[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-bilalmk-context-optimization-bn":3,"guides-for-bilalmk-context-optimization":221,"similar-k173essf79wsmej31f7hydqnj5867s8q":222},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":188,"isFallback":193,"parentExtension":194,"providers":195,"relations":200,"repo":202,"workflow":218},1778054086261.0906,"k173essf79wsmej31f7hydqnj5867s8q",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.",{},"Context Optimization Techniques","https://github.com/bilalmk/todo_correct/tree/HEAD/.claude/skills/mjs/context-optimization",[15,16,17,18,19,20],"context","optimization","llm","performance","cost","latency",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":177,"workflow":186},1778054163453.6995,"kn7891ny46w9embm6x9sh8ym2s866jgf","en",{"checks":26,"evaluatedAt":167,"extensionSummary":168,"promptVersionExtension":169,"promptVersionScoring":170,"rationale":171,"score":172,"summary":173,"tags":174,"targetMarket":175,"tier":176},[27,32,35,38,42,45,50,54,57,60,64,69,72,76,79,82,85,88,91,94,97,101,105,109,113,116,119,122,126,129,132,135,138,141,145,148,151,154,157,160,164],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly states the problem of context limits constraining agent performance and the need for optimization in various scenarios.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","The skill offers significant value over simple prompting by providing a structured framework for context optimization using four distinct strategies (compaction, masking, KV-cache, partitioning).",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The skill provides a comprehensive set of documented strategies and Python scripts for implementing context optimization, covering the full lifecycle from analysis to implementation.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The skill focuses on context optimization techniques, a single domain, without branching into unrelated capabilities like testing or deployment.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The displayed description accurately and concisely reflects the skill's purpose and use cases as detailed in the SKILL.md file.",{"category":46,"check":47,"severity":48,"summary":49},"Invocation","Scoped tools","not_applicable","This skill does not expose explicit tools or commands; its functionality is implemented via Python scripts and direct interaction with the LLM context.",{"category":51,"check":52,"severity":48,"summary":53},"Documentation","Configuration & parameter reference","The skill does not expose any user-configurable parameters or environment variables; its logic is self-contained within the provided scripts and SKILL.md.",{"category":39,"check":55,"severity":48,"summary":56},"Tool naming","The skill does not expose user-facing tools or commands, so tool naming conventions do not apply.",{"category":39,"check":58,"severity":48,"summary":59},"Minimal I/O surface","This skill does not expose explicit tools with parameter schemas or response shapes; its I/O is managed internally by the LLM and its scripts.",{"category":61,"check":62,"severity":30,"summary":63},"License","License usability","The extension is licensed under the MIT License, which is a permissive open-source license.",{"category":65,"check":66,"severity":67,"summary":68},"Maintenance","Commit recency","critical","There are no commits on the default branch, indicating the extension is likely unmaintained and poses a risk due to potential staleness or unaddressed issues.",{"category":65,"check":70,"severity":48,"summary":71},"Dependency Management","The skill does not appear to use any third-party dependencies directly within its core logic, relying instead on Python's standard library and LLM capabilities.",{"category":73,"check":74,"severity":48,"summary":75},"Security","Secret Management","The skill does not handle or expose any secrets.",{"category":73,"check":77,"severity":30,"summary":78},"Injection","The skill's logic appears to treat external data as content rather than instructions, and it does not fetch remote content.",{"category":73,"check":80,"severity":30,"summary":81},"Transitive Supply-Chain Grenades","The skill does not fetch remote content or execute arbitrary code from external sources; all logic is contained within the bundle.",{"category":73,"check":83,"severity":30,"summary":84},"Sandbox Isolation","The skill operates within its defined scope and does not attempt to modify files or paths outside of its project folder.",{"category":73,"check":86,"severity":30,"summary":87},"Sandbox escape primitives","No detached-process spawns or deny-retry loops were detected in the provided scripts.",{"category":73,"check":89,"severity":30,"summary":90},"Data Exfiltration","The skill does not make any undocumented outbound calls or attempt to submit confidential data to third parties.",{"category":73,"check":92,"severity":30,"summary":93},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks, invisible characters, or obfuscated instructions.",{"category":73,"check":95,"severity":30,"summary":96},"Opaque code execution","The bundled scripts are in plain, readable Python format and do not use obfuscation techniques like base64 decoding or runtime fetching.",{"category":98,"check":99,"severity":30,"summary":100},"Portability","Structural Assumption","The Python scripts include clear comments about token estimation and summarization, indicating awareness of potential environmental differences and recommending production-ready alternatives.",{"category":102,"check":103,"severity":48,"summary":104},"Trust","Issues Attention","No issues data is available for evaluation.",{"category":106,"check":107,"severity":30,"summary":108},"Versioning","Release Management","A meaningful version (1.0.0) is declared in the SKILL.md frontmatter.",{"category":110,"check":111,"severity":48,"summary":112},"Code Execution","Validation","The skill's logic is primarily handled by the LLM and its internal Python scripts, which do not expose parameters requiring external validation via schema libraries.",{"category":73,"check":114,"severity":48,"summary":115},"Unguarded Destructive Operations","The skill is analytical and read-only in nature, with no destructive operations.",{"category":110,"check":117,"severity":30,"summary":118},"Error Handling","The Python scripts include comments about using model-specific tokenizers and LLM-based summarization, suggesting awareness of potential issues and error states.",{"category":110,"check":120,"severity":48,"summary":121},"Logging","The skill does not perform destructive actions or outbound calls that would require local audit logging.",{"category":123,"check":124,"severity":48,"summary":125},"Compliance","GDPR","The skill does not operate on personal data.",{"category":123,"check":127,"severity":30,"summary":128},"Target market","The skill's techniques are universal and not tied to any specific geography or legal jurisdiction; targetMarket defaults to 'global'.",{"category":98,"check":130,"severity":30,"summary":131},"Runtime stability","The Python scripts explicitly mention using model-specific tokenizers and LLM-based summarization, acknowledging potential runtime differences and recommending production-ready alternatives.",{"category":46,"check":133,"severity":30,"summary":134},"Precise Purpose","The SKILL.md frontmatter and body clearly define the skill's purpose (context optimization) and when to use it, including explicit boundaries.",{"category":46,"check":136,"severity":30,"summary":137},"Concise Frontmatter","The frontmatter is concise, clearly stating the skill's core capability and use cases without excessive keywords.",{"category":51,"check":139,"severity":30,"summary":140},"Concise Body","The SKILL.md body is well-structured and under 500 lines, with detailed technical references delegated to separate files.",{"category":142,"check":143,"severity":30,"summary":144},"Context","Progressive Disclosure","Detailed technical information is appropriately split into a separate `references/optimization_techniques.md` file, linked from the main SKILL.md.",{"category":142,"check":146,"severity":48,"summary":147},"Forked exploration","This skill is not an exploration-style skill; it is a utility that applies optimization techniques directly.",{"category":28,"check":149,"severity":30,"summary":150},"Usage examples","The SKILL.md includes three practical, ready-to-use Python examples demonstrating compaction, observation masking, and cache-friendly ordering.",{"category":28,"check":152,"severity":30,"summary":153},"Edge cases","The documentation mentions performance considerations and common pitfalls like over-aggressive compaction and masking critical observations, with guidance on balance and testing.",{"category":110,"check":155,"severity":48,"summary":156},"Tool Fallback","This skill does not rely on external tools like MCP servers and has no fallback requirements.",{"category":98,"check":158,"severity":30,"summary":159},"Stack assumptions","The Python scripts include comments that acknowledge potential runtime differences and recommend specific libraries (tiktoken, anthropic tokenizer) for production, indicating clear awareness of stack assumptions.",{"category":161,"check":162,"severity":30,"summary":163},"Safety","Halt on unexpected state","The Python scripts include comments that discuss production considerations and the need for proper tokenizers, implying a robust error handling approach where unexpected states would be managed.",{"category":98,"check":165,"severity":30,"summary":166},"Cross-skill coupling","The skill is self-contained and focuses solely on context optimization techniques; it does not implicitly rely on other skills.",1778054125835,"This skill implements strategies like compaction, observation masking, KV-cache optimization, and context partitioning to enhance effective context capacity. It provides Python scripts for these techniques and detailed documentation on their implementation and performance considerations.","2.0.0","3.4.0","The critical finding for 'Commit recency' due to 'n/a' commits indicates a significant lack of maintenance, which is a major risk for users. Although other aspects of the skill are well-documented and functional, the unmaintained nature flags it as potentially unreliable.",49,"This skill provides a comprehensive framework for optimizing LLM context capacity using various techniques, but its unmaintained status is a critical concern.",[15,16,17,18,19,20],"global","flagged",{"codeQuality":178,"collectedAt":179,"documentation":180,"maintenance":182,"security":183,"testCoverage":185},{},1778054115222,{"descriptionLength":181,"readmeSize":8},206,{},{"hasNpmPackage":184,"smitheryVerified":184},false,{"hasCi":184,"hasTests":184},{"updatedAt":187},1778054163453,{"githubOwner":189,"githubRepo":190,"locale":24,"slug":191,"type":192},"bilalmk","todo_correct","context-optimization","skill",true,null,{"extract":196,"llm":199},{"commitSha":197,"license":198},"8b43aa04bd5c53e3cda46469b953684519a84ea7","MIT-0",{"promptVersionExtension":169,"promptVersionScoring":170,"score":172,"targetMarket":175,"tier":176},{"repoId":201},"kd75ecf652eb91ha327s8bqbex865z6v",{"_creationTime":203,"_id":201,"identity":204,"providers":206,"workflow":215},1777995558409.9006,{"githubOwner":189,"githubRepo":190,"sourceUrl":205},"https://github.com/bilalmk/todo_correct",{"discover":207,"github":210},{"sources":208},[209],"skills-sh",{"closedIssues90d":8,"forks":8,"openIssues90d":211,"pushedAt":212,"readmeSize":213,"stars":211,"topics":214},1,1769509251000,14662,[],{"discoverAt":216,"extractAt":217,"githubAt":217,"updatedAt":217},1777995558409,1778054088050,{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},1778054086910,1778054086261,[],[223,245,273,301,320,348],{"_creationTime":224,"_id":225,"community":226,"display":227,"identity":235,"providers":237,"relations":243,"workflow":244},1778054086261.0896,"k173qc4w9k717e5jcb4da4zrcx866a1a",{"reviewCount":8},{"description":228,"name":229,"sourceUrl":230,"tags":231},"Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.","Context Degradation Patterns","https://github.com/bilalmk/todo_correct/tree/HEAD/.claude/skills/mjs/context-degradation",[232,15,18,233,17,234],"agent","debugging","analysis",{"githubOwner":189,"githubRepo":190,"locale":24,"slug":236,"type":192},"context-degradation",{"extract":238,"llm":240},{"commitSha":197,"license":239},"MIT",{"promptVersionExtension":169,"promptVersionScoring":170,"score":241,"targetMarket":175,"tier":242},95,"verified",{"repoId":201},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},{"_creationTime":246,"_id":247,"community":248,"display":249,"identity":259,"providers":263,"relations":267,"workflow":269},1778054123074.2515,"k17an427chh58vrfr9bqc9zfa5867a4z",{"reviewCount":8},{"description":250,"installMethods":251,"name":252,"sourceUrl":253,"tags":254},"Deep Core Web Vitals and page speed audit. Use when the user asks about page speed, Core Web Vitals, LCP, CLS, INP, FCP, TTFB, Lighthouse scores, why a page is slow, performance optimization, or resource size analysis. For broader technical SEO issues, see diagnose-seo.",{},"Audit Speed","https://github.com/calm-north/seojuice-skills/tree/HEAD/skills/audit-speed",[255,18,256,257,16,258],"seo","web-vitals","lighthouse","audit",{"githubOwner":260,"githubRepo":261,"locale":24,"slug":262,"type":192},"calm-north","seojuice-skills","audit-speed",{"extract":264,"llm":266},{"commitSha":265,"license":239},"c1f633bea512365ba04477076369e418ecc82ffd",{"promptVersionExtension":169,"promptVersionScoring":170,"score":241,"targetMarket":175,"tier":242},{"repoId":268},"kd77p09fwtcsr2sfmxw6921ek1864v0a",{"anyEnrichmentAt":270,"extractAt":271,"githubAt":270,"llmAt":272,"updatedAt":272},1778054123513,1778054123074,1778054162250,{"_creationTime":274,"_id":275,"community":276,"display":277,"identity":287,"providers":291,"relations":295,"workflow":297},1778053269518.5881,"k177wxssjdrgvnn2kdjw0zgb7d867n56",{"reviewCount":8},{"description":278,"installMethods":279,"name":280,"sourceUrl":281,"tags":282},"Async/await and Promise optimization guidelines. Use when writing, reviewing, or refactoring asynchronous code to eliminate waterfalls and maximize parallelism. Triggers on tasks involving data fetching, loaders, actions, or Promise handling.",{},"Async Best Practices","https://github.com/sergiodxa/agent-skills/tree/HEAD/skills/frontend-async-best-practices",[283,284,18,16,285,286],"javascript","async","promises","typescript",{"githubOwner":288,"githubRepo":289,"locale":24,"slug":290,"type":192},"sergiodxa","agent-skills","frontend-async-best-practices",{"extract":292,"llm":294},{"commitSha":293,"license":239},"40e21b46189d5c7de6610b68a25280af863f8775",{"promptVersionExtension":169,"promptVersionScoring":170,"score":241,"targetMarket":175,"tier":242},{"repoId":296},"kd73wtzzjgc8jttgs0x15sp8s9865fzg",{"anyEnrichmentAt":298,"extractAt":299,"githubAt":298,"llmAt":300,"updatedAt":300},1778053270043,1778053269518,1778053306113,{"_creationTime":302,"_id":303,"community":304,"display":305,"identity":313,"providers":315,"relations":318,"workflow":319},1778053269518.589,"k1771mns3f2gw8hennvnkezwth867pj6",{"reviewCount":8},{"description":306,"installMethods":307,"name":308,"sourceUrl":309,"tags":310},"JavaScript performance optimization guidelines. Use when writing, reviewing, or refactoring JavaScript/TypeScript code to ensure optimal performance patterns. Triggers on tasks involving loops, data structures, DOM manipulation, or general JS optimization.",{},"JavaScript Best Practices","https://github.com/sergiodxa/agent-skills/tree/HEAD/skills/frontend-js-best-practices",[283,286,18,16,311,312],"best-practices","code-quality",{"githubOwner":288,"githubRepo":289,"locale":24,"slug":314,"type":192},"frontend-js-best-practices",{"extract":316,"llm":317},{"commitSha":293,"license":239},{"promptVersionExtension":169,"promptVersionScoring":170,"score":241,"targetMarket":175,"tier":242},{"repoId":296},{"anyEnrichmentAt":298,"extractAt":299,"githubAt":298,"llmAt":300,"updatedAt":300},{"_creationTime":321,"_id":322,"community":323,"display":324,"identity":333,"providers":337,"relations":342,"workflow":344},1778053730743.9404,"k173rfwq4dc7fwm8h0rev5cza1866g27",{"reviewCount":8},{"description":325,"installMethods":326,"name":327,"sourceUrl":328,"tags":329},"Help users define AI product strategy. Use when someone is building an AI product, deciding where to apply AI in their product, planning an AI roadmap, evaluating build vs buy for AI capabilities, or figuring out how to integrate AI into existing products.",{},"AI Product Strategy","https://github.com/refoundai/lenny-skills/tree/HEAD/skills/ai-product-strategy",[330,331,332,17],"ai","product-strategy","planning",{"githubOwner":334,"githubRepo":335,"locale":24,"slug":336,"type":192},"refoundai","lenny-skills","ai-product-strategy",{"extract":338,"llm":340},{"commitSha":339,"license":239},"280a57aa42fed3b6f35f51f0d9e71013b4c8ae74",{"promptVersionExtension":169,"promptVersionScoring":170,"score":341,"targetMarket":175,"tier":242},98,{"repoId":343},"kd71b12s61d3nrk4f6dxqd3z35865mkg",{"anyEnrichmentAt":345,"extractAt":346,"githubAt":345,"llmAt":347,"updatedAt":347},1778053732694,1778053730744,1778053975687,{"_creationTime":349,"_id":350,"community":351,"display":352,"identity":361,"providers":365,"relations":369,"workflow":371},1778053100136.2388,"k17ba7hx1c2htdr84qc7vc86cd867abn",{"reviewCount":8},{"description":353,"installMethods":354,"name":355,"sourceUrl":356,"tags":357},"Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like \"review this paper\", \"analyze this research\", \"summarize this study\", or \"write a peer review\".",{},"Academic Paper Review Skill","https://github.com/bytedance/deer-flow/tree/HEAD/skills/public/academic-paper-review",[358,359,360,234,17],"research","academic","paper-review",{"githubOwner":362,"githubRepo":363,"locale":24,"slug":364,"type":192},"bytedance","deer-flow","academic-paper-review",{"extract":366,"llm":368},{"commitSha":367,"license":239},"1336872b15c25d45ebcb7c1cf72369c2bdd53187",{"promptVersionExtension":169,"promptVersionScoring":170,"score":341,"targetMarket":175,"tier":242},{"repoId":370},"kd789sm7egx1h0t1jag6zzhcq98656wv",{"anyEnrichmentAt":372,"extractAt":373,"githubAt":372,"llmAt":374,"updatedAt":374},1778053101076,1778053100136,1778053169012]