[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-Ramsbaby-openclaw-memorybox-en":3,"guides-for-Ramsbaby-openclaw-memorybox":345,"similar-k170ddv8dg3cc0max0edc6w2y986nwjj-en":346},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":226,"parentExtension":247,"providers":248,"relations":253,"repo":255,"tags":341,"workflow":342},1778696140284.4524,"k170ddv8dg3cc0max0edc6w2y986nwjj",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Memory health CLI that diagnoses bloated MEMORY.md files, splits oversized sections into domain files, archives stale daily logs, and runs continuous health monitoring. Use when MEMORY.md exceeds 10KB, context windows overflow from memory bloat, or agent sessions slow down from loading large memory files. Pure bash, zero dependencies.",{"claudeCode":12},"Ramsbaby/openclaw-memorybox","openclaw-memorybox","https://github.com/Ramsbaby/openclaw-memorybox",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":241},1778696174921.5002,"kn72c6sapvhk3rqm9wmp95wwk986mp88","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":217,"tier":218,"useCases":219},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,132,135,138,142,146,149,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of AI agent memory bloat leading to performance issues and crashes, and explicitly mentions when to use the tool.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The tool offers significant value beyond default behavior by automating memory maintenance, a critical but often neglected aspect of long-running AI agents, with a clear impact on performance and stability.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The CLI tool is pure bash with zero dependencies, making it easily deployable. It addresses the complete lifecycle of memory management for AI agents, from diagnosis to cleanup and monitoring.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on memory file maintenance for AI agents, aligning with its name and description without extending into unrelated domains like testing or deployment.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the tool's functionality, highlighting its purpose, use cases, and zero-dependency nature.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The CLI commands are specific verb-noun actions like 'doctor', 'split', 'archive', making them easy for an agent to select and use.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","Command-line options are documented in the README and CLI help, and environment variables for the daemon mode are also clearly specified.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","All CLI commands are descriptive and follow a clear verb-noun pattern within the domain of memory management.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The CLI commands operate on specific workspace paths and accept well-defined arguments, with outputs focused on diagnostic information and actions taken.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The project is licensed under MIT, a permissive open-source license, with the license text provided in a dedicated LICENSE file.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on April 27, 2026, which is well within the last 3 months.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The tool is pure bash with zero external dependencies, so no third-party dependency management is required.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The tool operates on local files and does not handle or expose any secrets.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The tool processes local markdown files and bash scripts; it does not load untrusted third-party data or fetch remote content as instructions.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The tool is pure bash with no runtime external file fetching or remote code execution. All necessary scripts are bundled.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The tool operates within the specified workspace and only manipulates files within that scope, adhering to standard file system operations.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The bash scripts do not contain any detached process spawns or retry loops around denied operations.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The tool only operates on local files and has no outbound network calls, thus preventing data exfiltration.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled content, including README and scripts, appears free of hidden steering tricks, control characters, or unusual Unicode.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The bash scripts are plain, readable, and not obfuscated or dynamically fetched.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The tool assumes a standard directory structure for AI agent memory files, which is documented and can be initialized via `memorybox init`.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","In the last 90 days, 0 issues were opened and 5 were closed, indicating active maintenance and timely issue resolution.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","A meaningful version (2.2.0 in SKILL.md frontmatter, and also in README/CHANGELOG) is declared, and installation instructions reference a specific version/tag.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Input arguments like workspace paths and days for archiving are handled and validated appropriately within the bash scripts.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","Destructive operations like moving files are either interactive or operate on clearly defined, user-approved paths, with backups made.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The bash scripts use `set -euo pipefail` for robust error handling and exit non-zero on failure, with informative messages provided.",{"category":110,"check":114,"severity":24,"summary":115},"Logging","The daemon script logs its activity to a local file, and CLI commands provide clear output on actions taken.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The tool operates on local files and does not transmit any personal data to third parties.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The tool is a general-purpose file maintenance utility for AI agent memory and has no regional or jurisdictional limitations.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The tool is pure bash and designed to be cross-platform on macOS and Linux, with no specific shell or OS dependencies beyond bash itself.",{"category":44,"check":127,"severity":24,"summary":128},"README","The README is comprehensive, well-structured, and clearly states the extension's purpose, usage, and benefits.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The CLI exposes 10 commands, which is within the ideal range of 3-10 tools.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","The CLI commands have distinct names and functions, avoiding redundancy or near-synonyms.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features in the README and SKILL.md, such as the CLI commands and daemon mode, have corresponding implementations.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","Clear installation instructions are provided in both README and SKILL.md, including a one-liner curl command and examples.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","Error messages from the scripts are clear, indicate the failure point, and suggest remediation steps or relevant commands.",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","The tool is pure bash with no external dependencies, thus satisfying this check.",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","The extension is primarily a file management tool and does not involve state-changing operations that would necessitate a dry-run mode.",{"category":154,"check":155,"severity":151,"summary":156},"Protocol","Idempotent retry & timeouts","The tool operates on local files and does not involve remote calls or state-changing operations that require idempotency or timeouts.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The tool does not emit any telemetry. The daemon script logs to a local file, which is opt-in via environment variables for logging directory.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly states the tool's purpose (memory health CLI) and when to use it (e.g., MEMORY.md exceeds 10KB, context windows overflow).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise and effectively summarizes the core capability and triggers.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md and README are well-structured with content progressively disclosed, keeping main sections concise and deferring details to references or separate files.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The README and SKILL.md outline procedures and link to external assets or sections, rather than embedding large amounts of raw material inline.",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","The skill is a utility and does not involve deep exploration or code review that would benefit from `context: fork`.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The README and SKILL.md provide multiple clear, ready-to-use examples for installation, diagnosis, and fixing memory issues.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The tool handles edge cases like missing directories or MEMORY.md files, and provides recovery steps or clear suggestions.",{"category":110,"check":183,"severity":151,"summary":184},"Tool Fallback","The skill uses only bundled bash scripts and the Claude Code environment, not external MCP servers, so this check is not applicable.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The bash scripts use `set -euo pipefail` and explicit checks to halt execution on unexpected states, reporting errors.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills; its functionality is clearly defined and standalone.",1778696174030,"OpenClaw MemoryBox is a command-line utility written in pure bash that diagnoses, splits, archives, and monitors AI agent memory files (like MEMORY.md) to prevent bloat and performance degradation. It organizes memory into a 3-tier structure and includes a background daemon for continuous health monitoring.",[195,196,197,198,199],"Diagnoses memory health and size analysis","Splits oversized memory sections into domain files","Archives stale daily logs automatically","Monitors memory health via a background daemon","Pure bash with zero external dependencies",[201,202,203],"Replacing AI memory engines (e.g., Mem0, Supermemory)","Modifying agent configuration or internal workings","Handling agent core logic or decision-making","3.0.0","4.4.0","To maintain the health and performance of AI agent memory files, preventing issues like context overflow and agent crashes by keeping memory lean and organized.","The extension is a high-quality, pure bash utility with excellent documentation and clear use cases. The low score reflects the absence of a dry-run feature, which is not applicable to its core functionality.",99,"A robust, pure bash CLI tool for AI agent memory health, offering comprehensive diagnostics and automated cleanup.",[211,212,213,214,215,216],"memory","maintenance","cli","devtools","zero-dependency","bash","global","verified",[220,221,222,223],"When MEMORY.md exceeds 10KB","When context windows overflow due to memory bloat","When agent sessions slow down from loading large memory files","To automate memory cleanup for 24/7 AI agents",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":238,"testCoverage":240},{"hasLockfile":226},false,1778696160040,{"descriptionLength":229,"readmeSize":230},336,20083,{"closedIssues90d":232,"forks":233,"hasChangelog":234,"manifestVersion":235,"openIssues90d":8,"pushedAt":236,"stars":237},5,4,true,"2.2.0",1777291295000,9,{"hasNpmPackage":226,"license":239,"smitheryVerified":226},"MIT",{"hasCi":234,"hasTests":226},{"updatedAt":242},1778696174921,{"basePath":244,"githubOwner":245,"githubRepo":13,"locale":18,"slug":13,"type":246},"","Ramsbaby","skill",null,{"evaluate":249,"extract":251},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":250,"targetMarket":217,"tier":218},[211,212,213,214,215,216],{"commitSha":252},"HEAD",{"repoId":254},"kd7arj8x2xnfzd1vs9ave44m1d86nacw",{"_creationTime":256,"_id":254,"identity":257,"providers":258,"workflow":337},1778696135401.8289,{"githubOwner":245,"githubRepo":13,"sourceUrl":14},{"classify":259,"discover":323,"github":326},{"commitSha":252,"extensions":260},[261,316],{"basePath":244,"description":10,"displayName":13,"installMethods":262,"rationale":263,"selectedPaths":264,"source":315,"sourceLanguage":18,"type":246},{"claudeCode":12},"SKILL.md frontmatter at SKILL.md",[265,268,271,273,276,278,280,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313],{"path":266,"priority":267},"SKILL.md","mandatory",{"path":269,"priority":270},"README.md","high",{"path":272,"priority":270},"LICENSE",{"path":274,"priority":275},"CHANGELOG.md","medium",{"path":277,"priority":275},"README.ko.md",{"path":279,"priority":275},"SECURITY.md",{"path":281,"priority":282},"assets/demo.cast","low",{"path":284,"priority":282},"assets/demo.gif",{"path":286,"priority":282},"assets/traffic-chart.png",{"path":288,"priority":282},"docs/assets/hero.svg",{"path":290,"priority":282},"docs/assets/lifecycle.svg",{"path":292,"priority":282},"docs/blog-writing-guide.md",{"path":294,"priority":282},"scripts/archive-old-logs.sh",{"path":296,"priority":282},"scripts/check-memory-size.sh",{"path":298,"priority":282},"scripts/generate-traffic-chart.py",{"path":300,"priority":282},"scripts/memorybox-watch.sh",{"path":302,"priority":282},"scripts/migrate.sh",{"path":304,"priority":282},"scripts/session-end-hook.sh",{"path":306,"priority":282},"templates/MEMORY.md.template",{"path":308,"priority":282},"templates/memory/README.md",{"path":310,"priority":282},"templates/memory/domains/decisions.md.template",{"path":312,"priority":282},"templates/memory/domains/milestones.md.template",{"path":314,"priority":282},"templates/memory/domains/persona.md.template","rule",{"basePath":246,"description":317,"displayName":318,"installMethods":319,"rationale":320,"selectedPaths":321,"source":315,"sourceLanguage":18,"type":246},"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.","memorybox",{"claudeCode":12},"SKILL.md frontmatter at skill/SKILL.md",[322],{"path":266,"priority":267},{"sources":324},[325],"manual",{"closedIssues90d":232,"description":327,"forks":233,"homepage":328,"license":239,"openIssues90d":8,"pushedAt":236,"readmeSize":230,"stars":237,"topics":329},"🧠 Install once, forget about memory management. Zero-dependency maintenance CLI for OpenClaw agents. Works alongside Mem0, Supermemory, QMD.","https://ramsbaby.netlify.app",[211,330,331,332,333,334,335,336],"claude-code","ai-agents","anthropic","context-management","knowledge-base","persistent-memory","slash-commands",{"classifiedAt":338,"discoverAt":339,"extractAt":340,"githubAt":340,"updatedAt":338},1778696139852,1778696135401,1778696137954,[216,213,214,212,211,215],{"evaluatedAt":242,"extractAt":343,"updatedAt":344},1778696140284,1778696222506,[],[347,378,406,433,464,492],{"_creationTime":348,"_id":349,"community":350,"display":351,"identity":357,"providers":361,"relations":370,"tags":373,"workflow":374},1778691884319.0664,"k172gnk14qpj28ndayqyr7y56186n1ys",{"reviewCount":8},{"description":352,"installMethods":353,"name":355,"sourceUrl":356},"Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills.",{"claudeCode":354},"khendzel/skills-janitor","janitor-fix","https://github.com/khendzel/skills-janitor",{"basePath":358,"githubOwner":359,"githubRepo":360,"locale":18,"slug":355,"type":246},"skills/janitor-fix","khendzel","skills-janitor",{"evaluate":362,"extract":369},{"promptVersionExtension":204,"promptVersionScoring":205,"score":363,"tags":364,"targetMarket":217,"tier":218},100,[365,212,366,367,216,368],"skills","cleanup","automation","python",{"commitSha":252},{"parentExtensionId":371,"repoId":372},"k173y287h96a0x42zvrvymzvgn86nq38","kd722xn3d2v8ze2vwgebvzgpv986mj48",[367,216,366,212,368,365],{"evaluatedAt":375,"extractAt":376,"updatedAt":377},1778691964565,1778691884319,1778692172300,{"_creationTime":379,"_id":380,"community":381,"display":382,"identity":388,"providers":392,"relations":400,"tags":402,"workflow":403},1778697205743.8958,"k17a1wa1fwjqf68n1ghcnjcn6186ngbk",{"reviewCount":8},{"description":383,"installMethods":384,"name":386,"sourceUrl":387},"Instructions for fetching current Dubai time via bash command",{"claudeCode":385},"shanraisshan/claude-code-best-practice","time-fetcher","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":389,"githubOwner":390,"githubRepo":391,"locale":18,"slug":386,"type":246},"agent-teams/.claude/skills/time-fetcher","shanraisshan","claude-code-best-practice",{"evaluate":393,"extract":399},{"promptVersionExtension":204,"promptVersionScoring":205,"score":363,"tags":394,"targetMarket":217,"tier":218},[395,396,216,397,398],"time","dubai","utility","datetime",{"commitSha":252},{"repoId":401},"kd74710g49kxgwbfjxeb7s132d86myxr",[216,398,396,395,397],{"evaluatedAt":404,"extractAt":405,"updatedAt":404},1778697339084,1778697205743,{"_creationTime":407,"_id":408,"community":409,"display":410,"identity":416,"providers":420,"relations":426,"tags":429,"workflow":430},1778694720643.0364,"k178ezcgbcwcccen6aezxvmxbh86mhxg",{"reviewCount":8},{"description":411,"installMethods":412,"name":414,"sourceUrl":415},"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":413},"nowork-studio/toprank","toprank-upgrade","https://github.com/nowork-studio/toprank",{"basePath":417,"githubOwner":418,"githubRepo":419,"locale":18,"slug":417,"type":246},"toprank-upgrade-skill","nowork-studio","toprank",{"evaluate":421,"extract":425},{"promptVersionExtension":204,"promptVersionScoring":205,"score":363,"tags":422,"targetMarket":217,"tier":218},[423,424,367,216,368],"plugin-management","upgrade",{"commitSha":252,"license":239},{"parentExtensionId":427,"repoId":428},"k17dxqwvvhjw9ft30d5zz356z986my6s","kd74wn8s89tp9hrfsmcra492r586nbrv",[367,216,423,368,424],{"evaluatedAt":431,"extractAt":432,"updatedAt":431},1778695134020,1778694720643,{"_creationTime":434,"_id":435,"community":436,"display":437,"identity":443,"providers":448,"relations":457,"tags":460,"workflow":461},1778696691708.3274,"k170az7r02e9e2v47mpy80kx6n86nff3",{"reviewCount":8},{"description":438,"installMethods":439,"name":441,"sourceUrl":442},"Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy",{"claudeCode":440},"ruvnet/ruflo","Trader Regime","https://github.com/ruvnet/ruflo",{"basePath":444,"githubOwner":445,"githubRepo":446,"locale":18,"slug":447,"type":246},"plugins/ruflo-neural-trader/skills/trader-regime","ruvnet","ruflo","trader-regime",{"evaluate":449,"extract":456},{"promptVersionExtension":204,"promptVersionScoring":205,"score":363,"tags":450,"targetMarket":217,"tier":218},[451,452,453,454,455,213],"finance","trading","market-analysis","ai","typescript",{"commitSha":252,"license":239},{"parentExtensionId":458,"repoId":459},"k17drge8h1fgzchr0p4jaeg33n86mwmy","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[454,213,451,453,452,455],{"evaluatedAt":462,"extractAt":463,"updatedAt":462},1778701108877,1778696691708,{"_creationTime":465,"_id":466,"community":467,"display":468,"identity":474,"providers":478,"relations":485,"tags":488,"workflow":489},1778699234184.6174,"k174zww66m804nhr89ttra7r6d86nwyg",{"reviewCount":8},{"description":469,"installMethods":470,"name":472,"sourceUrl":473},"Use first for install/update routing — sends setup, doctor, or MCP requests to the correct OMC setup flow",{"claudeCode":471},"Yeachan-Heo/oh-my-claudecode","setup","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":475,"githubOwner":476,"githubRepo":477,"locale":18,"slug":472,"type":246},"skills/setup","Yeachan-Heo","oh-my-claudecode",{"evaluate":479,"extract":484},{"promptVersionExtension":204,"promptVersionScoring":205,"score":363,"tags":480,"targetMarket":217,"tier":218},[472,481,482,213,483],"routing","configuration","mcp",{"commitSha":252},{"parentExtensionId":486,"repoId":487},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[213,482,483,481,472],{"evaluatedAt":490,"extractAt":491,"updatedAt":490},1778699724286,1778699234184,{"_creationTime":493,"_id":494,"community":495,"display":496,"identity":500,"providers":503,"relations":512,"tags":513,"workflow":514},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":497,"installMethods":498,"name":499,"sourceUrl":473},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":471},"Project Session Manager",{"basePath":501,"githubOwner":476,"githubRepo":477,"locale":18,"slug":502,"type":246},"skills/project-session-manager","project-session-manager",{"evaluate":504,"extract":511},{"promptVersionExtension":204,"promptVersionScoring":205,"score":363,"tags":505,"targetMarket":217,"tier":218},[506,507,508,509,367,213,510],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":252,"license":239},{"parentExtensionId":486,"repoId":487},[367,213,510,507,506,509,508],{"evaluatedAt":515,"extractAt":491,"updatedAt":515},1778699613343]