,"priority":322},{"basePath":413,"description":414,"displayName":415,"installMethods":416,"rationale":417,"selectedPaths":418,"source":328,"sourceLanguage":18,"type":247},"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",[419],{"path":350,"priority":322},{"basePath":421,"description":422,"displayName":423,"installMethods":424,"rationale":425,"selectedPaths":426,"source":328,"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",[427],{"path":350,"priority":322},{"basePath":429,"description":430,"displayName":431,"installMethods":432,"rationale":433,"selectedPaths":434,"source":328,"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",[435],{"path":350,"priority":322},{"basePath":437,"description":438,"displayName":439,"installMethods":440,"rationale":441,"selectedPaths":442,"source":328,"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",[443],{"path":350,"priority":322},{"basePath":445,"description":446,"displayName":447,"installMethods":448,"rationale":449,"selectedPaths":450,"source":328,"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",[451],{"path":350,"priority":322},{"basePath":256,"description":453,"displayName":454,"installMethods":455,"license":299,"rationale":456,"selectedPaths":457,"source":328,"sourceLanguage":18,"type":274},"Persistent memory and cognitive profiling for Claude Code","neuro-cortex-memory",{"pypi":454},"pyproject.toml with mcp/fastmcp dependency + scripts at pyproject.toml",[458,460,462,463,464,467,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738],{"path":459,"priority":322},"package.json",{"path":461,"priority":322},"pyproject.toml",{"path":324,"priority":322},{"path":326,"priority":327},{"path":465,"priority":466},"mcp_server/doctor.py","medium",{"path":468,"priority":469},"mcp_server/__main__.py","low",{"path":471,"priority":469},"mcp_server/handlers/__init__.py",{"path":473,"priority":469},"mcp_server/handlers/_telemetry_wrap.py",{"path":475,"priority":469},"mcp_server/handlers/_tool_meta.py",{"path":477,"priority":469},"mcp_server/handlers/add_rule.py",{"path":479,"priority":469},"mcp_server/handlers/admission.py",{"path":481,"priority":469},"mcp_server/handlers/anchor.py",{"path":483,"priority":469},"mcp_server/handlers/assess_coverage.py",{"path":485,"priority":469},"mcp_server/handlers/backfill_helpers.py",{"path":487,"priority":469},"mcp_server/handlers/backfill_memories.py",{"path":489,"priority":469},"mcp_server/handlers/change_impact.py",{"path":491,"priority":469},"mcp_server/handlers/checkpoint.py",{"path":493,"priority":469},"mcp_server/handlers/codebase_analyze.py",{"path":495,"priority":469},"mcp_server/handlers/codebase_analyze_helpers.py",{"path":497,"priority":469},"mcp_server/handlers/consolidate.py",{"path":499,"priority":469},"mcp_server/handlers/consolidation/__init__.py",{"path":501,"priority":469},"mcp_server/handlers/consolidation/cascade.py",{"path":503,"priority":469},"mcp_server/handlers/consolidation/cls.py",{"path":505,"priority":469},"mcp_server/handlers/consolidation/compression.py",{"path":507,"priority":469},"mcp_server/handlers/consolidation/decay.py",{"path":509,"priority":469},"mcp_server/handlers/consolidation/homeostatic.py",{"path":511,"priority":469},"mcp_server/handlers/consolidation/memify.py",{"path":513,"priority":469},"mcp_server/handlers/consolidation/plasticity.py",{"path":515,"priority":469},"mcp_server/handlers/consolidation/pruning.py",{"path":517,"priority":469},"mcp_server/handlers/consolidation/sleep.py",{"path":519,"priority":469},"mcp_server/handlers/consolidation/transfer.py",{"path":521,"priority":469},"mcp_server/handlers/create_trigger.py",{"path":523,"priority":469},"mcp_server/handlers/detect_domain.py",{"path":525,"priority":469},"mcp_server/handlers/detect_gaps.py",{"path":527,"priority":469},"mcp_server/handlers/drill_down.py",{"path":529,"priority":469},"mcp_server/handlers/explore_features.py",{"path":531,"priority":469},"mcp_server/handlers/forget.py",{"path":533,"priority":469},"mcp_server/handlers/get_causal_chain.py",{"path":535,"priority":469},"mcp_server/handlers/get_methodology_graph.py",{"path":537,"priority":469},"mcp_server/handlers/get_project_story.py",{"path":539,"priority":469},"mcp_server/handlers/get_rules.py",{"path":541,"priority":469},"mcp_server/handlers/get_telemetry.py",{"path":543,"priority":469},"mcp_server/handlers/import_sessions.py",{"path":545,"priority":469},"mcp_server/handlers/ingest_codebase.py",{"path":547,"priority":469},"mcp_server/handlers/ingest_codebase_cypher.py",{"path":549,"priority":469},"mcp_server/handlers/ingest_codebase_graph.py",{"path":551,"priority":469},"mcp_server/handlers/ingest_codebase_pages.py",{"path":553,"priority":469},"mcp_server/handlers/ingest_codebase_schema.py",{"path":555,"priority":469},"mcp_server/handlers/ingest_codebase_writers.py",{"path":557,"priority":469},"mcp_server/handlers/ingest_helpers.py",{"path":559,"priority":469},"mcp_server/handlers/ingest_prd.py",{"path":561,"priority":469},"mcp_server/handlers/latency_class.py",{"path":563,"priority":469},"mcp_server/handlers/list_domains.py",{"path":565,"priority":469},"mcp_server/handlers/memories_facets.py",{"path":567,"priority":469},"mcp_server/handlers/memories_page.py",{"path":569,"priority":469},"mcp_server/handlers/memory_stats.py",{"path":571,"priority":469},"mcp_server/handlers/narrative.py",{"path":573,"priority":469},"mcp_server/handlers/navigate_memory.py",{"path":575,"priority":469},"mcp_server/handlers/open_visualization.py",{"path":577,"priority":469},"mcp_server/handlers/quadtree_handler.py",{"path":579,"priority":469},"mcp_server/handlers/query_methodology.py",{"path":581,"priority":469},"mcp_server/handlers/query_workflow_graph.py",{"path":583,"priority":469},"mcp_server/handlers/rate_memory.py",{"path":585,"priority":469},"mcp_server/handlers/rebuild_profiles.py",{"path":587,"priority":469},"mcp_server/handlers/recall.py",{"path":589,"priority":469},"mcp_server/handlers/recall_helpers.py",{"path":591,"priority":469},"mcp_server/handlers/recall_hierarchical.py",{"path":593,"priority":469},"mcp_server/handlers/recompute_layout.py",{"path":595,"priority":469},"mcp_server/handlers/record_session_end.py",{"path":597,"priority":469},"mcp_server/handlers/remember.py",{"path":599,"priority":469},"mcp_server/handlers/remember_helpers.py",{"path":601,"priority":469},"mcp_server/handlers/remember_response.py",{"path":603,"priority":469},"mcp_server/handlers/seed_project.py",{"path":605,"priority":469},"mcp_server/handlers/seed_project_constants.py",{"path":607,"priority":469},"mcp_server/handlers/seed_project_stages.py",{"path":609,"priority":469},"mcp_server/handlers/sync_instructions.py",{"path":611,"priority":469},"mcp_server/handlers/tile_handler.py",{"path":613,"priority":469},"mcp_server/handlers/unified_search.py",{"path":615,"priority":469},"mcp_server/handlers/validate_memory.py",{"path":617,"priority":469},"mcp_server/handlers/wiki_adr.py",{"path":619,"priority":469},"mcp_server/handlers/wiki_api.py",{"path":621,"priority":469},"mcp_server/handlers/wiki_compile.py",{"path":623,"priority":469},"mcp_server/handlers/wiki_consolidate.py",{"path":625,"priority":469},"mcp_server/handlers/wiki_curate.py",{"path":627,"priority":469},"mcp_server/handlers/wiki_emerge.py",{"path":629,"priority":469},"mcp_server/handlers/wiki_export.py",{"path":631,"priority":469},"mcp_server/handlers/wiki_extract.py",{"path":633,"priority":469},"mcp_server/handlers/wiki_link.py",{"path":635,"priority":469},"mcp_server/handlers/wiki_list.py",{"path":637,"priority":469},"mcp_server/handlers/wiki_migrate.py",{"path":639,"priority":469},"mcp_server/handlers/wiki_pipeline.py",{"path":641,"priority":469},"mcp_server/handlers/wiki_purge.py",{"path":643,"priority":469},"mcp_server/handlers/wiki_read.py",{"path":645,"priority":469},"mcp_server/handlers/wiki_refine.py",{"path":647,"priority":469},"mcp_server/handlers/wiki_reindex.py",{"path":649,"priority":469},"mcp_server/handlers/wiki_rename.py",{"path":651,"priority":469},"mcp_server/handlers/wiki_resolve.py",{"path":653,"priority":469},"mcp_server/handlers/wiki_seed_codebase.py",{"path":655,"priority":469},"mcp_server/handlers/wiki_synthesize.py",{"path":657,"priority":469},"mcp_server/handlers/wiki_verify.py",{"path":659,"priority":469},"mcp_server/handlers/wiki_view.py",{"path":661,"priority":469},"mcp_server/handlers/wiki_write.py",{"path":663,"priority":469},"mcp_server/handlers/workflow_graph.py",{"path":665,"priority":469},"tests_py/handlers/__init__.py",{"path":667,"priority":469},"tests_py/handlers/test_a3_homeostatic_scalar.py",{"path":669,"priority":469},"tests_py/handlers/test_admission.py",{"path":671,"priority":469},"tests_py/handlers/test_backfill_discover_files_issue15.py",{"path":673,"priority":469},"tests_py/handlers/test_backfill_heat.py",{"path":675,"priority":469},"tests_py/handlers/test_beam_anticheat.py",{"path":677,"priority":469},"tests_py/handlers/test_checkpoint.py",{"path":679,"priority":469},"tests_py/handlers/test_cls_diagnostics.py",{"path":681,"priority":469},"tests_py/handlers/test_codebase_analyze_rglob.py",{"path":683,"priority":469},"tests_py/handlers/test_consolidate.py",{"path":685,"priority":469},"tests_py/handlers/test_consolidate_telemetry.py",{"path":687,"priority":469},"tests_py/handlers/test_detect_domain.py",{"path":689,"priority":469},"tests_py/handlers/test_explore_features.py",{"path":691,"priority":469},"tests_py/handlers/test_get_methodology_graph.py",{"path":693,"priority":469},"tests_py/handlers/test_get_telemetry.py",{"path":695,"priority":469},"tests_py/handlers/test_import_sessions.py",{"path":697,"priority":469},"tests_py/handlers/test_import_sessions_stream.py",{"path":699,"priority":469},"tests_py/handlers/test_ingest_codebase.py",{"path":701,"priority":469},"tests_py/handlers/test_ingest_prd.py",{"path":703,"priority":469},"tests_py/handlers/test_latency_class.py",{"path":705,"priority":469},"tests_py/handlers/test_list_domains.py",{"path":707,"priority":469},"tests_py/handlers/test_memify_diagnostics.py",{"path":709,"priority":469},"tests_py/handlers/test_memory_stats.py",{"path":711,"priority":469},"tests_py/handlers/test_open_visualization.py",{"path":713,"priority":469},"tests_py/handlers/test_query_methodology.py",{"path":715,"priority":469},"tests_py/handlers/test_query_workflow_graph.py",{"path":717,"priority":469},"tests_py/handlers/test_rebuild_profiles.py",{"path":719,"priority":469},"tests_py/handlers/test_recall.py",{"path":721,"priority":469},"tests_py/handlers/test_recall_enhancements.py",{"path":723,"priority":469},"tests_py/handlers/test_recall_hierarchical_bounded.py",{"path":725,"priority":469},"tests_py/handlers/test_recall_low_signal_filter.py",{"path":727,"priority":469},"tests_py/handlers/test_record_session_end.py",{"path":729,"priority":469},"tests_py/handlers/test_registry.py",{"path":731,"priority":469},"tests_py/handlers/test_remember.py",{"path":733,"priority":469},"tests_py/handlers/test_seed_project.py",{"path":735,"priority":469},"tests_py/handlers/test_wiki_redirect_handlers.py",{"path":737,"priority":469},"tests_py/handlers/test_wiki_seed_codebase.py",{"path":739,"priority":469},"tests_py/handlers/test_wiki_sync_errors.py",{"sources":741},[742],"manual",{"npmPackage":454},{"closedIssues90d":231,"description":745,"forks":232,"homepage":746,"license":238,"openIssues90d":8,"pushedAt":233,"readmeSize":229,"stars":234,"topics":747},"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",[748,749,750,751,275,752,753,754,755,756,757,758,759,760,761,762,763,764,765,766],"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":769,"discoverAt":770,"extractAt":771,"githubAt":771,"npmAt":772,"updatedAt":769},1778683561790,1778683544931,1778683554398,1778683559402,[215,213,214,212,211],{"evaluatedAt":242,"extractAt":291,"updatedAt":242},[],[777,805,834,859,887,916],{"_creationTime":778,"_id":779,"community":780,"display":781,"identity":787,"providers":791,"relations":798,"tags":801,"workflow":802},1778696595410.5657,"k17bk9m02r7jkbzzqapbzfvq8h86m6qn",{"reviewCount":8},{"description":782,"installMethods":783,"name":785,"sourceUrl":786},"Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.",{"claudeCode":784},"rohitg00/pro-workflow","orchestrate","https://github.com/rohitg00/pro-workflow",{"basePath":788,"githubOwner":789,"githubRepo":790,"locale":18,"slug":785,"type":247},"skills/orchestrate","rohitg00","pro-workflow",{"evaluate":792,"extract":797},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":793,"targetMarket":216,"tier":217},[794,795,796,211,214],"llm-ops","agent","workflow",{"commitSha":281},{"parentExtensionId":799,"repoId":800},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[795,214,794,211,796],{"evaluatedAt":803,"extractAt":804,"updatedAt":803},1778696881233,1778696595410,{"_creationTime":806,"_id":807,"community":808,"display":809,"identity":816,"providers":819,"relations":827,"tags":829,"workflow":830},1778696140284.4526,"k17ebph1z8m6amj5ederqx1w1h86mdck",{"reviewCount":8},{"description":810,"installMethods":811,"name":814,"sourceUrl":815},"Diagnoses bloated MEMORY.md files, splits oversized sections into domain-specific files, archives stale daily logs, and deduplicates content using a 3-tier hierarchy (MEMORY.md → domains/ → archive/). Use when MEMORY.md exceeds 10KB, context pressure is high, or the user asks to clean up, organize, or maintain agent memory files. Works alongside Mem0, Supermemory, QMD, or standalone.",{"bash":812,"claudeCode":813},"curl -fsSL https://raw.githubusercontent.com/Ramsbaby/openclaw-memorybox/main/install.sh | bash","Ramsbaby/openclaw-memorybox","MemoryBox","https://github.com/Ramsbaby/openclaw-memorybox",{"basePath":247,"githubOwner":817,"githubRepo":818,"locale":18,"slug":247,"type":247},"Ramsbaby","openclaw-memorybox",{"evaluate":820,"extract":826},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":821,"targetMarket":216,"tier":217},[822,215,823,212,824,825],"memory-management","cli","organization","typescript",{"commitSha":281,"license":299},{"repoId":828},"kd7arj8x2xnfzd1vs9ave44m1d86nacw",[215,823,212,822,824,825],{"evaluatedAt":831,"extractAt":832,"updatedAt":833},1778696193032,1778696140284,1778696222982,{"_creationTime":835,"_id":836,"community":837,"display":838,"identity":843,"providers":847,"relations":853,"tags":855,"workflow":856},1778696691708.3027,"k174mp6hf33cptbna2p91t2ts586n4ad",{"reviewCount":8},{"description":839,"installMethods":840,"name":822,"sourceUrl":842},"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":841},"ruvnet/ruflo","https://github.com/ruvnet/ruflo",{"basePath":844,"githubOwner":845,"githubRepo":846,"locale":18,"slug":822,"type":247},".agents/skills/memory-management","ruvnet","ruflo",{"evaluate":848,"extract":852},{"promptVersionExtension":204,"promptVersionScoring":205,"score":294,"tags":849,"targetMarket":216,"tier":217},[211,759,214,850,851],"agentdb","hnsw",{"commitSha":281},{"repoId":854},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[850,851,214,211,759],{"evaluatedAt":857,"extractAt":858,"updatedAt":857},1778699160670,1778696691708,{"_creationTime":860,"_id":861,"community":862,"display":863,"identity":869,"providers":872,"relations":880,"tags":882,"workflow":883},1778699438912.8826,"k170fxxh22hdspg4vr94whgj1986mpr9",{"reviewCount":8},{"description":864,"installMethods":865,"name":867,"sourceUrl":868},"Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.",{"claudeCode":866},"yvgude/lean-ctx","lean-ctx","https://github.com/yvgude/lean-ctx",{"basePath":870,"githubOwner":871,"githubRepo":867,"locale":18,"slug":867,"type":247},"skills/lean-ctx","yvgude",{"evaluate":873,"extract":879},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":874,"targetMarket":216,"tier":217},[875,215,876,297,877,878],"context-compression","cli-tools","rust","code-analysis",{"commitSha":281},{"repoId":881},"kd7dxtfr9j3z54hs3bz0218e1n86may0",[215,876,878,875,297,877],{"evaluatedAt":884,"extractAt":885,"updatedAt":886},1778699456179,1778699438912,1778699517795,{"_creationTime":888,"_id":889,"community":890,"display":891,"identity":897,"providers":901,"relations":909,"tags":912,"workflow":913},1778696833339.6243,"k174g80xa9zxhydbncvpf0xzy986nvx5",{"reviewCount":8},{"description":892,"installMethods":893,"name":895,"sourceUrl":896},"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.",{"claudeCode":894},"sanjay3290/ai-skills","manus","https://github.com/sanjay3290/ai-skills",{"basePath":898,"githubOwner":899,"githubRepo":900,"locale":18,"slug":895,"type":247},"skills/manus","sanjay3290","ai-skills",{"evaluate":902,"extract":908},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":903,"targetMarket":216,"tier":217},[215,904,905,906,907],"autonomous-execution","research","automation","api-integration",{"commitSha":281},{"parentExtensionId":910,"repoId":911},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[215,907,906,904,905],{"evaluatedAt":914,"extractAt":915,"updatedAt":914},1778697107270,1778696833339,{"_creationTime":917,"_id":918,"community":919,"display":920,"identity":926,"providers":931,"relations":938,"tags":941,"workflow":942},1778693539593.186,"k17bgwvhb6h29py715de1cm9xd86msq6",{"reviewCount":8},{"description":921,"installMethods":922,"name":924,"sourceUrl":925},"Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on \"risk\", \"drawdown\", \"tilt\", \"position size\", \"lot size\", \"confidence\", \"revenge trading\", \"overtrading\", \"discipline\".",{"claudeCode":923},"mnemox-ai/tradememory-protocol","Risk Management","https://github.com/mnemox-ai/tradememory-protocol",{"basePath":927,"githubOwner":928,"githubRepo":929,"locale":18,"slug":930,"type":247},"tradememory-plugin/skills/risk-management","mnemox-ai","tradememory-protocol","risk-management",{"evaluate":932,"extract":937},{"promptVersionExtension":204,"promptVersionScoring":205,"score":271,"tags":933,"targetMarket":216,"tier":217},[934,930,215,935,936],"trading","behavioral-analysis","finance",{"commitSha":281,"license":299},{"parentExtensionId":939,"repoId":940},"k170vxkqee48k2xq1v55a025nh86nzn7","kd73z11kfekksxyrs8ds0snacs86ncdy",[215,935,936,930,934],{"evaluatedAt":943,"extractAt":944,"updatedAt":945},1778693700524,1778693539593,1778693833120]