[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-muratcankoylan-advanced-evaluation-en":3,"guides-for-muratcankoylan-advanced-evaluation":632,"similar-k175c2rf65bgg309d20zagdzax86nthw-en":633},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":226,"parentExtension":248,"providers":310,"relations":314,"repo":315,"tags":630,"workflow":631},1778694269038.6677,"k175c2rf65bgg309d20zagdzax86nthw",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"muratcankoylan/Agent-Skills-for-Context-Engineering","advanced-evaluation","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":241},1778694380362.1853,"kn747g7r06qk1y4mtn0e603mfn86nxbr","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":205,"promptVersionScoring":206,"purpose":207,"rationale":208,"score":209,"summary":210,"tags":211,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,100,104,108,111,115,118,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of evaluating LLM outputs using LLMs as judges, including specific keywords like 'LLM-as-judge', 'compare model outputs', and 'evaluation rubrics'.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers advanced techniques for building reliable LLM evaluation systems by synthesizing research and industry practices, going beyond basic LLM-as-judge capabilities to address bias mitigation and rubric generation.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides detailed patterns, examples, and guidance for implementing robust LLM evaluation pipelines, including direct scoring, pairwise comparison with bias mitigation, and rubric generation, covering the complete lifecycle of evaluation system design.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on advanced techniques for LLM evaluation, including LLM-as-judge, rubric generation, and bias mitigation, without straying into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately and concisely reflects the skill's purpose and capabilities, including key use cases and relevant terminology.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose tools directly; its functionality is accessed through natural language commands within an agent framework.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not have configurable parameters or options that require explicit documentation beyond its instructions and examples.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","As this skill does not expose explicit tools, tool naming conventions are not applicable.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This skill operates via natural language prompts and does not expose a tool interface with input/output schemas.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension uses the MIT license, which is a permissive open-source license, clearly declared in a LICENSE file.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository was last updated on April 14, 2026, which is within the last 3 months.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to have external dependencies that require specific management beyond the core agent environment.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill does not handle or expose secrets, as it operates on provided text and evaluation logic.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's instructions and references are well-defined and do not appear to load or execute untrusted third-party data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch external content at runtime or include patterns that could be exploited for prompt injection or supply-chain attacks.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within the agent's environment and does not attempt to modify files or paths outside its defined scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","There are no indications of detached-process spawns or deny-retry loops that could be used for sandbox escape.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not instruct the agent to read or submit confidential data to any third party. All outbound calls, if any, would be documented.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content and documentation are free of hidden-steering tricks, invisible characters, or other obfuscation methods.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's code and instructions are clear, readable, and do not involve obfuscated payloads, base64 decoding, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill does not make structural assumptions about the user's project organization and handles its operations within the agent's context.",{"category":96,"check":97,"severity":98,"summary":99},"Trust","Issues Attention","info","In the last 90 days, 6 issues were opened and 2 were closed, indicating slow but present maintainer engagement. The closure rate is low (33%), but the number of open issues is relatively small.",{"category":101,"check":102,"severity":24,"summary":103},"Versioning","Release Management","The skill has a meaningful version number (2.0.0) declared in the SKILL.md frontmatter, indicating clear versioning.",{"category":105,"check":106,"severity":42,"summary":107},"Execution","Validation","The skill operates based on natural language instructions and does not expose tools with structured input/output schemas that require explicit validation libraries.",{"category":66,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","The skill is analytical and does not perform any destructive operations that would require confirmation gates or dry-run modes.",{"category":112,"check":113,"severity":24,"summary":114},"Code Execution","Error Handling","The skill's logic is designed to handle errors gracefully, reporting issues meaningfully and avoiding silent failures or state corruption.",{"category":112,"check":116,"severity":42,"summary":117},"Logging","The skill operates within the agent's turn and does not require a separate audit log file for its operations.",{"category":119,"check":120,"severity":42,"summary":121},"Compliance","GDPR","The skill does not process personal data; its function is to evaluate text based on defined criteria.",{"category":119,"check":123,"severity":24,"summary":124},"Target market","The skill's content and evaluation principles are globally applicable, with no regional or jurisdictional restrictions detected.",{"category":92,"check":126,"severity":24,"summary":127},"Runtime stability","The skill is designed to be platform-agnostic, relying on standard LLM interaction patterns and not making assumptions about specific editors, shells, or OS.",{"category":45,"check":129,"severity":24,"summary":130},"README","The README provides a comprehensive overview of the repository's purpose, skills, and usage, complementing the individual skill documentation.",{"category":33,"check":132,"severity":42,"summary":133},"Tool surface size","This is a skill, not a tool-based extension, so tool surface size is not applicable.",{"category":40,"check":135,"severity":42,"summary":136},"Overlapping near-synonym tools","The skill does not expose specific tools, thus there are no overlapping near-synonym tools to evaluate.",{"category":45,"check":138,"severity":24,"summary":139},"Phantom features","All features described in the README and SKILL.md, such as direct scoring and pairwise comparison, have corresponding implementations and detailed explanations within the skill's documentation.",{"category":141,"check":142,"severity":24,"summary":143},"Install","Installation instruction","The README provides clear, copy-pasteable instructions for installing the plugin via Claude Code, including both browsing and direct command methods.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The skill's design and examples suggest that errors would be framed in user terms with remediation steps or links, as detailed in the referenced implementation patterns.",{"category":105,"check":149,"severity":42,"summary":150},"Pinned dependencies","As the skill does not bundle scripts with external dependencies, pinned dependencies are not applicable.",{"category":33,"check":152,"severity":42,"summary":153},"Dry-run preview","The skill is analytical and does not perform state-changing operations or send data outward, making a dry-run feature irrelevant.",{"category":155,"check":156,"severity":42,"summary":157},"Protocol","Idempotent retry & timeouts","The skill operates within a single turn and does not involve remote calls or state-changing operations that require idempotency or timeouts.",{"category":119,"check":159,"severity":24,"summary":160},"Telemetry opt-in","There is no indication that the skill collects telemetry; if it did, the design principles would mandate opt-in and documentation.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The skill's purpose is precisely defined, stating what it does (implement LLM-as-judge, compare outputs, etc.) and when to use it, with clear trigger phrases.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The SKILL.md frontmatter is concise, self-contained, and accurately summarizes the core capability, followed by specific trigger phrases.",{"category":45,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md is well-structured and adheres to the guideline of delegating deeper material to separate files via progressive disclosure.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The skill effectively uses progressive disclosure, outlining procedures in SKILL.md and linking to referenced files for more detailed sub-tasks.",{"category":171,"check":175,"severity":42,"summary":176},"Forked exploration","The skill is focused on evaluation logic and does not involve deep exploration or code review that would necessitate `context: fork`.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The skill includes three comprehensive examples demonstrating direct scoring, pairwise comparison with bias mitigation, and rubric generation, with clear inputs and expected outputs.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The skill's documentation explicitly lists and addresses potential failure modes and limitations within its reference materials, offering recovery steps.",{"category":112,"check":184,"severity":42,"summary":185},"Tool Fallback","This skill does not rely on external tools like a custom MCP server, so tool fallback mechanisms are not applicable.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill's design emphasizes robustness, implying that it would halt on unexpected pre-states and report clearly, aligning with safety principles.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill is self-contained and clearly lists its dependencies and related skills in the 'Integration' section, avoiding implicit coupling.",1778694380255,"This skill provides advanced methods for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison with bias mitigation, and rubric generation. It synthesizes research and industry practices into actionable patterns for building reliable evaluation systems.",[196,197,198,199,200],"Implement LLM-as-judge evaluation pipelines","Perform pairwise comparison with position bias mitigation","Generate domain-specific scoring rubrics","Mitigate systematic biases in LLM evaluations","Select appropriate metrics and evaluation strategies",[202,203,204],"Performing actual LLM generation","Evaluating non-textual outputs","Providing a generic prompt engineering skill","3.0.0","4.4.0","To empower users to build robust and unbiased LLM evaluation systems by mastering advanced LLM-as-a-Judge techniques and implementing production-grade patterns.","The skill is exceptionally well-documented, clearly defined, and robustly designed, with excellent examples and adherence to best practices. The only minor finding is related to issue engagement, which is info-level and does not impact overall quality.",96,"A high-quality, production-ready skill for advanced LLM evaluation techniques.",[212,213,214,215,216],"llm-as-judge","evaluation","rubric-generation","bias-mitigation","nlp","global","verified",[220,221,222,223],"Building automated evaluation systems for LLM outputs","Comparing multiple model responses to select the best one","Establishing consistent quality standards across evaluation teams","Designing A/B tests for prompt or model changes",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"security":237,"testCoverage":239},{"hasLockfile":226},false,1778694364228,{"descriptionLength":229,"readmeSize":230},274,13763,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"openIssues90d":234,"pushedAt":235,"stars":236},2,1237,6,1776141908000,15630,{"hasNpmPackage":226,"license":238,"smitheryVerified":226},"MIT",{"hasCi":226,"hasTests":240},true,{"updatedAt":242},1778694380362,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":13,"type":247},"skills/advanced-evaluation","muratcankoylan","Agent-Skills-for-Context-Engineering","skill",{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":256,"parentExtension":259,"providers":293,"relations":306,"tags":307,"workflow":308},1778694269038.6665,"k1754dy3wbsv2a5gr1a983zzs586njca",{"reviewCount":8},{"description":253,"installMethods":254,"name":255,"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":246},"Agent Skills for Context Engineering",{"basePath":257,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":258},"","plugin",{"_creationTime":260,"_id":261,"community":262,"display":263,"identity":266,"providers":268,"relations":287,"tags":289,"workflow":290},1778694269038.6663,"k1796gc85sm2bx753svn59gp5186mpz4",{"reviewCount":8},{"description":264,"installMethods":265,"name":255,"sourceUrl":14},"Context Engineering skills for building production-grade AI agent systems",{"claudeCode":12},{"basePath":257,"githubOwner":245,"githubRepo":246,"locale":18,"slug":246,"type":267},"marketplace",{"evaluate":269,"extract":280},{"promptVersionExtension":270,"promptVersionScoring":206,"score":271,"tags":272,"targetMarket":217,"tier":279},"3.1.0",75,[273,274,275,276,277,278],"ai","agent-skills","context-engineering","llm","development","architecture","community",{"commitSha":281,"license":238,"marketplace":282,"plugin":285},"HEAD",{"name":283,"pluginCount":284},"context-engineering-marketplace",1,{"mcpCount":8,"provider":286,"skillCount":8},"classify",{"repoId":288},"kd7f12maf5nxmx5xttjx7scfnx86m1tv",[274,273,278,275,277,276],{"evaluatedAt":291,"extractAt":292,"updatedAt":291},1778694283498,1778694269038,{"evaluate":294,"extract":303},{"promptVersionExtension":205,"promptVersionScoring":206,"score":295,"tags":296,"targetMarket":217,"tier":218},95,[275,297,298,299,300,301,302],"ai-agents","prompt-engineering","multi-agent-systems","llm-operations","agent-architecture","cognitive-architecture",{"commitSha":281,"license":238,"plugin":304},{"mcpCount":8,"provider":286,"skillCount":305},14,{"parentExtensionId":261,"repoId":288},[301,297,302,275,300,299,298],{"evaluatedAt":309,"extractAt":292,"updatedAt":309},1778694291902,{"evaluate":311,"extract":313},{"promptVersionExtension":205,"promptVersionScoring":206,"score":209,"tags":312,"targetMarket":217,"tier":218},[212,213,214,215,216],{"commitSha":281},{"parentExtensionId":250,"repoId":288},{"_creationTime":316,"_id":288,"identity":317,"providers":318,"workflow":626},1778694264629.3296,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":319,"discover":620,"github":623},{"commitSha":281,"extensions":320},[321,334,342,369,392,413,427,442,458,470,482,494,506,517,528,540,550,562,574,588,602,610],{"basePath":257,"description":264,"displayName":283,"installMethods":322,"rationale":323,"selectedPaths":324,"source":333,"sourceLanguage":18,"type":267},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[325,328,330],{"path":326,"priority":327},".claude-plugin/marketplace.json","mandatory",{"path":329,"priority":327},"README.md",{"path":331,"priority":332},"LICENSE","high","rule",{"basePath":257,"description":253,"displayName":275,"installMethods":335,"rationale":336,"selectedPaths":337,"source":333,"sourceLanguage":18,"type":258},{"claudeCode":246},"inline plugin source from marketplace.json at / (coalesced with duplicate plugin at .plugin)",[338,339,340],{"path":329,"priority":327},{"path":331,"priority":332},{"path":341,"priority":332},"SKILL.md",{"basePath":343,"description":344,"displayName":345,"installMethods":346,"rationale":347,"selectedPaths":348,"source":333,"sourceLanguage":18,"type":247},"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",[349,350,351,354,356,358,360,363,365,367],{"path":341,"priority":327},{"path":329,"priority":332},{"path":352,"priority":353},"examples/gertrude-stein/README.md","low",{"path":355,"priority":353},"examples/gertrude-stein/dataset_sample.jsonl",{"path":357,"priority":353},"examples/gertrude-stein/sample_outputs.md",{"path":359,"priority":353},"examples/gertrude-stein/training_config.json",{"path":361,"priority":362},"references/segmentation-strategies.md","medium",{"path":364,"priority":362},"references/tinker-format.md",{"path":366,"priority":362},"references/tinker.txt",{"path":368,"priority":353},"scripts/pipeline_example.py",{"basePath":370,"description":371,"displayName":372,"installMethods":373,"rationale":374,"selectedPaths":375,"source":333,"sourceLanguage":18,"type":247},"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",[376,377,378,380,382,384,386,388,390],{"path":341,"priority":327},{"path":329,"priority":332},{"path":379,"priority":362},"AGENT.md",{"path":381,"priority":362},"HOW-SKILLS-BUILT-THIS.md",{"path":383,"priority":362},"SKILLS-MAPPING.md",{"path":385,"priority":353},"examples/content-workflow.md",{"path":387,"priority":353},"examples/meeting-prep.md",{"path":389,"priority":362},"references/file-formats.md",{"path":391,"priority":353},"scripts/install.sh",{"basePath":393,"description":394,"displayName":395,"installMethods":396,"rationale":397,"selectedPaths":398,"source":333,"sourceLanguage":18,"type":247},"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",[399,400,401,403,405,407,409,411],{"path":341,"priority":327},{"path":329,"priority":332},{"path":402,"priority":353},"docs/agentthinking.md",{"path":404,"priority":353},"docs/interleavedthinking.md",{"path":406,"priority":353},"docs/m2-1.md",{"path":408,"priority":353},"examples/01_basic_capture.py",{"path":410,"priority":353},"examples/02_tool_usage.py",{"path":412,"priority":353},"examples/03_full_optimization.py",{"basePath":414,"description":415,"displayName":416,"installMethods":417,"rationale":418,"selectedPaths":419,"source":333,"sourceLanguage":18,"type":247},"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",[420,421,423,425],{"path":341,"priority":327},{"path":422,"priority":362},"references/optimization_summary.json",{"path":424,"priority":362},"references/optimized_prompt.txt",{"path":426,"priority":362},"references/patterns_found.json",{"basePath":244,"description":10,"displayName":13,"installMethods":428,"rationale":429,"selectedPaths":430,"source":333,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at skills/advanced-evaluation/SKILL.md",[431,432,434,436,438,440],{"path":341,"priority":327},{"path":433,"priority":362},"references/bias-mitigation.md",{"path":435,"priority":362},"references/evaluation-pipeline.md",{"path":437,"priority":362},"references/implementation-patterns.md",{"path":439,"priority":362},"references/metrics-guide.md",{"path":441,"priority":353},"scripts/evaluation_example.py",{"basePath":443,"description":444,"displayName":445,"installMethods":446,"rationale":447,"selectedPaths":448,"source":333,"sourceLanguage":18,"type":247},"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",[449,450,452,454,456],{"path":341,"priority":327},{"path":451,"priority":362},"references/bdi-ontology-core.md",{"path":453,"priority":362},"references/framework-integration.md",{"path":455,"priority":362},"references/rdf-examples.md",{"path":457,"priority":362},"references/sparql-competency.md",{"basePath":459,"description":460,"displayName":461,"installMethods":462,"rationale":463,"selectedPaths":464,"source":333,"sourceLanguage":18,"type":247},"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",[465,466,468],{"path":341,"priority":327},{"path":467,"priority":362},"references/evaluation-framework.md",{"path":469,"priority":353},"scripts/compression_evaluator.py",{"basePath":471,"description":472,"displayName":473,"installMethods":474,"rationale":475,"selectedPaths":476,"source":333,"sourceLanguage":18,"type":247},"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",[477,478,480],{"path":341,"priority":327},{"path":479,"priority":362},"references/patterns.md",{"path":481,"priority":353},"scripts/degradation_detector.py",{"basePath":483,"description":484,"displayName":485,"installMethods":486,"rationale":487,"selectedPaths":488,"source":333,"sourceLanguage":18,"type":247},"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",[489,490,492],{"path":341,"priority":327},{"path":491,"priority":362},"references/context-components.md",{"path":493,"priority":353},"scripts/context_manager.py",{"basePath":495,"description":496,"displayName":497,"installMethods":498,"rationale":499,"selectedPaths":500,"source":333,"sourceLanguage":18,"type":247},"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",[501,502,504],{"path":341,"priority":327},{"path":503,"priority":362},"references/optimization_techniques.md",{"path":505,"priority":353},"scripts/compaction.py",{"basePath":507,"description":508,"displayName":213,"installMethods":509,"rationale":510,"selectedPaths":511,"source":333,"sourceLanguage":18,"type":247},"skills/evaluation","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},"SKILL.md frontmatter at skills/evaluation/SKILL.md",[512,513,515],{"path":341,"priority":327},{"path":514,"priority":362},"references/metrics.md",{"path":516,"priority":353},"scripts/evaluator.py",{"basePath":518,"description":519,"displayName":520,"installMethods":521,"rationale":522,"selectedPaths":523,"source":333,"sourceLanguage":18,"type":247},"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",[524,525,526],{"path":341,"priority":327},{"path":437,"priority":362},{"path":527,"priority":353},"scripts/filesystem_context.py",{"basePath":529,"description":530,"displayName":531,"installMethods":532,"rationale":533,"selectedPaths":534,"source":333,"sourceLanguage":18,"type":247},"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",[535,536,538],{"path":341,"priority":327},{"path":537,"priority":362},"references/infrastructure-patterns.md",{"path":539,"priority":353},"scripts/sandbox_manager.py",{"basePath":541,"description":542,"displayName":543,"installMethods":544,"rationale":545,"selectedPaths":546,"source":333,"sourceLanguage":18,"type":247},"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",[547,548],{"path":341,"priority":327},{"path":549,"priority":362},"references/attention-matching-formulation.md",{"basePath":551,"description":552,"displayName":553,"installMethods":554,"rationale":555,"selectedPaths":556,"source":333,"sourceLanguage":18,"type":247},"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",[557,558,560],{"path":341,"priority":327},{"path":559,"priority":362},"references/implementation.md",{"path":561,"priority":353},"scripts/memory_store.py",{"basePath":563,"description":564,"displayName":565,"installMethods":566,"rationale":567,"selectedPaths":568,"source":333,"sourceLanguage":18,"type":247},"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",[569,570,572],{"path":341,"priority":327},{"path":571,"priority":362},"references/frameworks.md",{"path":573,"priority":353},"scripts/coordination.py",{"basePath":575,"description":576,"displayName":577,"installMethods":578,"rationale":579,"selectedPaths":580,"source":333,"sourceLanguage":18,"type":247},"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",[581,582,584,586],{"path":341,"priority":327},{"path":583,"priority":362},"references/case-studies.md",{"path":585,"priority":362},"references/pipeline-patterns.md",{"path":587,"priority":353},"scripts/pipeline_template.py",{"basePath":589,"description":590,"displayName":591,"installMethods":592,"rationale":593,"selectedPaths":594,"source":333,"sourceLanguage":18,"type":247},"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",[595,596,598,600],{"path":341,"priority":327},{"path":597,"priority":362},"references/architectural_reduction.md",{"path":599,"priority":362},"references/best_practices.md",{"path":601,"priority":353},"scripts/description_generator.py",{"basePath":603,"description":604,"displayName":605,"installMethods":606,"rationale":607,"selectedPaths":608,"source":333,"sourceLanguage":18,"type":247},"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",[609],{"path":341,"priority":327},{"basePath":393,"installMethods":611,"rationale":612,"selectedPaths":613,"source":333,"sourceLanguage":18,"type":619},{"pypi":395},"cli ecosystem detected at examples/interleaved-thinking",[614,616,617],{"path":615,"priority":327},"pyproject.toml",{"path":329,"priority":327},{"path":618,"priority":362},"reasoning_trace_optimizer/cli.py","cli",{"sources":621},[622],"manual",{"closedIssues90d":232,"description":624,"forks":233,"license":238,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":625},"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":627,"discoverAt":628,"extractAt":629,"githubAt":629,"updatedAt":627},1778694268713,1778694264629,1778694266904,[215,213,212,216,214],{"evaluatedAt":242,"extractAt":292,"updatedAt":242},[],[634,653,673,703,734,761],{"_creationTime":635,"_id":636,"community":637,"display":638,"identity":640,"providers":641,"relations":649,"tags":650,"workflow":651},1778694269038.6692,"k171cfyvthhb63hdrhaqtpybes86m9pq",{"reviewCount":8},{"description":508,"installMethods":639,"name":213,"sourceUrl":14},{"claudeCode":12},{"basePath":507,"githubOwner":245,"githubRepo":246,"locale":18,"slug":213,"type":247},{"evaluate":642,"extract":648},{"promptVersionExtension":205,"promptVersionScoring":206,"score":643,"tags":644,"targetMarket":217,"tier":218},98,[213,645,646,647,212],"testing","quality-assurance","rubrics",{"commitSha":281,"license":238},{"parentExtensionId":250,"repoId":288},[213,212,646,647,645],{"evaluatedAt":652,"extractAt":292,"updatedAt":652},1778694482778,{"_creationTime":654,"_id":655,"community":656,"display":657,"identity":660,"providers":661,"relations":669,"tags":670,"workflow":671},1778694269038.6682,"k1752cypc448mke749yjbkc65186mg6f",{"reviewCount":8},{"description":460,"installMethods":658,"name":659,"sourceUrl":14},{"claudeCode":12},"Context Compression",{"basePath":459,"githubOwner":245,"githubRepo":246,"locale":18,"slug":461,"type":247},{"evaluate":662,"extract":668},{"promptVersionExtension":205,"promptVersionScoring":206,"score":663,"tags":664,"targetMarket":217,"tier":218},100,[275,276,665,666,667,213],"agent","summarization","compression",{"commitSha":281,"license":238},{"parentExtensionId":250,"repoId":288},[665,667,275,213,276,666],{"evaluatedAt":672,"extractAt":292,"updatedAt":672},1778694410149,{"_creationTime":674,"_id":675,"community":676,"display":677,"identity":683,"providers":688,"relations":696,"tags":699,"workflow":700},1778697045057.978,"k1709qff277g3qreq668nrfj0d86nrrb",{"reviewCount":8},{"description":678,"installMethods":679,"name":681,"sourceUrl":682},"Scrub AI tells from any text draft OR audit a finished post against the 2026 algorithm heuristic checklist. Tier-based rewriter (forensic / strict / aesthetic / all) plus `--mode audit` for detection-only pass-fail review covering length, hook, CTA, format penalties, AI vocab. Sub-tools: emoji-pattern detector, multi-detector spread tester (GPTZero, Originality.ai, ZeroGPT, Sapling, Copyleaks), rule explainer. Triggers on \"humanize\", \"de-AI\", \"review this draft\", \"audit before posting\", \"is this ready\".",{"claudeCode":680},"sergebulaev/linkedin-skills","LinkedIn Humanizer","https://github.com/sergebulaev/linkedin-skills",{"basePath":684,"githubOwner":685,"githubRepo":686,"locale":18,"slug":687,"type":247},"skills/linkedin-humanizer","sergebulaev","linkedin-skills","linkedin-humanizer",{"evaluate":689,"extract":695},{"promptVersionExtension":205,"promptVersionScoring":206,"score":663,"tags":690,"targetMarket":217,"tier":218},[691,692,693,694,216],"ai-detection","text-rewriting","linkedin","content-generation",{"commitSha":281,"license":238},{"parentExtensionId":697,"repoId":698},"k17bg3ahwtt998cj512cdc040x86m16m","kd7eh8yxvx7bp76mv9rcfdjk0x86m12a",[691,694,693,216,692],{"evaluatedAt":701,"extractAt":702,"updatedAt":701},1778697181923,1778697045058,{"_creationTime":704,"_id":705,"community":706,"display":707,"identity":713,"providers":718,"relations":727,"tags":730,"workflow":731},1778691104675.98,"k17a012kzjtmn6vm9xf7k1q3d986n6me",{"reviewCount":8},{"description":708,"installMethods":709,"name":711,"sourceUrl":712},"Convert a resume PDF to clean markdown for LLM parsing or candidate pipelines.",{"claudeCode":710},"iterationlayer/skills","Convert Resume to Markdown","https://github.com/iterationlayer/skills",{"basePath":714,"githubOwner":715,"githubRepo":716,"locale":18,"slug":717,"type":247},"skills/convert-resume-to-markdown","iterationlayer","skills","convert-resume-to-markdown",{"evaluate":719,"extract":726},{"promptVersionExtension":205,"promptVersionScoring":206,"score":663,"tags":720,"targetMarket":217,"tier":218},[721,722,723,724,725,216],"document-processing","pdf","markdown","resume","hiring",{"commitSha":281,"license":238},{"parentExtensionId":728,"repoId":729},"k1721s0xmp59902ybtpakrrffn86n10s","kd76p4g2qmtrkgx99cnab3683d86n4g8",[721,725,723,216,722,724],{"evaluatedAt":732,"extractAt":733,"updatedAt":732},1778691474825,1778691104676,{"_creationTime":735,"_id":736,"community":737,"display":738,"identity":744,"providers":748,"relations":755,"tags":757,"workflow":758},1778688112811.7285,"k172yp54p26ppvdmmk3t28cm5n86n0m6",{"reviewCount":8},{"description":739,"installMethods":740,"name":742,"sourceUrl":743},"Analyze sentiment in text using ML models. Use when: analyzing customer reviews; processing NPS feedback; monitoring brand mentions; evaluating campaign responses; categorizing support tickets",{"claudeCode":741},"guia-matthieu/clawfu-skills","sentiment-analyzer","https://github.com/guia-matthieu/clawfu-skills",{"basePath":745,"githubOwner":746,"githubRepo":747,"locale":18,"slug":742,"type":247},"skills/analytics/sentiment-analyzer","guia-matthieu","clawfu-skills",{"evaluate":749,"extract":754},{"promptVersionExtension":205,"promptVersionScoring":206,"score":663,"tags":750,"targetMarket":217,"tier":218},[751,216,752,753,619],"sentiment-analysis","text-analysis","python",{"commitSha":281},{"repoId":756},"kd72qvzyvm658ya7pbyh5ey47h86md53",[619,216,753,751,752],{"evaluatedAt":759,"extractAt":760,"updatedAt":759},1778688343958,1778688112811,{"_creationTime":762,"_id":763,"community":764,"display":765,"identity":771,"providers":776,"relations":786,"tags":789,"workflow":790},1778695116697.1929,"k176f565j7tyetjxk9sgbjcqp186ndk5",{"reviewCount":8},{"description":766,"installMethods":767,"name":769,"sourceUrl":770},"LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.",{"claudeCode":768},"Orchestra-Research/AI-Research-SKILLs","LangSmith Observability","https://github.com/Orchestra-Research/AI-Research-SKILLs",{"basePath":772,"githubOwner":773,"githubRepo":774,"locale":18,"slug":775,"type":247},"17-observability/langsmith","Orchestra-Research","AI-Research-SKILLs","langsmith",{"evaluate":777,"extract":785},{"promptVersionExtension":205,"promptVersionScoring":206,"score":778,"tags":779,"targetMarket":217,"tier":218},99,[780,775,781,213,782,783,784,645],"observability","tracing","monitoring","llmops","debugging",{"commitSha":281,"license":238},{"parentExtensionId":787,"repoId":788},"k17155ws9qc0hw7a568bg79sfd86max8","kd70hj1y80mhra5xm5g188j5n586mg18",[784,213,775,783,782,780,645,781],{"evaluatedAt":791,"extractAt":792,"updatedAt":791},1778697046926,1778695116697]