[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-muratcankoylan-project-development-en":3,"guides-for-muratcankoylan-project-development":618,"similar-k178ghjhvwyw1pv6vxnaqcwgyx86m2g7-en":619},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":228,"isFallback":211,"parentExtension":234,"providers":295,"relations":299,"repo":300,"tags":616,"workflow":617},1778694269038.6707,"k178ghjhvwyw1pv6vxnaqcwgyx86m2g7",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"muratcankoylan/Agent-Skills-for-Context-Engineering","Project Development","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":209,"workflow":226},1778694576171.7542,"kn7dxpe99syqxm29v1g5cr5t5586mp3b","en",{"checks":20,"evaluatedAt":165,"extensionSummary":166,"features":167,"nonGoals":174,"practices":178,"prerequisites":183,"promptVersionExtension":184,"promptVersionScoring":185,"purpose":186,"rationale":187,"score":188,"summary":189,"tags":190,"targetMarket":196,"tier":197,"useCases":198,"workflow":203},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,79,82,85,88,91,94,98,101,105,109,113,116,119,122,126,129,132,135,138,141,144,148,152,155,158,162],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the skill should be used for specific LLM project development tasks like starting projects, designing pipelines, and evaluating task-model fit, directly addressing user needs.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a structured methodology and concrete patterns (pipeline architecture, file system state, structured output design) that go beyond generic LLM advice, providing unique value for building LLM projects.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle guide, from task analysis to cost estimation and development planning, with detailed patterns and examples, 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 methodology and architecture for developing LLM projects, including pipeline design and task evaluation, without straying into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's purpose and trigger phrases, matching the detailed content of the SKILL.md.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The skill clearly defines its purpose for LLM project development, names specific artifacts (pipelines, LLM tasks), and provides explicit trigger phrases and boundaries ('When to Activate' and 'Gotchas').",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter in SKILL.md is concise, self-contained, and effectively summarizes the core capability with relevant trigger phrases.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md body is well-structured, under 500 lines, and delegates deeper material to referenced files, adhering to progressive disclosure.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The skill utilizes relative paths to link to detailed documentation in `references/` files (e.g., `pipeline-patterns.md`, `case-studies.md`), allowing for progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","This skill provides guidance and methodologies rather than performing deep exploration or code review, so `context: fork` is not applicable.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The skill includes detailed, end-to-end examples of batch analysis pipelines and architectural reduction, demonstrating practical application and plausible outcomes.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The 'Gotchas' section explicitly documents common failure modes (skipping validation, monolithic pipelines, over-constraining models, ignoring costs) with recovery steps and observable symptoms.",{"category":65,"check":66,"severity":24,"summary":67},"Code Execution","Halt on unexpected state","The skill's methodology emphasizes structured pipelines and file system state, implicitly promoting halting on unexpected states, and the 'Gotchas' section warns against proceeding without validation.",{"category":69,"check":70,"severity":24,"summary":71},"Portability","Cross-skill coupling","The skill is self-contained, focusing on LLM project development methodology. It explicitly cross-references related skills ('See `multi-agent-patterns` skill') rather than implicitly relying on them.",{"category":73,"check":74,"severity":56,"summary":75},"Security","Secret Management","This skill is purely guidance and documentation; it does not handle or use secrets.",{"category":73,"check":77,"severity":56,"summary":78},"Injection","The skill does not load or execute external data or files, making injection vulnerabilities not applicable.",{"category":73,"check":80,"severity":56,"summary":81},"Transitive Supply-Chain Grenades","The skill does not fetch remote content or execute external scripts at runtime.",{"category":73,"check":83,"severity":56,"summary":84},"Sandbox Isolation","As a guidance skill, it does not perform file system operations or execute code that could impact sandbox isolation.",{"category":73,"check":86,"severity":56,"summary":87},"Sandbox escape primitives","The skill does not involve code execution that could lead to sandbox escape.",{"category":73,"check":89,"severity":56,"summary":90},"Data Exfiltration","The skill does not involve reading or submitting confidential data.",{"category":73,"check":92,"severity":24,"summary":93},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks, and descriptions are clean printable ASCII.",{"category":95,"check":96,"severity":56,"summary":97},"Hooks","Opaque code execution","There is no opaque code execution; the provided scripts are plain Python.",{"category":69,"check":99,"severity":24,"summary":100},"Structural Assumption","The skill promotes standard file system structures and uses relative paths or clear placeholders, avoiding assumptions about user-specific project layouts.",{"category":102,"check":103,"severity":24,"summary":104},"Trust","Issues Attention","The repository has 6 open issues and 2 closed issues in the last 90 days, indicating active engagement and a positive closure rate relative to new issues.",{"category":106,"check":107,"severity":24,"summary":108},"Versioning","Release Management","The skill metadata declares a meaningful semver version (1.1.0) in the SKILL.md frontmatter.",{"category":110,"check":111,"severity":56,"summary":112},"Execution","Validation","The skill is guidance-based and does not execute code or handle structured input/output that requires schema validation.",{"category":73,"check":114,"severity":56,"summary":115},"Unguarded Destructive Operations","The skill provides guidance only and does not contain destructive operations.",{"category":65,"check":117,"severity":56,"summary":118},"Error Handling","This skill is documentation-based and does not contain executable code with error paths.",{"category":65,"check":120,"severity":56,"summary":121},"Logging","The skill is documentation-based and does not perform actions that require logging.",{"category":123,"check":124,"severity":56,"summary":125},"Compliance","GDPR","The skill does not operate on data that could include personal information.",{"category":123,"check":127,"severity":24,"summary":128},"Target market","The skill provides general development methodologies and patterns applicable globally, with no regional or jurisdictional logic detected.",{"category":69,"check":130,"severity":56,"summary":131},"Runtime stability","The skill is documentation-based and does not make assumptions about specific runtimes, shells, or operating systems.",{"category":47,"check":133,"severity":24,"summary":134},"README","The README file exists, is comprehensive, and clearly outlines the repository's purpose and contents, including installation and usage instructions.",{"category":33,"check":136,"severity":56,"summary":137},"Tool surface size","This is a single skill extension, not a toolset.",{"category":40,"check":139,"severity":56,"summary":140},"Overlapping near-synonym tools","This is a single skill extension and does not expose multiple tools.",{"category":47,"check":142,"severity":24,"summary":143},"Phantom features","All features described in the README and SKILL.md correspond to implemented guidance and patterns within the skill's documentation.",{"category":145,"check":146,"severity":24,"summary":147},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for Claude Code and other platforms, along with usage examples.",{"category":149,"check":150,"severity":56,"summary":151},"Errors","Actionable error messages","As a documentation-based skill, there are no user-facing error paths to evaluate.",{"category":110,"check":153,"severity":56,"summary":154},"Pinned dependencies","The skill is documentation-based and does not include scripts with dependencies.",{"category":33,"check":156,"severity":56,"summary":157},"Dry-run preview","The skill is purely guidance and documentation; it does not have state-changing commands.",{"category":159,"check":160,"severity":56,"summary":161},"Protocol","Idempotent retry & timeouts","The skill does not involve remote calls or state-changing operations requiring retry or timeouts.",{"category":123,"check":163,"severity":56,"summary":164},"Telemetry opt-in","The skill does not emit telemetry.",1778694575801,"This skill provides a detailed methodology for developing LLM projects, covering task-model fit analysis, pipeline architecture, structured output design, cost estimation, and agent-assisted development practices. It includes references to case studies and patterns for building robust and efficient LLM systems.",[168,169,170,171,172,173],"Task-model fit analysis framework","Canonical pipeline architecture patterns","File system state management for pipelines","Structured output design and parsing guidance","Cost estimation formulas and tracking advice","Agent-assisted development practices",[175,176,177],"Providing specific code implementations for LLM models","Acting as a general project management tool outside of LLM development","Detailed tool design or multi-agent orchestration patterns (refer to other skills)",[179,180,181,182],"Task-Model Fit Recognition","Pipeline Architecture Design","Structured Output Design","Agent-Assisted Development",[],"3.0.0","4.4.0","To guide users in effectively starting, structuring, and iterating on LLM projects, ensuring task-model fit, efficient pipeline architecture, and cost-effective development.","All checks passed or were not applicable, indicating a high-quality, well-documented, and production-ready skill.",100,"A comprehensive skill for designing and building LLM projects, offering structured methodologies and practical patterns.",[191,192,193,194,195],"llm","project-management","pipeline-architecture","agent-development","batch-processing","global","verified",[199,200,201,202],"Starting a new project that may benefit from LLMs","Designing batch processing pipelines with structured outputs","Evaluating task suitability for agents versus traditional code","Estimating costs and timelines for LLM-heavy projects",[204,205,206,207,208],"Task Analysis: Define input/output, classify task, set error rate, estimate value.","Manual Validation: Test one example, evaluate quality, identify failure modes, estimate tokens.","Architecture Selection: Choose single/multi-agent, identify tools/data, design storage/caching, plan parallelization.","Cost Estimation: Calculate tokens x price with buffer, estimate development time, identify infrastructure needs.","Development Plan: Implement stage-by-stage, define testing strategy, set iteration milestones, plan deployment.",{"codeQuality":210,"collectedAt":212,"documentation":213,"maintenance":216,"security":222,"testCoverage":224},{"hasLockfile":211},false,1778694559345,{"descriptionLength":214,"readmeSize":215},282,13763,{"closedIssues90d":217,"forks":218,"hasChangelog":211,"openIssues90d":219,"pushedAt":220,"stars":221},2,1237,6,1776141908000,15630,{"hasNpmPackage":211,"license":223,"smitheryVerified":211},"MIT",{"hasCi":211,"hasTests":225},true,{"updatedAt":227},1778694576171,{"basePath":229,"githubOwner":230,"githubRepo":231,"locale":18,"slug":232,"type":233},"skills/project-development","muratcankoylan","Agent-Skills-for-Context-Engineering","project-development","skill",{"_creationTime":235,"_id":236,"community":237,"display":238,"identity":242,"parentExtension":245,"providers":278,"relations":291,"tags":292,"workflow":293},1778694269038.6665,"k1754dy3wbsv2a5gr1a983zzs586njca",{"reviewCount":8},{"description":239,"installMethods":240,"name":241,"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":231},"Agent Skills for Context Engineering",{"basePath":243,"githubOwner":230,"githubRepo":231,"locale":18,"slug":231,"type":244},"","plugin",{"_creationTime":246,"_id":247,"community":248,"display":249,"identity":252,"providers":254,"relations":272,"tags":274,"workflow":275},1778694269038.6663,"k1796gc85sm2bx753svn59gp5186mpz4",{"reviewCount":8},{"description":250,"installMethods":251,"name":241,"sourceUrl":14},"Context Engineering skills for building production-grade AI agent systems",{"claudeCode":12},{"basePath":243,"githubOwner":230,"githubRepo":231,"locale":18,"slug":231,"type":253},"marketplace",{"evaluate":255,"extract":265},{"promptVersionExtension":256,"promptVersionScoring":185,"score":257,"tags":258,"targetMarket":196,"tier":264},"3.1.0",75,[259,260,261,191,262,263],"ai","agent-skills","context-engineering","development","architecture","community",{"commitSha":266,"license":223,"marketplace":267,"plugin":270},"HEAD",{"name":268,"pluginCount":269},"context-engineering-marketplace",1,{"mcpCount":8,"provider":271,"skillCount":8},"classify",{"repoId":273},"kd7f12maf5nxmx5xttjx7scfnx86m1tv",[260,259,263,261,262,191],{"evaluatedAt":276,"extractAt":277,"updatedAt":276},1778694283498,1778694269038,{"evaluate":279,"extract":288},{"promptVersionExtension":184,"promptVersionScoring":185,"score":280,"tags":281,"targetMarket":196,"tier":197},95,[261,282,283,284,285,286,287],"ai-agents","prompt-engineering","multi-agent-systems","llm-operations","agent-architecture","cognitive-architecture",{"commitSha":266,"license":223,"plugin":289},{"mcpCount":8,"provider":271,"skillCount":290},14,{"parentExtensionId":247,"repoId":273},[286,282,287,261,285,284,283],{"evaluatedAt":294,"extractAt":277,"updatedAt":294},1778694291902,{"evaluate":296,"extract":298},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":297,"targetMarket":196,"tier":197},[191,192,193,194,195],{"commitSha":266,"license":223},{"parentExtensionId":236,"repoId":273},{"_creationTime":301,"_id":273,"identity":302,"providers":303,"workflow":612},1778694264629.3296,{"githubOwner":230,"githubRepo":231,"sourceUrl":14},{"classify":304,"discover":606,"github":609},{"commitSha":266,"extensions":305},[306,319,327,354,377,398,412,430,446,458,470,482,494,506,517,529,539,551,563,574,588,596],{"basePath":243,"description":250,"displayName":268,"installMethods":307,"rationale":308,"selectedPaths":309,"source":318,"sourceLanguage":18,"type":253},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[310,313,315],{"path":311,"priority":312},".claude-plugin/marketplace.json","mandatory",{"path":314,"priority":312},"README.md",{"path":316,"priority":317},"LICENSE","high","rule",{"basePath":243,"description":239,"displayName":261,"installMethods":320,"rationale":321,"selectedPaths":322,"source":318,"sourceLanguage":18,"type":244},{"claudeCode":231},"inline plugin source from marketplace.json at / (coalesced with duplicate plugin at .plugin)",[323,324,325],{"path":314,"priority":312},{"path":316,"priority":317},{"path":326,"priority":317},"SKILL.md",{"basePath":328,"description":329,"displayName":330,"installMethods":331,"rationale":332,"selectedPaths":333,"source":318,"sourceLanguage":18,"type":233},"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",[334,335,336,339,341,343,345,348,350,352],{"path":326,"priority":312},{"path":314,"priority":317},{"path":337,"priority":338},"examples/gertrude-stein/README.md","low",{"path":340,"priority":338},"examples/gertrude-stein/dataset_sample.jsonl",{"path":342,"priority":338},"examples/gertrude-stein/sample_outputs.md",{"path":344,"priority":338},"examples/gertrude-stein/training_config.json",{"path":346,"priority":347},"references/segmentation-strategies.md","medium",{"path":349,"priority":347},"references/tinker-format.md",{"path":351,"priority":347},"references/tinker.txt",{"path":353,"priority":338},"scripts/pipeline_example.py",{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":318,"sourceLanguage":18,"type":233},"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",[361,362,363,365,367,369,371,373,375],{"path":326,"priority":312},{"path":314,"priority":317},{"path":364,"priority":347},"AGENT.md",{"path":366,"priority":347},"HOW-SKILLS-BUILT-THIS.md",{"path":368,"priority":347},"SKILLS-MAPPING.md",{"path":370,"priority":338},"examples/content-workflow.md",{"path":372,"priority":338},"examples/meeting-prep.md",{"path":374,"priority":347},"references/file-formats.md",{"path":376,"priority":338},"scripts/install.sh",{"basePath":378,"description":379,"displayName":380,"installMethods":381,"rationale":382,"selectedPaths":383,"source":318,"sourceLanguage":18,"type":233},"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",[384,385,386,388,390,392,394,396],{"path":326,"priority":312},{"path":314,"priority":317},{"path":387,"priority":338},"docs/agentthinking.md",{"path":389,"priority":338},"docs/interleavedthinking.md",{"path":391,"priority":338},"docs/m2-1.md",{"path":393,"priority":338},"examples/01_basic_capture.py",{"path":395,"priority":338},"examples/02_tool_usage.py",{"path":397,"priority":338},"examples/03_full_optimization.py",{"basePath":399,"description":400,"displayName":401,"installMethods":402,"rationale":403,"selectedPaths":404,"source":318,"sourceLanguage":18,"type":233},"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",[405,406,408,410],{"path":326,"priority":312},{"path":407,"priority":347},"references/optimization_summary.json",{"path":409,"priority":347},"references/optimized_prompt.txt",{"path":411,"priority":347},"references/patterns_found.json",{"basePath":413,"description":414,"displayName":415,"installMethods":416,"rationale":417,"selectedPaths":418,"source":318,"sourceLanguage":18,"type":233},"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",[419,420,422,424,426,428],{"path":326,"priority":312},{"path":421,"priority":347},"references/bias-mitigation.md",{"path":423,"priority":347},"references/evaluation-pipeline.md",{"path":425,"priority":347},"references/implementation-patterns.md",{"path":427,"priority":347},"references/metrics-guide.md",{"path":429,"priority":338},"scripts/evaluation_example.py",{"basePath":431,"description":432,"displayName":433,"installMethods":434,"rationale":435,"selectedPaths":436,"source":318,"sourceLanguage":18,"type":233},"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",[437,438,440,442,444],{"path":326,"priority":312},{"path":439,"priority":347},"references/bdi-ontology-core.md",{"path":441,"priority":347},"references/framework-integration.md",{"path":443,"priority":347},"references/rdf-examples.md",{"path":445,"priority":347},"references/sparql-competency.md",{"basePath":447,"description":448,"displayName":449,"installMethods":450,"rationale":451,"selectedPaths":452,"source":318,"sourceLanguage":18,"type":233},"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",[453,454,456],{"path":326,"priority":312},{"path":455,"priority":347},"references/evaluation-framework.md",{"path":457,"priority":338},"scripts/compression_evaluator.py",{"basePath":459,"description":460,"displayName":461,"installMethods":462,"rationale":463,"selectedPaths":464,"source":318,"sourceLanguage":18,"type":233},"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",[465,466,468],{"path":326,"priority":312},{"path":467,"priority":347},"references/patterns.md",{"path":469,"priority":338},"scripts/degradation_detector.py",{"basePath":471,"description":472,"displayName":473,"installMethods":474,"rationale":475,"selectedPaths":476,"source":318,"sourceLanguage":18,"type":233},"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",[477,478,480],{"path":326,"priority":312},{"path":479,"priority":347},"references/context-components.md",{"path":481,"priority":338},"scripts/context_manager.py",{"basePath":483,"description":484,"displayName":485,"installMethods":486,"rationale":487,"selectedPaths":488,"source":318,"sourceLanguage":18,"type":233},"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",[489,490,492],{"path":326,"priority":312},{"path":491,"priority":347},"references/optimization_techniques.md",{"path":493,"priority":338},"scripts/compaction.py",{"basePath":495,"description":496,"displayName":497,"installMethods":498,"rationale":499,"selectedPaths":500,"source":318,"sourceLanguage":18,"type":233},"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.","evaluation",{"claudeCode":12},"SKILL.md frontmatter at skills/evaluation/SKILL.md",[501,502,504],{"path":326,"priority":312},{"path":503,"priority":347},"references/metrics.md",{"path":505,"priority":338},"scripts/evaluator.py",{"basePath":507,"description":508,"displayName":509,"installMethods":510,"rationale":511,"selectedPaths":512,"source":318,"sourceLanguage":18,"type":233},"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",[513,514,515],{"path":326,"priority":312},{"path":425,"priority":347},{"path":516,"priority":338},"scripts/filesystem_context.py",{"basePath":518,"description":519,"displayName":520,"installMethods":521,"rationale":522,"selectedPaths":523,"source":318,"sourceLanguage":18,"type":233},"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",[524,525,527],{"path":326,"priority":312},{"path":526,"priority":347},"references/infrastructure-patterns.md",{"path":528,"priority":338},"scripts/sandbox_manager.py",{"basePath":530,"description":531,"displayName":532,"installMethods":533,"rationale":534,"selectedPaths":535,"source":318,"sourceLanguage":18,"type":233},"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",[536,537],{"path":326,"priority":312},{"path":538,"priority":347},"references/attention-matching-formulation.md",{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":318,"sourceLanguage":18,"type":233},"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",[546,547,549],{"path":326,"priority":312},{"path":548,"priority":347},"references/implementation.md",{"path":550,"priority":338},"scripts/memory_store.py",{"basePath":552,"description":553,"displayName":554,"installMethods":555,"rationale":556,"selectedPaths":557,"source":318,"sourceLanguage":18,"type":233},"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",[558,559,561],{"path":326,"priority":312},{"path":560,"priority":347},"references/frameworks.md",{"path":562,"priority":338},"scripts/coordination.py",{"basePath":229,"description":10,"displayName":232,"installMethods":564,"rationale":565,"selectedPaths":566,"source":318,"sourceLanguage":18,"type":233},{"claudeCode":12},"SKILL.md frontmatter at skills/project-development/SKILL.md",[567,568,570,572],{"path":326,"priority":312},{"path":569,"priority":347},"references/case-studies.md",{"path":571,"priority":347},"references/pipeline-patterns.md",{"path":573,"priority":338},"scripts/pipeline_template.py",{"basePath":575,"description":576,"displayName":577,"installMethods":578,"rationale":579,"selectedPaths":580,"source":318,"sourceLanguage":18,"type":233},"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",[581,582,584,586],{"path":326,"priority":312},{"path":583,"priority":347},"references/architectural_reduction.md",{"path":585,"priority":347},"references/best_practices.md",{"path":587,"priority":338},"scripts/description_generator.py",{"basePath":589,"description":590,"displayName":591,"installMethods":592,"rationale":593,"selectedPaths":594,"source":318,"sourceLanguage":18,"type":233},"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",[595],{"path":326,"priority":312},{"basePath":378,"installMethods":597,"rationale":598,"selectedPaths":599,"source":318,"sourceLanguage":18,"type":605},{"pypi":380},"cli ecosystem detected at examples/interleaved-thinking",[600,602,603],{"path":601,"priority":312},"pyproject.toml",{"path":314,"priority":312},{"path":604,"priority":347},"reasoning_trace_optimizer/cli.py","cli",{"sources":607},[608],"manual",{"closedIssues90d":217,"description":610,"forks":218,"license":223,"openIssues90d":219,"pushedAt":220,"readmeSize":215,"stars":221,"topics":611},"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":613,"discoverAt":614,"extractAt":615,"githubAt":615,"updatedAt":613},1778694268713,1778694264629,1778694266904,[194,195,191,193,192],{"evaluatedAt":227,"extractAt":277,"updatedAt":227},[],[620,648,676,705,738,766],{"_creationTime":621,"_id":622,"community":623,"display":624,"identity":630,"providers":634,"relations":641,"tags":644,"workflow":645},1778694480889.9487,"k17eg219cke0p45yfhh8n2t37986mgm4",{"reviewCount":8},{"description":625,"installMethods":626,"name":628,"sourceUrl":629},"Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration",{"claudeCode":627},"NeoLabHQ/context-engineering-kit","create-command","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":631,"githubOwner":632,"githubRepo":633,"locale":18,"slug":628,"type":233},"plugins/customaize-agent/skills/create-command","NeoLabHQ","context-engineering-kit",{"evaluate":635,"extract":640},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":636,"targetMarket":196,"tier":197},[637,194,283,638,639],"command-creation","mcp","claude-code",{"commitSha":266},{"parentExtensionId":642,"repoId":643},"k173g0c46wghgz5j9gn02wfydn86mkh8","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[194,639,637,638,283],{"evaluatedAt":646,"extractAt":647,"updatedAt":646},1778694773368,1778694480890,{"_creationTime":649,"_id":650,"community":651,"display":652,"identity":658,"providers":662,"relations":669,"tags":672,"workflow":673},1778692846401.1536,"k17f8b769y9swjcqb91vq74zy986n2wf",{"reviewCount":8},{"description":653,"installMethods":654,"name":656,"sourceUrl":657},"Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.",{"claudeCode":655},"mattpocock/skills","write-a-skill","https://github.com/mattpocock/skills",{"basePath":659,"githubOwner":660,"githubRepo":661,"locale":18,"slug":656,"type":233},"skills/productivity/write-a-skill","mattpocock","skills",{"evaluate":663,"extract":668},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":664,"targetMarket":196,"tier":197},[665,194,666,283,667],"skill-creation","documentation","productivity",{"commitSha":266},{"parentExtensionId":670,"repoId":671},"k171mc92f05dc4v6jzgf6bng7d86mr9t","kd70nm2vazehgqc4j28ve6cwv986mv1s",[194,666,667,283,665],{"evaluatedAt":674,"extractAt":675,"updatedAt":674},1778693512400,1778692846401,{"_creationTime":677,"_id":678,"community":679,"display":680,"identity":686,"providers":690,"relations":698,"tags":701,"workflow":702},1778675056600.2441,"k171y80q0m602mftp477895w5s86n54t",{"reviewCount":8},{"description":681,"installMethods":682,"name":684,"sourceUrl":685},"Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.",{"claudeCode":683},"alirezarezvani/claude-skills","extract","https://github.com/alirezarezvani/claude-skills",{"basePath":687,"githubOwner":688,"githubRepo":689,"locale":18,"slug":684,"type":233},"engineering-team/self-improving-agent/skills/extract","alirezarezvani","claude-skills",{"evaluate":691,"extract":697},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":692,"targetMarket":196,"tier":197},[693,194,694,695,696],"skill-extraction","code-generation","knowledge-management","developer-tools",{"commitSha":266},{"parentExtensionId":699,"repoId":700},"k171b5pw3erme9qy3334r4gbv586mzhf","kd7ff9s1w43mfyy1n7hf87816186m6px",[194,694,696,695,693],{"evaluatedAt":703,"extractAt":704,"updatedAt":703},1778682824392,1778675056600,{"_creationTime":706,"_id":707,"community":708,"display":709,"identity":715,"providers":720,"relations":731,"tags":734,"workflow":735},1778696691708.3308,"k17d3c35ws96bb55ry97apwm5n86mqp2",{"reviewCount":8},{"description":710,"installMethods":711,"name":713,"sourceUrl":714},"Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval",{"claudeCode":712},"ruvnet/ruflo","Chat Format","https://github.com/ruvnet/ruflo",{"basePath":716,"githubOwner":717,"githubRepo":718,"locale":18,"slug":719,"type":233},"plugins/ruflo-ruvllm/skills/chat-format","ruvnet","ruflo","chat-format",{"evaluate":721,"extract":730},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":722,"targetMarket":196,"tier":197},[191,723,724,725,726,727,728,729],"prompting","rag","context-retrieval","openai","anthropic","gemini","ollama",{"commitSha":266,"license":223},{"parentExtensionId":732,"repoId":733},"k17ekc0sj70ms9kgkkgr2ypr4s86mz40","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[727,725,728,191,729,726,723,724],{"evaluatedAt":736,"extractAt":737,"updatedAt":736},1778701390930,1778696691708,{"_creationTime":739,"_id":740,"community":741,"display":742,"identity":748,"providers":752,"relations":759,"tags":762,"workflow":763},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":743,"installMethods":744,"name":746,"sourceUrl":747},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":745},"Yeachan-Heo/oh-my-claudecode","oh-my-claudecode","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":749,"githubOwner":750,"githubRepo":746,"locale":18,"slug":751,"type":233},"skills/ask","Yeachan-Heo","ask",{"evaluate":753,"extract":758},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":754,"targetMarket":196,"tier":197},[605,755,191,723,756,757],"automation","code-review","artifact-generation",{"commitSha":266,"license":223},{"parentExtensionId":760,"repoId":761},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[757,755,605,756,191,723],{"evaluatedAt":764,"extractAt":765,"updatedAt":764},1778699303045,1778699234184,{"_creationTime":767,"_id":768,"community":769,"display":770,"identity":776,"providers":781,"relations":789,"tags":792,"workflow":793},1778696595410.5698,"k171sdysmt658g1cdd7hgt8p8h86nms7",{"reviewCount":8},{"description":771,"installMethods":772,"name":774,"sourceUrl":775},"End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying \"wrap up\", \"done for the day\", \"finish coding\", or ending a coding session.",{"claudeCode":773},"rohitg00/pro-workflow","Wrap-Up Ritual","https://github.com/rohitg00/pro-workflow",{"basePath":777,"githubOwner":778,"githubRepo":779,"locale":18,"slug":780,"type":233},"skills/wrap-up","rohitg00","pro-workflow","wrap-up",{"evaluate":782,"extract":788},{"promptVersionExtension":184,"promptVersionScoring":185,"score":188,"tags":783,"targetMarket":196,"tier":197},[784,191,667,785,786,787],"workflow","memory","knowledge-base","code-quality",{"commitSha":266,"license":223},{"parentExtensionId":790,"repoId":791},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[787,786,191,785,667,784],{"evaluatedAt":794,"extractAt":795,"updatedAt":794},1778697164619,1778696595410]