[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-hilyfux-knowledge-graph-en":3,"guides-for-hilyfux-knowledge-graph":352,"similar-k170wck2hytdh71br77mdwdc8986np98-en":353},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":222,"isFallback":207,"parentExtension":226,"providers":281,"relations":285,"repo":286,"tags":349,"workflow":350},1778688381229.8945,"k170wck2hytdh71br77mdwdc8986np98",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Use when user says \"update/refresh knowledge graph\", \"graph status\", \"blind spots\", \"knowledge node coverage\", \"CLAUDE.md coverage\", or \"init knowledge graph\". Also use when receiving a \"[kg auto-trigger]\" message injected by hooks. Do not use for regular coding tasks.\n",{"claudeCode":12},"hilyfux/knowledge-graph","knowledge-graph","https://github.com/hilyfux/knowledge-graph",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":205,"workflow":220},1778688451722.8535,"kn7fjdsn8hagmetrr34dn4qw5986mpgh","en",{"checks":20,"evaluatedAt":174,"extensionSummary":175,"features":176,"nonGoals":182,"promptVersionExtension":186,"promptVersionScoring":187,"purpose":188,"rationale":189,"score":190,"summary":191,"tags":192,"targetMarket":198,"tier":199,"useCases":200},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,80,83,86,89,92,95,98,102,105,110,114,118,121,125,128,131,134,138,141,144,147,150,153,156,160,164,168,169,170,171,172,173],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the purpose of updating/refreshing a knowledge graph and mentions specific triggers and use cases, including receiving a '[kg auto-trigger]' message.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers significant value by providing persistent, repo-native memory for AI agents, learning over time, predicting context, and surviving session resets, which goes beyond default LLM behavior.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is designed for production use with bash scripts, clear commands, and hooks for Claude Code, and supports MCP for other agents, covering the full lifecycle of knowledge management within a repository.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on managing and leveraging a project's knowledge graph through file analysis and git history, without extending into unrelated domains like testing or deployment.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The provided description is concise, readable, and accurately reflects the extension's functionality, including its triggers and non-goals.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The description clearly defines the artifact (knowledge graph), the task (update/refresh), and specific user intents, along with explicit non-goals.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is concise and self-contained, effectively summarizing the core capability and providing clear trigger phrases.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md is well-structured with clear modes and steps, delegating detailed architecture and requirements to external documentation files.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","Detailed architecture, installation, and configuration information are provided in separate documentation files, adhering to progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","The skill does not appear to involve deep code review or multi-file exploration that would necessitate `context: fork`.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The README provides clear quick start examples for macOS/Linux and Windows, along with explanations for Codex/MCP usage.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The script logic appears to handle edge cases like missing files, non-project directories, and insufficient event data, with informative error messages.",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","The skill relies on internal bash scripts and standard Unix utilities, with no external MCP servers that would require fallback.",{"category":69,"check":70,"severity":24,"summary":71},"Safety","Halt on unexpected state","The scripts include guards for project directory, event validation, and timeout handling, halting on unexpected states.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill is self-contained and does not appear to implicitly rely on other skills; cross-references are explicit in documentation.",{"category":77,"check":78,"severity":24,"summary":79},"Security","Secret Management","The extension operates on project files and git history, and does not appear to handle or expose secrets.",{"category":77,"check":81,"severity":24,"summary":82},"Injection","The scripts process file paths and git data locally, with input validation and no runtime downloads of external instructions.",{"category":77,"check":84,"severity":24,"summary":85},"Transitive Supply-Chain Grenades","The extension relies on bundled bash scripts and local git commands, avoiding runtime downloads or remote code execution.",{"category":77,"check":87,"severity":24,"summary":88},"Sandbox Isolation","The scripts operate within the project directory and use standard tools, with no indication of attempting to modify files outside the project scope.",{"category":77,"check":90,"severity":24,"summary":91},"Sandbox escape primitives","The bash scripts do not employ detached processes, retry loops on denied calls, or other sandbox-escape primitives.",{"category":77,"check":93,"severity":24,"summary":94},"Data Exfiltration","The extension focuses on local project analysis and does not include instructions to read or submit confidential data to a third party.",{"category":77,"check":96,"severity":24,"summary":97},"Hidden Text Tricks","The bundled scripts and markdown files appear free of hidden steering tricks, unicode tags, or obfuscation.",{"category":99,"check":100,"severity":24,"summary":101},"Hooks","Opaque code execution","The bundled scripts are plain bash, with no obfuscation, base64 payloads, or runtime code fetches.",{"category":73,"check":103,"severity":24,"summary":104},"Structural Assumption","The skill makes assumptions about project structure (e.g., presence of .knowledge-graph directory) but relies on standard git and bash, with error handling for missing components.",{"category":106,"check":107,"severity":108,"summary":109},"Trust","Issues Attention","info","There is 1 open issue and 0 closed issues in the last 90 days, indicating low recent activity but no direct negative signal.",{"category":111,"check":112,"severity":24,"summary":113},"Versioning","Release Management","The project uses versioning in the `VERSION` file and Git commit hashes, and the README references the MIT license.",{"category":115,"check":116,"severity":24,"summary":117},"Execution","Pinned dependencies","The extension relies on standard bash utilities (`jq`, `git`) and does not appear to bundle or pin third-party dependencies.",{"category":33,"check":119,"severity":56,"summary":120},"Dry-run preview","The extension is primarily analytical and does not perform state-changing operations that would require a dry-run mode.",{"category":122,"check":123,"severity":24,"summary":124},"Protocol","Idempotent retry & timeouts","The bash scripts are designed to be idempotent where applicable (e.g., initialization) and use timeouts for critical operations like analysis.",{"category":77,"check":126,"severity":24,"summary":127},"Unguarded Destructive Operations","The extension's operations are primarily analytical and write to a local `.knowledge-graph` directory, with no destructive operations on the user's project code.",{"category":65,"check":129,"severity":24,"summary":130},"Error Handling","The bash scripts include error checking, logging to event files, and informative messages for various failure conditions.",{"category":65,"check":132,"severity":24,"summary":133},"Logging","Destructive actions (writes) and errors are logged to `.knowledge-graph/graph-events.jsonl`, providing an audit trail.",{"category":135,"check":136,"severity":56,"summary":137},"Compliance","GDPR","The extension operates on project file paths and git history, and does not process personal data.",{"category":135,"check":139,"severity":24,"summary":140},"Target market","The extension is designed to work with standard bash and git, making it globally applicable without regional restrictions.",{"category":73,"check":142,"severity":24,"summary":143},"Runtime stability","The extension relies on standard bash utilities and git, ensuring multi-platform compatibility (macOS, Linux, Windows via Git Bash/WSL).",{"category":47,"check":145,"severity":24,"summary":146},"README","A comprehensive README exists, clearly detailing the extension's purpose, features, alternatives, and usage.",{"category":33,"check":148,"severity":24,"summary":149},"Tool surface size","The skill exposes a reasonable number of commands for its scope (init, update, status, query), and the MCP server provides 4 core tools.",{"category":40,"check":151,"severity":24,"summary":152},"Overlapping near-synonym tools","The exposed commands and MCP tools (`kg_status`, `kg_query`, `kg_predict`, `kg_cochange`) cover distinct functionalities without significant overlap.",{"category":47,"check":154,"severity":24,"summary":155},"Phantom features","All advertised features, such as Claude Code integration, MCP server, and persistent memory, are implemented and described.",{"category":157,"check":158,"severity":24,"summary":159},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for macOS/Linux and Windows, including setup for Codex/MCP.",{"category":161,"check":162,"severity":24,"summary":163},"Errors","Actionable error messages","Errors provide context on what failed, why (e.g., missing nodes, pending events), and suggest remediation steps (e.g., run init/update command).",{"category":165,"check":166,"severity":24,"summary":167},"License","License usability","The project is licensed under the MIT license, which is permissive and widely usable.",{"category":33,"check":148,"severity":24,"summary":149},{"category":40,"check":151,"severity":24,"summary":152},{"category":47,"check":154,"severity":24,"summary":155},{"category":157,"check":158,"severity":24,"summary":159},{"category":161,"check":162,"severity":24,"summary":163},{"category":165,"check":166,"severity":24,"summary":167},1778688451537,"This skill provides a persistent, repository-native knowledge graph for AI coding agents, leveraging bash scripts and git history. It tracks file operations and commits to build a memory layer, supporting Claude Code natively and other MCP-aware agents via a bundled server.",[177,178,179,180,181],"Cross-agent memory (Claude Code, MCP)","Session-to-session continuity via snapshots","Predicts errors and context based on co-change history","Zero-interrupt workflow with background analysis","Evidence-based rules traceable to commits/errors",[183,184,185],"Replacing standard version control systems","Storing sensitive user data or credentials","Performing code generation or execution directly (focus is on context management)","3.0.0","4.4.0","To provide AI agents with persistent, project-specific memory that survives session resets and improves context awareness, ultimately leading to more accurate and efficient coding assistance.","The extension is well-documented, production-ready, and adheres to best practices. Findings are minor, such as low issue engagement and the absence of explicit dry-run functionality which is not applicable.",95,"A robust and well-documented skill for managing a project's knowledge graph, enhancing AI agent memory and context.",[193,13,194,195,196,197],"memory","git","bash","mcp","claude-code","global","verified",[201,202,203,204],"Maintaining consistent project context across AI agent sessions","Improving AI coding agent's understanding of project structure and dependencies","Ensuring AI agent follows project conventions and avoids known pitfalls","Providing auditable and version-controlled AI agent knowledge",{"codeQuality":206,"collectedAt":208,"documentation":209,"maintenance":212,"security":217,"testCoverage":219},{"hasLockfile":207},false,1778688431964,{"descriptionLength":210,"readmeSize":211},270,11113,{"closedIssues90d":8,"forks":8,"hasChangelog":213,"openIssues90d":214,"pushedAt":215,"stars":216},true,1,1778039913000,10,{"hasNpmPackage":207,"license":218,"smitheryVerified":207},"MIT",{"hasCi":207,"hasTests":213},{"updatedAt":221},1778688451722,{"basePath":223,"githubOwner":224,"githubRepo":13,"locale":18,"slug":13,"type":225},"skills/knowledge-graph","hilyfux","skill",{"_creationTime":227,"_id":228,"community":229,"display":230,"identity":233,"parentExtension":236,"providers":269,"relations":276,"tags":277,"workflow":278},1778688381229.8943,"k1716hqxxq72s4623edvj0sc2s86nrvv",{"reviewCount":8},{"description":231,"installMethods":232,"name":13,"sourceUrl":14},"Persistent memory layer for Claude Code — tracks file operations, mines co-change patterns, generates distributed CLAUDE.md knowledge nodes. Zero dependencies beyond jq.",{"claudeCode":13},{"basePath":234,"githubOwner":224,"githubRepo":13,"locale":18,"slug":13,"type":235},"","plugin",{"_creationTime":237,"_id":238,"community":239,"display":240,"identity":244,"providers":246,"relations":262,"tags":264,"workflow":265},1778688381229.894,"k17cbhxz59f98xy0xnhtgaq59186n3fa",{"reviewCount":8},{"description":241,"installMethods":242,"name":243,"sourceUrl":14},"Persistent memory layer for Claude Code with zero-interrupt architecture",{"claudeCode":12},"Knowledge Graph",{"basePath":234,"githubOwner":224,"githubRepo":13,"locale":18,"slug":13,"type":245},"marketplace",{"evaluate":247,"extract":256},{"promptVersionExtension":248,"promptVersionScoring":187,"score":249,"tags":250,"targetMarket":198,"tier":255},"3.1.0",93,[251,193,252,253,194,195,254],"ai","code","developer-tools","jq","community",{"commitSha":257,"license":218,"marketplace":258,"plugin":260},"HEAD",{"name":259,"pluginCount":214},"hilyfux-knowledge-graph",{"mcpCount":8,"provider":261,"skillCount":8},"classify",{"repoId":263},"kd726s6dkwq1hy5se33xvs6mqx86m67m",[251,195,252,253,194,254,193],{"evaluatedAt":266,"extractAt":267,"updatedAt":268},1778688415198,1778688381229,1778688496391,{"evaluate":270,"extract":274},{"promptVersionExtension":186,"promptVersionScoring":187,"score":271,"tags":272,"targetMarket":198,"tier":255},94,[13,193,273,197,196,195,254],"git-native",{"commitSha":257,"license":218,"plugin":275},{"mcpCount":8,"provider":261,"skillCount":214},{"parentExtensionId":238,"repoId":263},[195,197,273,254,13,196,193],{"evaluatedAt":279,"extractAt":267,"updatedAt":280},1778688431684,1778688497232,{"evaluate":282,"extract":284},{"promptVersionExtension":186,"promptVersionScoring":187,"score":190,"tags":283,"targetMarket":198,"tier":199},[193,13,194,195,196,197],{"commitSha":257},{"parentExtensionId":228,"repoId":263},{"_creationTime":287,"_id":263,"identity":288,"providers":289,"workflow":345},1778688377223.2065,{"githubOwner":224,"githubRepo":13,"sourceUrl":14},{"classify":290,"discover":339,"github":342},{"commitSha":257,"extensions":291},[292,305,316],{"basePath":234,"description":241,"displayName":259,"installMethods":293,"rationale":294,"selectedPaths":295,"source":304,"sourceLanguage":18,"type":245},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[296,299,301],{"path":297,"priority":298},".claude-plugin/marketplace.json","mandatory",{"path":300,"priority":298},"README.md",{"path":302,"priority":303},"LICENSE","high","rule",{"basePath":234,"description":231,"displayName":13,"installMethods":306,"license":218,"rationale":307,"selectedPaths":308,"source":304,"sourceLanguage":18,"type":235},{"claudeCode":13},"plugin manifest at .claude-plugin/plugin.json (coalesced with duplicate plugin at standalone/skills/knowledge-graph)",[309,311,312,313],{"path":310,"priority":298},".claude-plugin/plugin.json",{"path":300,"priority":298},{"path":302,"priority":303},{"path":314,"priority":315},"skills/knowledge-graph/SKILL.md","medium",{"basePath":223,"description":10,"displayName":13,"installMethods":317,"rationale":318,"selectedPaths":319,"source":304,"sourceLanguage":18,"type":225},{"claudeCode":12},"SKILL.md frontmatter at skills/knowledge-graph/SKILL.md (coalesced with duplicate skill at standalone/skills/knowledge-graph)",[320,322,325,327,329,331,333,335,337],{"path":321,"priority":298},"SKILL.md",{"path":323,"priority":324},"scripts/analyze.sh","low",{"path":326,"priority":324},"scripts/context.sh",{"path":328,"priority":324},"scripts/guard.sh",{"path":330,"priority":324},"scripts/infer.sh",{"path":332,"priority":324},"scripts/mcp-server.sh",{"path":334,"priority":324},"scripts/prompt-trigger.sh",{"path":336,"priority":324},"scripts/track.sh",{"path":338,"priority":324},"scripts/version.sh",{"sources":340},[341],"manual",{"closedIssues90d":8,"description":343,"forks":8,"license":218,"openIssues90d":214,"pushedAt":215,"readmeSize":211,"stars":216,"topics":344},"Stop AI Coding from forgetting.  A knowledge graph–driven memory layer for LLMs (ChatGPT, Claude, Codex, DeepSeek, Gemini), enabling persistent long-term memory beyond context window limits.  Build smarter AI agents with structured context, better consistency, and scalable multi-step reasoning across complex coding workflows.",[],{"classifiedAt":346,"discoverAt":347,"extractAt":348,"githubAt":348,"updatedAt":346},1778688381018,1778688377223,1778688379278,[195,197,194,13,196,193],{"evaluatedAt":221,"extractAt":267,"updatedAt":351},1778688496967,[],[354,382,410,439,467,496],{"_creationTime":355,"_id":356,"community":357,"display":358,"identity":364,"providers":369,"relations":375,"tags":378,"workflow":379},1778696691708.329,"k170yjw596k3cg892bq130jyd186mhyz",{"reviewCount":8},{"description":359,"installMethods":360,"name":362,"sourceUrl":363},"Validate a Claude Code plugin structure, frontmatter, and MCP tool references",{"claudeCode":361},"ruvnet/ruflo","Validate Plugin","https://github.com/ruvnet/ruflo",{"basePath":365,"githubOwner":366,"githubRepo":367,"locale":18,"slug":368,"type":225},"plugins/ruflo-plugin-creator/skills/validate-plugin","ruvnet","ruflo","validate-plugin",{"evaluate":370,"extract":374},{"promptVersionExtension":186,"promptVersionScoring":187,"score":371,"tags":372,"targetMarket":198,"tier":199},100,[373,235,253,197,196],"validation",{"commitSha":257,"license":218},{"parentExtensionId":376,"repoId":377},"k17f4y1y2y777p7zrxxhbnf03n86mr5j","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[197,253,196,235,373],{"evaluatedAt":380,"extractAt":381,"updatedAt":380},1778701241052,1778696691708,{"_creationTime":383,"_id":384,"community":385,"display":386,"identity":392,"providers":396,"relations":403,"tags":406,"workflow":407},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":387,"installMethods":388,"name":390,"sourceUrl":391},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":389},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":393,"githubOwner":394,"githubRepo":395,"locale":18,"slug":390,"type":225},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":397,"extract":402},{"promptVersionExtension":186,"promptVersionScoring":187,"score":371,"tags":398,"targetMarket":198,"tier":199},[399,400,401,196,197],"command-creation","agent-development","prompt-engineering",{"commitSha":257},{"parentExtensionId":404,"repoId":405},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[400,197,399,196,401],{"evaluatedAt":408,"extractAt":409,"updatedAt":408},1778694773368,1778694480890,{"_creationTime":411,"_id":412,"community":413,"display":414,"identity":420,"providers":425,"relations":432,"tags":435,"workflow":436},1778692488329.0164,"k17d7dgccv6vnj9tcw0cehwnph86nryb",{"reviewCount":8},{"description":415,"installMethods":416,"name":418,"sourceUrl":419},"Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.",{"claudeCode":417},"luiseiman/claude-kit","Rule Effectiveness Analysis","https://github.com/luiseiman/claude-kit",{"basePath":421,"githubOwner":422,"githubRepo":423,"locale":18,"slug":424,"type":225},"skills/rule-effectiveness","luiseiman","claude-kit","rule-effectiveness",{"evaluate":426,"extract":431},{"promptVersionExtension":186,"promptVersionScoring":187,"score":371,"tags":427,"targetMarket":198,"tier":199},[197,428,429,430,194],"configuration","analysis","optimization",{"commitSha":257,"license":218},{"parentExtensionId":433,"repoId":434},"k17650xadq8363kzchr4w0gmf186nq24","kd79wqc8an5wh20cc2znr8tyb586mxwx",[429,197,428,194,430],{"evaluatedAt":437,"extractAt":438,"updatedAt":437},1778693275143,1778692488329,{"_creationTime":440,"_id":441,"community":442,"display":443,"identity":449,"providers":453,"relations":461,"tags":463,"workflow":464},1778697205743.8958,"k17a1wa1fwjqf68n1ghcnjcn6186ngbk",{"reviewCount":8},{"description":444,"installMethods":445,"name":447,"sourceUrl":448},"Instructions for fetching current Dubai time via bash command",{"claudeCode":446},"shanraisshan/claude-code-best-practice","time-fetcher","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":450,"githubOwner":451,"githubRepo":452,"locale":18,"slug":447,"type":225},"agent-teams/.claude/skills/time-fetcher","shanraisshan","claude-code-best-practice",{"evaluate":454,"extract":460},{"promptVersionExtension":186,"promptVersionScoring":187,"score":371,"tags":455,"targetMarket":198,"tier":199},[456,457,195,458,459],"time","dubai","utility","datetime",{"commitSha":257},{"repoId":462},"kd74710g49kxgwbfjxeb7s132d86myxr",[195,459,457,456,458],{"evaluatedAt":465,"extractAt":466,"updatedAt":465},1778697339084,1778697205743,{"_creationTime":468,"_id":469,"community":470,"display":471,"identity":477,"providers":481,"relations":489,"tags":492,"workflow":493},1778694720643.0364,"k178ezcgbcwcccen6aezxvmxbh86mhxg",{"reviewCount":8},{"description":472,"installMethods":473,"name":475,"sourceUrl":476},"Upgrade toprank plugin to the latest version. Updates the marketplace repo, installs the new version to the plugin cache, and updates installed_plugins.json. Use when asked to \"upgrade toprank\", \"update toprank\", or \"get latest version\". Also handles inline upgrade prompts when a skill detects UPGRADE_AVAILABLE at startup.\n",{"claudeCode":474},"nowork-studio/toprank","toprank-upgrade","https://github.com/nowork-studio/toprank",{"basePath":478,"githubOwner":479,"githubRepo":480,"locale":18,"slug":478,"type":225},"toprank-upgrade-skill","nowork-studio","toprank",{"evaluate":482,"extract":488},{"promptVersionExtension":186,"promptVersionScoring":187,"score":371,"tags":483,"targetMarket":198,"tier":199},[484,485,486,195,487],"plugin-management","upgrade","automation","python",{"commitSha":257,"license":218},{"parentExtensionId":490,"repoId":491},"k17dxqwvvhjw9ft30d5zz356z986my6s","kd74wn8s89tp9hrfsmcra492r586nbrv",[486,195,484,487,485],{"evaluatedAt":494,"extractAt":495,"updatedAt":494},1778695134020,1778694720643,{"_creationTime":497,"_id":498,"community":499,"display":500,"identity":506,"providers":510,"relations":517,"tags":520,"workflow":521},1778691884319.0664,"k172gnk14qpj28ndayqyr7y56186n1ys",{"reviewCount":8},{"description":501,"installMethods":502,"name":504,"sourceUrl":505},"Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills.",{"claudeCode":503},"khendzel/skills-janitor","janitor-fix","https://github.com/khendzel/skills-janitor",{"basePath":507,"githubOwner":508,"githubRepo":509,"locale":18,"slug":504,"type":225},"skills/janitor-fix","khendzel","skills-janitor",{"evaluate":511,"extract":516},{"promptVersionExtension":186,"promptVersionScoring":187,"score":371,"tags":512,"targetMarket":198,"tier":199},[513,514,515,486,195,487],"skills","maintenance","cleanup",{"commitSha":257},{"parentExtensionId":518,"repoId":519},"k173y287h96a0x42zvrvymzvgn86nq38","kd722xn3d2v8ze2vwgebvzgpv986mj48",[486,195,515,514,487,513],{"evaluatedAt":522,"extractAt":523,"updatedAt":524},1778691964565,1778691884319,1778692172300]