[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-muratcankoylan-evaluation-de":3,"guides-for-muratcankoylan-evaluation":638,"similar-k171cfyvthhb63hdrhaqtpybes86m9pq-de":639},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":248,"isFallback":245,"parentExtension":253,"providers":315,"relations":319,"repo":320,"tags":636,"workflow":637},1778694269038.6692,"k171cfyvthhb63hdrhaqtpybes86m9pq",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"This skill should be used when the user asks to \"evaluate agent performance\", \"build test framework\", \"measure agent quality\", \"create evaluation rubrics\", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.",{"claudeCode":12},"muratcankoylan/Agent-Skills-for-Context-Engineering","evaluation","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":229,"workflow":246},1778694482778.6643,"kn7btqgg8envwc182efkthcyw186n1h1","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":210,"promptVersionExtension":211,"promptVersionScoring":212,"purpose":213,"rationale":214,"score":215,"summary":216,"tags":217,"targetMarket":222,"tier":223,"useCases":224},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,114,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of evaluating agent performance and quality, naming specific user requests and concepts like LLM-as-judge and quality gates.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill provides a structured framework for evaluating agent systems, going beyond basic prompt engineering by offering multi-dimensional rubrics, LLM-as-judge methodologies, and test set design principles.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a comprehensive framework for evaluation, including design, implementation, and continuous monitoring, making it suitable for real-world workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on the evaluation of agent performance and quality, without extending into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The 'Displayed Description' accurately reflects the skill's purpose as described in the SKILL.md file.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose specific tools; its functionality is based on instructions and logic within its SKILL.md and associated scripts.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not expose configurable parameters or options directly to the user; its behavior is driven by the instructions within the SKILL.md file.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This skill does not expose user-facing tools with names.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This skill does not expose tools with parameter schemas or response shapes.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension uses the MIT license, which is permissive and widely usable.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The last commit was on April 14, 2026, which is within the last 3 months.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The extension does not appear to have third-party dependencies that require explicit management.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill is focused on evaluation frameworks and does not handle secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's focus on structured evaluation and its lack of external data loading suggests no injection vulnerabilities.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch external content at runtime; all logic is bundled within the repository.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates as an evaluation framework and does not perform file system modifications or operations outside its defined scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached-process spawns or deny-retry loops were found in the provided scripts.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill is analytical and does not perform outbound calls to submit confidential data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks and uses clean, printable ASCII and expected Unicode.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The bundled scripts are plain and readable, with no obfuscation like base64 payloads or minified code without source maps.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill makes no assumptions about user-specific project organization outside its own bundle and does not modify files.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 6 open issues and 2 closed in the last 90 days, the closure rate is reasonable and the number of open issues is low.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The SKILL.md frontmatter declares a meaningful semver version (1.1.0).",{"category":104,"check":105,"severity":42,"summary":106},"Execution","Validation","The skill's primary operation is logic-based within SKILL.md and Python scripts; it does not expose tools with parameters that require schema validation.",{"category":66,"check":108,"severity":42,"summary":109},"Unguarded Destructive Operations","The skill is analytical and does not perform destructive operations.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The provided Python scripts demonstrate robust error handling with structured error reporting and clear messages for potential issues.",{"category":111,"check":115,"severity":42,"summary":116},"Logging","The skill is primarily an instructional framework and does not perform destructive actions or outbound calls requiring local audit logging.",{"category":118,"check":119,"severity":42,"summary":120},"Compliance","GDPR","The skill does not operate on personal data; it provides a framework for evaluation.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill is language-agnostic and provides general evaluation principles, making it globally applicable.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The provided Python scripts use standard libraries and should be portable across POSIX-compliant systems. The SKILL.md is language-agnostic.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README file exists and provides a comprehensive overview of the Agent Skills for Context Engineering, including the purpose and structure of individual skills.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","This is a skill, not a CLI or MCP server, and does not expose tools in that manner.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","This skill does not expose multiple tools.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All features advertised in the README and SKILL.md have corresponding implementations or documented concepts within the repository.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for Claude Code and other platforms, along with guidance for individual skill usage.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The provided Python scripts include actionable error messages with clear root causes and remediation steps, as demonstrated in the `ProductionMonitor` class.",{"category":104,"check":148,"severity":24,"summary":149},"Pinned dependencies","The Python scripts correctly use shebangs and assume standard interpreter versions. No third-party dependencies are explicitly required for the core logic.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill is purely analytical and does not perform state-changing operations or send data outward.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill does not involve remote calls or state-changing operations that would require idempotency or timeouts.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The provided code does not emit telemetry; if it did, the structure suggests an opt-in mechanism would be implemented based on its general design principles.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The SKILL.md and displayed description clearly define the skill's purpose: evaluating agent performance, building test frameworks, and measuring quality, with specific triggers and boundaries.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise and effectively summarizes the core capability and triggers for the evaluation skill.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and adheres to the recommended length, delegating deeper material to the references file.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Deeper implementation details for metrics and runners are provided in a separate `references/metrics.md` file, demonstrating progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill is not designed for deep exploration or code review; it provides a framework and does not require a forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md includes end-to-end Python code examples for evaluation runners and production monitoring, demonstrating how to use the skill's components.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The `references/metrics.md` file implicitly handles edge cases like insufficient data for monitoring and the `evaluator.py` script has fallbacks for missing ground truth.",{"category":111,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external tools or MCP servers; it is self-contained.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The `EvaluationRunner` and `ProductionMonitor` classes handle unexpected states gracefully, such as insufficient data for metrics or errors during test execution, reporting them clearly.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and provides evaluation capabilities that can be integrated with other skills without implicit reliance on them being loaded simultaneously.",1778694482513,"This skill provides a structured approach to evaluating agent performance, including methodologies for building test frameworks, creating evaluation rubrics, and implementing LLM-as-judge techniques. It includes example code for evaluation runners and production monitoring.",[195,196,197,198,199],"Builds multi-dimensional evaluation rubrics","Implements LLM-as-judge methodologies","Designs test sets stratified by complexity","Provides framework for continuous evaluation pipelines","Includes example code for evaluation and monitoring",[201,202,203,204],"Performing the evaluation itself","Automating agent development or tuning","Replacing human oversight entirely","Providing a specific agent to be evaluated",[206,207,208,209],"Evaluation methodology","Test design","Quality measurement","LLM-as-judge implementation",[],"3.0.0","4.4.0","To enable systematic evaluation of AI agent performance and quality, ensuring agents meet defined standards and drive desired outcomes.","The skill is highly polished with comprehensive documentation, clear examples, and robust code. The 'pass' severity on all applicable checks indicates a top-tier extension.",98,"A comprehensive framework for evaluating agent performance and quality.",[13,218,219,220,221],"testing","quality-assurance","rubrics","llm-as-judge","global","verified",[225,226,227,228],"When testing agent performance systematically","When validating context engineering choices","When measuring improvements over time","When building quality gates for agent pipelines",{"codeQuality":230,"collectedAt":232,"documentation":233,"maintenance":236,"security":242,"testCoverage":244},{"hasLockfile":231},false,1778694467712,{"descriptionLength":234,"readmeSize":235},264,13763,{"closedIssues90d":237,"forks":238,"hasChangelog":231,"openIssues90d":239,"pushedAt":240,"stars":241},2,1237,6,1776141908000,15630,{"hasNpmPackage":231,"license":243,"smitheryVerified":231},"MIT",{"hasCi":231,"hasTests":245},true,{"updatedAt":247},1778694482778,{"basePath":249,"githubOwner":250,"githubRepo":251,"locale":18,"slug":13,"type":252},"skills/evaluation","muratcankoylan","Agent-Skills-for-Context-Engineering","skill",{"_creationTime":254,"_id":255,"community":256,"display":257,"identity":261,"parentExtension":264,"providers":298,"relations":311,"tags":312,"workflow":313},1778694269038.6665,"k1754dy3wbsv2a5gr1a983zzs586njca",{"reviewCount":8},{"description":258,"installMethods":259,"name":260,"sourceUrl":14},"Comprehensive context engineering skills for building production-grade AI agent systems — covering fundamentals, degradation patterns, compression, optimization, latent briefing (KV sharing between agents), multi-agent coordination, memory systems, tool design, filesystem context, hosted agents, evaluation, advanced evaluation, project development, and cognitive architecture",{"claudeCode":251},"Agent Skills for Context Engineering",{"basePath":262,"githubOwner":250,"githubRepo":251,"locale":18,"slug":251,"type":263},"","plugin",{"_creationTime":265,"_id":266,"community":267,"display":268,"identity":271,"providers":273,"relations":292,"tags":294,"workflow":295},1778694269038.6663,"k1796gc85sm2bx753svn59gp5186mpz4",{"reviewCount":8},{"description":269,"installMethods":270,"name":260,"sourceUrl":14},"Context Engineering skills for building production-grade AI agent systems",{"claudeCode":12},{"basePath":262,"githubOwner":250,"githubRepo":251,"locale":18,"slug":251,"type":272},"marketplace",{"evaluate":274,"extract":285},{"promptVersionExtension":275,"promptVersionScoring":212,"score":276,"tags":277,"targetMarket":222,"tier":284},"3.1.0",75,[278,279,280,281,282,283],"ai","agent-skills","context-engineering","llm","development","architecture","community",{"commitSha":286,"license":243,"marketplace":287,"plugin":290},"HEAD",{"name":288,"pluginCount":289},"context-engineering-marketplace",1,{"mcpCount":8,"provider":291,"skillCount":8},"classify",{"repoId":293},"kd7f12maf5nxmx5xttjx7scfnx86m1tv",[279,278,283,280,282,281],{"evaluatedAt":296,"extractAt":297,"updatedAt":296},1778694283498,1778694269038,{"evaluate":299,"extract":308},{"promptVersionExtension":211,"promptVersionScoring":212,"score":300,"tags":301,"targetMarket":222,"tier":223},95,[280,302,303,304,305,306,307],"ai-agents","prompt-engineering","multi-agent-systems","llm-operations","agent-architecture","cognitive-architecture",{"commitSha":286,"license":243,"plugin":309},{"mcpCount":8,"provider":291,"skillCount":310},14,{"parentExtensionId":266,"repoId":293},[306,302,307,280,305,304,303],{"evaluatedAt":314,"extractAt":297,"updatedAt":314},1778694291902,{"evaluate":316,"extract":318},{"promptVersionExtension":211,"promptVersionScoring":212,"score":215,"tags":317,"targetMarket":222,"tier":223},[13,218,219,220,221],{"commitSha":286,"license":243},{"parentExtensionId":255,"repoId":293},{"_creationTime":321,"_id":293,"identity":322,"providers":323,"workflow":632},1778694264629.3296,{"githubOwner":250,"githubRepo":251,"sourceUrl":14},{"classify":324,"discover":626,"github":629},{"commitSha":286,"extensions":325},[326,339,347,374,397,418,432,450,466,478,490,502,514,523,534,546,556,568,580,594,608,616],{"basePath":262,"description":269,"displayName":288,"installMethods":327,"rationale":328,"selectedPaths":329,"source":338,"sourceLanguage":18,"type":272},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[330,333,335],{"path":331,"priority":332},".claude-plugin/marketplace.json","mandatory",{"path":334,"priority":332},"README.md",{"path":336,"priority":337},"LICENSE","high","rule",{"basePath":262,"description":258,"displayName":280,"installMethods":340,"rationale":341,"selectedPaths":342,"source":338,"sourceLanguage":18,"type":263},{"claudeCode":251},"inline plugin source from marketplace.json at / (coalesced with duplicate plugin at .plugin)",[343,344,345],{"path":334,"priority":332},{"path":336,"priority":337},{"path":346,"priority":337},"SKILL.md",{"basePath":348,"description":349,"displayName":350,"installMethods":351,"rationale":352,"selectedPaths":353,"source":338,"sourceLanguage":18,"type":252},"examples/book-sft-pipeline","This skill should be used when the user asks to \"fine-tune on books\", \"create SFT dataset\", \"train style model\", \"extract ePub text\", or mentions style transfer, LoRA training, book segmentation, or author voice replication.","book-sft-pipeline",{"claudeCode":12},"SKILL.md frontmatter at examples/book-sft-pipeline/SKILL.md",[354,355,356,359,361,363,365,368,370,372],{"path":346,"priority":332},{"path":334,"priority":337},{"path":357,"priority":358},"examples/gertrude-stein/README.md","low",{"path":360,"priority":358},"examples/gertrude-stein/dataset_sample.jsonl",{"path":362,"priority":358},"examples/gertrude-stein/sample_outputs.md",{"path":364,"priority":358},"examples/gertrude-stein/training_config.json",{"path":366,"priority":367},"references/segmentation-strategies.md","medium",{"path":369,"priority":367},"references/tinker-format.md",{"path":371,"priority":367},"references/tinker.txt",{"path":373,"priority":358},"scripts/pipeline_example.py",{"basePath":375,"description":376,"displayName":377,"installMethods":378,"rationale":379,"selectedPaths":380,"source":338,"sourceLanguage":18,"type":252},"examples/digital-brain-skill","This skill should be used when the user asks to \"write a post\", \"check my voice\", \"look up contact\", \"prepare for meeting\", \"weekly review\", \"track goals\", or mentions personal brand, content creation, network management, or voice consistency.","digital-brain",{"claudeCode":12},"SKILL.md frontmatter at examples/digital-brain-skill/SKILL.md",[381,382,383,385,387,389,391,393,395],{"path":346,"priority":332},{"path":334,"priority":337},{"path":384,"priority":367},"AGENT.md",{"path":386,"priority":367},"HOW-SKILLS-BUILT-THIS.md",{"path":388,"priority":367},"SKILLS-MAPPING.md",{"path":390,"priority":358},"examples/content-workflow.md",{"path":392,"priority":358},"examples/meeting-prep.md",{"path":394,"priority":367},"references/file-formats.md",{"path":396,"priority":358},"scripts/install.sh",{"basePath":398,"description":399,"displayName":400,"installMethods":401,"rationale":402,"selectedPaths":403,"source":338,"sourceLanguage":18,"type":252},"examples/interleaved-thinking","Debug and optimize AI agents by analyzing reasoning traces. Activates on 'debug agent', 'optimize prompt', 'analyze reasoning', 'why did the agent fail', 'improve agent performance', or when diagnosing agent failures and context degradation.","reasoning-trace-optimizer",{"claudeCode":12},"SKILL.md frontmatter at examples/interleaved-thinking/SKILL.md",[404,405,406,408,410,412,414,416],{"path":346,"priority":332},{"path":334,"priority":337},{"path":407,"priority":358},"docs/agentthinking.md",{"path":409,"priority":358},"docs/interleavedthinking.md",{"path":411,"priority":358},"docs/m2-1.md",{"path":413,"priority":358},"examples/01_basic_capture.py",{"path":415,"priority":358},"examples/02_tool_usage.py",{"path":417,"priority":358},"examples/03_full_optimization.py",{"basePath":419,"description":420,"displayName":421,"installMethods":422,"rationale":423,"selectedPaths":424,"source":338,"sourceLanguage":18,"type":252},"examples/interleaved-thinking/generated_skills/comprehensive-research-agent","Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls","comprehensive-research-agent",{"claudeCode":12},"SKILL.md frontmatter at examples/interleaved-thinking/generated_skills/comprehensive-research-agent/SKILL.md",[425,426,428,430],{"path":346,"priority":332},{"path":427,"priority":367},"references/optimization_summary.json",{"path":429,"priority":367},"references/optimized_prompt.txt",{"path":431,"priority":367},"references/patterns_found.json",{"basePath":433,"description":434,"displayName":435,"installMethods":436,"rationale":437,"selectedPaths":438,"source":338,"sourceLanguage":18,"type":252},"skills/advanced-evaluation","This skill should be used when the user asks to \"implement LLM-as-judge\", \"compare model outputs\", \"create evaluation rubrics\", \"mitigate evaluation bias\", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.","advanced-evaluation",{"claudeCode":12},"SKILL.md frontmatter at skills/advanced-evaluation/SKILL.md",[439,440,442,444,446,448],{"path":346,"priority":332},{"path":441,"priority":367},"references/bias-mitigation.md",{"path":443,"priority":367},"references/evaluation-pipeline.md",{"path":445,"priority":367},"references/implementation-patterns.md",{"path":447,"priority":367},"references/metrics-guide.md",{"path":449,"priority":358},"scripts/evaluation_example.py",{"basePath":451,"description":452,"displayName":453,"installMethods":454,"rationale":455,"selectedPaths":456,"source":338,"sourceLanguage":18,"type":252},"skills/bdi-mental-states","This skill should be used when the user asks to \"model agent mental states\", \"implement BDI architecture\", \"create belief-desire-intention models\", \"transform RDF to beliefs\", \"build cognitive agent\", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.","bdi-mental-states",{"claudeCode":12},"SKILL.md frontmatter at skills/bdi-mental-states/SKILL.md",[457,458,460,462,464],{"path":346,"priority":332},{"path":459,"priority":367},"references/bdi-ontology-core.md",{"path":461,"priority":367},"references/framework-integration.md",{"path":463,"priority":367},"references/rdf-examples.md",{"path":465,"priority":367},"references/sparql-competency.md",{"basePath":467,"description":468,"displayName":469,"installMethods":470,"rationale":471,"selectedPaths":472,"source":338,"sourceLanguage":18,"type":252},"skills/context-compression","This skill should be used when the user asks to \"compress context\", \"summarize conversation history\", \"implement compaction\", \"reduce token usage\", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.","context-compression",{"claudeCode":12},"SKILL.md frontmatter at skills/context-compression/SKILL.md",[473,474,476],{"path":346,"priority":332},{"path":475,"priority":367},"references/evaluation-framework.md",{"path":477,"priority":358},"scripts/compression_evaluator.py",{"basePath":479,"description":480,"displayName":481,"installMethods":482,"rationale":483,"selectedPaths":484,"source":338,"sourceLanguage":18,"type":252},"skills/context-degradation","This skill should be used when the user asks to \"diagnose context problems\", \"fix lost-in-middle issues\", \"debug agent failures\", \"understand context poisoning\", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.","context-degradation",{"claudeCode":12},"SKILL.md frontmatter at skills/context-degradation/SKILL.md",[485,486,488],{"path":346,"priority":332},{"path":487,"priority":367},"references/patterns.md",{"path":489,"priority":358},"scripts/degradation_detector.py",{"basePath":491,"description":492,"displayName":493,"installMethods":494,"rationale":495,"selectedPaths":496,"source":338,"sourceLanguage":18,"type":252},"skills/context-fundamentals","This skill should be used when the user asks to \"understand context\", \"explain context windows\", \"design agent architecture\", \"debug context issues\", \"optimize context usage\", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.","context-fundamentals",{"claudeCode":12},"SKILL.md frontmatter at skills/context-fundamentals/SKILL.md",[497,498,500],{"path":346,"priority":332},{"path":499,"priority":367},"references/context-components.md",{"path":501,"priority":358},"scripts/context_manager.py",{"basePath":503,"description":504,"displayName":505,"installMethods":506,"rationale":507,"selectedPaths":508,"source":338,"sourceLanguage":18,"type":252},"skills/context-optimization","This skill should be used when the user asks to \"optimize context\", \"reduce token costs\", \"improve context efficiency\", \"implement KV-cache optimization\", \"partition context\", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.","context-optimization",{"claudeCode":12},"SKILL.md frontmatter at skills/context-optimization/SKILL.md",[509,510,512],{"path":346,"priority":332},{"path":511,"priority":367},"references/optimization_techniques.md",{"path":513,"priority":358},"scripts/compaction.py",{"basePath":249,"description":10,"displayName":13,"installMethods":515,"rationale":516,"selectedPaths":517,"source":338,"sourceLanguage":18,"type":252},{"claudeCode":12},"SKILL.md frontmatter at skills/evaluation/SKILL.md",[518,519,521],{"path":346,"priority":332},{"path":520,"priority":367},"references/metrics.md",{"path":522,"priority":358},"scripts/evaluator.py",{"basePath":524,"description":525,"displayName":526,"installMethods":527,"rationale":528,"selectedPaths":529,"source":338,"sourceLanguage":18,"type":252},"skills/filesystem-context","This skill should be used when the user asks to \"offload context to files\", \"implement dynamic context discovery\", \"use filesystem for agent memory\", \"reduce context window bloat\", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.","filesystem-context",{"claudeCode":12},"SKILL.md frontmatter at skills/filesystem-context/SKILL.md",[530,531,532],{"path":346,"priority":332},{"path":445,"priority":367},{"path":533,"priority":358},"scripts/filesystem_context.py",{"basePath":535,"description":536,"displayName":537,"installMethods":538,"rationale":539,"selectedPaths":540,"source":338,"sourceLanguage":18,"type":252},"skills/hosted-agents","This skill should be used when the user asks to \"build background agent\", \"create hosted coding agent\", \"set up sandboxed execution\", \"implement multiplayer agent\", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.","hosted-agents",{"claudeCode":12},"SKILL.md frontmatter at skills/hosted-agents/SKILL.md",[541,542,544],{"path":346,"priority":332},{"path":543,"priority":367},"references/infrastructure-patterns.md",{"path":545,"priority":358},"scripts/sandbox_manager.py",{"basePath":547,"description":548,"displayName":549,"installMethods":550,"rationale":551,"selectedPaths":552,"source":338,"sourceLanguage":18,"type":252},"skills/latent-briefing","This skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for multi-agent\", \"orchestrator worker context\", \"latent briefing\", \"reduce worker tokens\", \"cross-agent memory without summarization\", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.","latent-briefing",{"claudeCode":12},"SKILL.md frontmatter at skills/latent-briefing/SKILL.md",[553,554],{"path":346,"priority":332},{"path":555,"priority":367},"references/attention-matching-formulation.md",{"basePath":557,"description":558,"displayName":559,"installMethods":560,"rationale":561,"selectedPaths":562,"source":338,"sourceLanguage":18,"type":252},"skills/memory-systems","Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to \"implement agent memory\", \"persist state across sessions\", \"build knowledge graph for agents\", \"track entities over time\", \"add long-term memory\", \"choose a memory framework\", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).\n","memory-systems",{"claudeCode":12},"SKILL.md frontmatter at skills/memory-systems/SKILL.md",[563,564,566],{"path":346,"priority":332},{"path":565,"priority":367},"references/implementation.md",{"path":567,"priority":358},"scripts/memory_store.py",{"basePath":569,"description":570,"displayName":571,"installMethods":572,"rationale":573,"selectedPaths":574,"source":338,"sourceLanguage":18,"type":252},"skills/multi-agent-patterns","This skill should be used when the user asks to \"design multi-agent system\", \"implement supervisor pattern\", \"create swarm architecture\", \"coordinate multiple agents\", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.","multi-agent-patterns",{"claudeCode":12},"SKILL.md frontmatter at skills/multi-agent-patterns/SKILL.md",[575,576,578],{"path":346,"priority":332},{"path":577,"priority":367},"references/frameworks.md",{"path":579,"priority":358},"scripts/coordination.py",{"basePath":581,"description":582,"displayName":583,"installMethods":584,"rationale":585,"selectedPaths":586,"source":338,"sourceLanguage":18,"type":252},"skills/project-development","This skill should be used when the user asks to \"start an LLM project\", \"design batch pipeline\", \"evaluate task-model fit\", \"structure agent project\", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.","project-development",{"claudeCode":12},"SKILL.md frontmatter at skills/project-development/SKILL.md",[587,588,590,592],{"path":346,"priority":332},{"path":589,"priority":367},"references/case-studies.md",{"path":591,"priority":367},"references/pipeline-patterns.md",{"path":593,"priority":358},"scripts/pipeline_template.py",{"basePath":595,"description":596,"displayName":597,"installMethods":598,"rationale":599,"selectedPaths":600,"source":338,"sourceLanguage":18,"type":252},"skills/tool-design","This skill should be used when the user asks to \"design agent tools\", \"create tool descriptions\", \"reduce tool complexity\", \"implement MCP tools\", or mentions tool consolidation, architectural reduction, tool naming conventions, or agent-tool interfaces.","tool-design",{"claudeCode":12},"SKILL.md frontmatter at skills/tool-design/SKILL.md",[601,602,604,606],{"path":346,"priority":332},{"path":603,"priority":367},"references/architectural_reduction.md",{"path":605,"priority":367},"references/best_practices.md",{"path":607,"priority":358},"scripts/description_generator.py",{"basePath":609,"description":610,"displayName":611,"installMethods":612,"rationale":613,"selectedPaths":614,"source":338,"sourceLanguage":18,"type":252},"template","Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.","skill-template",{"claudeCode":12},"SKILL.md frontmatter at template/SKILL.md",[615],{"path":346,"priority":332},{"basePath":398,"installMethods":617,"rationale":618,"selectedPaths":619,"source":338,"sourceLanguage":18,"type":625},{"pypi":400},"cli ecosystem detected at examples/interleaved-thinking",[620,622,623],{"path":621,"priority":332},"pyproject.toml",{"path":334,"priority":332},{"path":624,"priority":367},"reasoning_trace_optimizer/cli.py","cli",{"sources":627},[628],"manual",{"closedIssues90d":237,"description":630,"forks":238,"license":243,"openIssues90d":239,"pushedAt":240,"readmeSize":235,"stars":241,"topics":631},"A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.",[],{"classifiedAt":633,"discoverAt":634,"extractAt":635,"githubAt":635,"updatedAt":633},1778694268713,1778694264629,1778694266904,[13,221,219,220,218],{"evaluatedAt":247,"extractAt":297,"updatedAt":247},[],[640,660,688,721,751,774],{"_creationTime":641,"_id":642,"community":643,"display":644,"identity":647,"providers":648,"relations":656,"tags":657,"workflow":658},1778694269038.6682,"k1752cypc448mke749yjbkc65186mg6f",{"reviewCount":8},{"description":468,"installMethods":645,"name":646,"sourceUrl":14},{"claudeCode":12},"Context Compression",{"basePath":467,"githubOwner":250,"githubRepo":251,"locale":18,"slug":469,"type":252},{"evaluate":649,"extract":655},{"promptVersionExtension":211,"promptVersionScoring":212,"score":650,"tags":651,"targetMarket":222,"tier":223},100,[280,281,652,653,654,13],"agent","summarization","compression",{"commitSha":286,"license":243},{"parentExtensionId":255,"repoId":293},[652,654,280,13,281,653],{"evaluatedAt":659,"extractAt":297,"updatedAt":659},1778694410149,{"_creationTime":661,"_id":662,"community":663,"display":664,"identity":670,"providers":674,"relations":682,"tags":684,"workflow":685},1778697513812.0618,"k17a42wbbfjawy7azce27f0f8186mv0g",{"reviewCount":8},{"description":665,"installMethods":666,"name":668,"sourceUrl":669},"Anti-AI-generic design guidelines. Use when creating UI prototypes, reviewing designs for generic AI patterns, or setting up a project design system.",{"claudeCode":667},"spartan-stratos/spartan-ai-toolkit","design-workflow","https://github.com/spartan-stratos/spartan-ai-toolkit",{"basePath":671,"githubOwner":672,"githubRepo":673,"locale":18,"slug":668,"type":252},".codex/skills/design-workflow","spartan-stratos","spartan-ai-toolkit",{"evaluate":675,"extract":681},{"promptVersionExtension":211,"promptVersionScoring":212,"score":650,"tags":676,"targetMarket":222,"tier":223},[677,678,679,680,219],"design","ux","guidelines","prototyping",{"commitSha":286},{"repoId":683},"kd73rjj0rnrv7y0rz9qc3psn0586n75g",[677,679,680,219,678],{"evaluatedAt":686,"extractAt":687,"updatedAt":686},1778697723103,1778697513812,{"_creationTime":689,"_id":690,"community":691,"display":692,"identity":698,"providers":704,"relations":713,"tags":716,"workflow":717},1778691370980.6204,"k175r5wzz8n1wk65qfwqv70vkn86n2kg",{"reviewCount":8},{"description":693,"installMethods":694,"name":696,"sourceUrl":697},"Überprüft Pull Requests in Drupal 11 (oder anderen) Projekten gemäß der Codex-Methodik (Geschäftslogik, Edge Cases von Hooks/Queries, Sicherheit, Performance, Vollständigkeit). Generiert einen .md-Bericht im erkannten IDE-Ordner (.antigravity/, .cursor/, .vscode/ oder docs/) mit Befunden nach Schweregrad und umsetzbaren Lösungen. Verwenden Sie dies, wenn der Benutzer \"Codex-Überprüfung\", \"PR-Überprüfung\", \"PR überprüfen\", \"PR überprüfen\" anfordert.",{"claudeCode":695},"j4rk0r/claude-skills","Codex PR Review","https://github.com/j4rk0r/claude-skills",{"basePath":699,"githubOwner":700,"githubRepo":701,"locale":702,"slug":703,"type":252},"skills/codex-pr-review","j4rk0r","claude-skills","de","codex-pr-review",{"evaluate":705,"extract":712},{"promptVersionExtension":211,"promptVersionScoring":212,"score":650,"tags":706,"targetMarket":222,"tier":223},[707,708,709,710,711,219],"drupal","code-review","pull-request","codex","security",{"commitSha":286,"license":243},{"repoId":714,"translatedFrom":715},"kd79shaph0e07035621cxd7x1n86m944","k175cj68ewyej64segk2xnppss86n5ad",[708,710,707,709,219,711],{"evaluatedAt":718,"extractAt":719,"updatedAt":720},1778691239127,1778691193352,1778691370980,{"_creationTime":722,"_id":723,"community":724,"display":725,"identity":731,"providers":735,"relations":744,"tags":747,"workflow":748},1778695548458.405,"k17e4fvenz80ssf2drcpw8g07d86nmyp",{"reviewCount":8},{"description":726,"installMethods":727,"name":729,"sourceUrl":730},"Test A2A interoperability between agents by validating Agent Card conformance, exercising all task lifecycle states, and verifying streaming and error handling. Use when verifying a new A2A server implementation before deployment, validating interoperability between two or more A2A agents, running conformance tests in CI/CD for A2A services, debugging failures in multi-agent A2A workflows, or certifying that an agent meets A2A protocol requirements for a registry.\n",{"claudeCode":728},"pjt222/agent-almanac","test-a2a-interop","https://github.com/pjt222/agent-almanac",{"basePath":732,"githubOwner":733,"githubRepo":734,"locale":18,"slug":729,"type":252},"skills/test-a2a-interop","pjt222","agent-almanac",{"evaluate":736,"extract":743},{"promptVersionExtension":211,"promptVersionScoring":212,"score":650,"tags":737,"targetMarket":222,"tier":223},[738,218,739,740,741,742],"a2a","interoperability","conformance","protocol","agent-card",{"commitSha":286},{"parentExtensionId":745,"repoId":746},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[738,742,740,739,741,218],{"evaluatedAt":749,"extractAt":750,"updatedAt":749},1778701974333,1778695548458,{"_creationTime":752,"_id":753,"community":754,"display":755,"identity":759,"providers":761,"relations":770,"tags":771,"workflow":772},1778695548458.3948,"k17dt4dfvv34st23k22bndh01186m334",{"reviewCount":8},{"description":756,"installMethods":757,"name":758,"sourceUrl":730},"Run the jigsawR test suite via WSL R execution. Supports full suite, filtered by pattern, or single file. Interprets pass/fail/skip counts and identifies failing tests. Never uses --vanilla flag (renv needs .Rprofile for activation). Use after modifying any R source code, after adding a new puzzle type or feature, before committing changes to verify nothing is broken, or when debugging a specific test failure.\n",{"claudeCode":728},"run-puzzle-tests",{"basePath":760,"githubOwner":733,"githubRepo":734,"locale":18,"slug":758,"type":252},"skills/run-puzzle-tests",{"evaluate":762,"extract":769},{"promptVersionExtension":211,"promptVersionScoring":212,"score":650,"tags":763,"targetMarket":222,"tier":223},[764,218,765,766,767,768],"r","jigsawr","wsl","testthat","renv",{"commitSha":286},{"parentExtensionId":745,"repoId":746},[765,764,768,218,767,766],{"evaluatedAt":773,"extractAt":750,"updatedAt":773},1778700998995,{"_creationTime":775,"_id":776,"community":777,"display":778,"identity":784,"providers":788,"relations":795,"tags":797,"workflow":798},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":779,"installMethods":780,"name":782,"sourceUrl":783},"Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.",{"claudeCode":781},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":785,"githubOwner":786,"githubRepo":787,"locale":18,"slug":782,"type":252},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":789,"extract":794},{"promptVersionExtension":211,"promptVersionScoring":212,"score":650,"tags":790,"targetMarket":222,"tier":223},[218,791,792,793,625],"telegram","automation","qa",{"commitSha":286},{"repoId":796},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[792,625,793,791,218],{"evaluatedAt":799,"extractAt":800,"updatedAt":799},1778698038113,1778697652123]