[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-muratcankoylan-context-compression-en":3,"guides-for-muratcankoylan-context-compression":621,"similar-k1752cypc448mke749yjbkc65186mg6f-en":622},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":233,"isFallback":216,"parentExtension":239,"providers":299,"relations":303,"repo":304,"tags":619,"workflow":620},1778694269038.6682,"k1752cypc448mke749yjbkc65186mg6f",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"muratcankoylan/Agent-Skills-for-Context-Engineering","Context Compression","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":214,"workflow":231},1778694410149.4346,"kn71hdvym9vwvxzgv7nzhdkcs186msdd","en",{"checks":20,"evaluatedAt":171,"extensionSummary":172,"features":173,"nonGoals":179,"practices":183,"prerequisites":187,"promptVersionExtension":188,"promptVersionScoring":189,"purpose":190,"rationale":191,"score":192,"summary":193,"tags":194,"targetMarket":201,"tier":202,"useCases":203,"workflow":208},[21,26,29,32,36,39,43,46,50,54,58,61,64,68,72,76,80,84,87,91,94,97,100,103,106,109,113,116,120,124,128,131,135,139,142,145,148,151,154,157,161,165,166,167,168],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of context compression and token usage optimization for long-running agent sessions.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers distinct compression strategies (Anchored Iterative Summarization, Opaque Compression, Regenerative Full Summary) and detailed guidance on choosing between them, going beyond default LLM summarization.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides production-ready strategies and detailed guidance on implementation, evaluation, and integration, covering the complete lifecycle of context compression.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on context compression strategies and related evaluation, without venturing into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's purpose, detailing specific triggers and use cases for context compression.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Precise Purpose","The skill precisely names its artifact (conversation history/codebases) and user intent (compress context, summarize, reduce token usage) with clear triggers and non-goals.",{"category":40,"check":44,"severity":24,"summary":45},"Concise Frontmatter","The frontmatter is concise and clearly outlines the core capability and trigger phrases for context compression.",{"category":47,"check":48,"severity":24,"summary":49},"Documentation","Concise Body","The SKILL.md is well-structured with detailed topics and examples, deferring deeper material to references and avoiding excessive length.",{"category":51,"check":52,"severity":24,"summary":53},"Context","Progressive Disclosure","The skill effectively uses the `references/evaluation-framework.md` file for detailed probe types and scoring rubrics, adhering to progressive disclosure.",{"category":51,"check":55,"severity":56,"summary":57},"Forked exploration","not_applicable","This skill does not involve deep exploration that would require forking context.",{"category":22,"check":59,"severity":24,"summary":60},"Usage examples","The skill provides two clear examples demonstrating debugging session compression and probe response quality, with expected outputs.",{"category":22,"check":62,"severity":24,"summary":63},"Edge cases","The skill documents several critical 'Gotchas' including issues with tool definitions, hallucination, artifact references, early turns, compounded cycles, code vs prose, and probe evaluation.",{"category":65,"check":66,"severity":56,"summary":67},"Code Execution","Tool Fallback","The skill does not appear to rely on external MCP servers or custom tools.",{"category":69,"check":70,"severity":56,"summary":71},"Safety","Halt on unexpected state","The skill focuses on summarization and does not appear to have destructive operations that would require halting on unexpected states.",{"category":73,"check":74,"severity":24,"summary":75},"Portability","Cross-skill coupling","The skill explicitly lists related skills in its 'Integration' section, allowing users to understand dependencies and scope without implicit coupling.",{"category":77,"check":78,"severity":24,"summary":79},"License","License usability","The provided LICENSE file is the MIT license, which is a permissive open-source license.",{"category":81,"check":82,"severity":24,"summary":83},"Maintenance","Commit recency","The last commit was on April 14, 2026, which is within the last 3 months.",{"category":81,"check":85,"severity":56,"summary":86},"Dependency Management","The skill appears to be written in Python pseudocode and does not list external dependencies.",{"category":88,"check":89,"severity":56,"summary":90},"Security","Secret Management","The skill focuses on context summarization and does not appear to handle secrets.",{"category":88,"check":92,"severity":24,"summary":93},"Injection","The skill's focus on summarization and lack of external data loading suggests no injection vulnerabilities.",{"category":88,"check":95,"severity":24,"summary":96},"Transitive Supply-Chain Grenades","The skill does not appear to fetch external content at runtime or use remote pipes.",{"category":88,"check":98,"severity":24,"summary":99},"Sandbox Isolation","The skill's logic is primarily text processing and does not interact with the file system or perform external operations.",{"category":88,"check":101,"severity":24,"summary":102},"Sandbox escape primitives","No detached process spawns or deny-retry loops were detected in the provided code.",{"category":88,"check":104,"severity":24,"summary":105},"Data Exfiltration","The skill does not involve submitting any data, confidential or otherwise, to third parties.",{"category":88,"check":107,"severity":24,"summary":108},"Hidden Text Tricks","Bundled content appears free of hidden-steering tricks and uses clean printable ASCII.",{"category":110,"check":111,"severity":24,"summary":112},"Hooks","Opaque code execution","The provided Python script is plain and readable, with no obfuscation like base64 or runtime fetches.",{"category":73,"check":114,"severity":24,"summary":115},"Structural Assumption","The skill's logic is self-contained and does not make assumptions about user project structure.",{"category":117,"check":118,"severity":24,"summary":119},"Trust","Issues Attention","6 issues opened and 2 closed in the last 90 days, indicating active engagement and a closure rate greater than 50%.",{"category":121,"check":122,"severity":24,"summary":123},"Versioning","Release Management","A meaningful semver (1.2.0) is declared in the SKILL.md frontmatter.",{"category":125,"check":126,"severity":56,"summary":127},"Execution","Pinned dependencies","The skill uses Python pseudocode and does not rely on third-party dependencies.",{"category":33,"check":129,"severity":56,"summary":130},"Dry-run preview","The skill is focused on summarization and does not have state-changing operations.",{"category":132,"check":133,"severity":56,"summary":134},"Protocol","Idempotent retry & timeouts","The skill does not involve remote calls or state-changing operations.",{"category":136,"check":137,"severity":24,"summary":138},"Compliance","GDPR","The skill only processes conversation history and does not operate on personal data.",{"category":136,"check":140,"severity":24,"summary":141},"Target market","The skill's functionality is universal and does not have regional or jurisdictional limitations.",{"category":73,"check":143,"severity":24,"summary":144},"Runtime stability","The skill uses Python pseudocode and standard libraries, making it platform-agnostic.",{"category":47,"check":146,"severity":24,"summary":147},"README","The README provides a good overview of context engineering, the repository's structure, and installation instructions.",{"category":33,"check":149,"severity":56,"summary":150},"Tool surface size","This is a single-skill extension, not a collection of tools.",{"category":40,"check":152,"severity":56,"summary":153},"Overlapping near-synonym tools","This is a single skill, not a collection of tools with potential synonyms.",{"category":47,"check":155,"severity":24,"summary":156},"Phantom features","All advertised features, such as the different compression strategies and evaluation framework, are implemented in the SKILL.md and supporting files.",{"category":158,"check":159,"severity":24,"summary":160},"Install","Installation instruction","The README provides clear instructions for adding the marketplace and installing the plugin, including copy-pasteable commands.",{"category":162,"check":163,"severity":56,"summary":164},"Errors","Actionable error messages","The skill itself does not expose user-facing error paths; error handling would be within the agent framework utilizing the skill.",{"category":125,"check":126,"severity":56,"summary":127},{"category":33,"check":129,"severity":56,"summary":130},{"category":132,"check":133,"severity":56,"summary":134},{"category":136,"check":169,"severity":56,"summary":170},"Telemetry opt-in","The skill does not appear to emit any telemetry.",1778694410033,"This skill offers detailed strategies for context compression in LLM agent systems, including Anchored Iterative Summarization, Opaque Compression, and Regenerative Full Summary. It provides a robust evaluation framework with probe generation and scoring, alongside practical guidance and gotchas for implementation.",[174,175,176,177,178],"Strategies for context compression (Anchored Iterative, Opaque, Regenerative)","Guidance on optimizing tokens-per-task vs. tokens-per-request","Detailed explanation of artifact trail preservation","Methodologies for probe-based evaluation of compression quality","Implementation steps for structured summaries and compression triggers",[180,181,182],"Replacing prompt engineering entirely","Handling context compression for raw code blocks without summarization","Providing a generic text summarization tool outside of agent context engineering",[184,185,186],"Context Engineering","LLM Evaluation","Agent Design Patterns",[],"3.0.0","4.4.0","To provide agents with effective methods for managing and reducing token usage in long-running sessions by intelligently compressing conversation history and evaluating the quality of compression.","All checks passed or were not applicable, indicating high quality and adherence to best practices.",100,"A high-quality skill providing comprehensive strategies for context compression and evaluation.",[195,196,197,198,199,200],"context-engineering","llm","agent","summarization","compression","evaluation","global","verified",[204,205,206,207],"When agent sessions exceed context window limits","Designing conversation summarization strategies","Debugging agents that 'forget' previous information","Optimizing token usage in long-running agent sessions",[209,210,211,212,213],"Identify need for context compression due to session length or token limits.","Select an appropriate compression strategy (Anchored Iterative, Opaque, Regenerative).","Implement the chosen strategy, focusing on structured summaries and appropriate triggers.","Evaluate compression quality using the provided probe-based framework.","Monitor re-fetching frequency as a key quality signal.",{"codeQuality":215,"collectedAt":217,"documentation":218,"maintenance":221,"security":227,"testCoverage":229},{"hasLockfile":216},false,1778694397092,{"descriptionLength":219,"readmeSize":220},293,13763,{"closedIssues90d":222,"forks":223,"hasChangelog":216,"openIssues90d":224,"pushedAt":225,"stars":226},2,1237,6,1776141908000,15630,{"hasNpmPackage":216,"license":228,"smitheryVerified":216},"MIT",{"hasCi":216,"hasTests":230},true,{"updatedAt":232},1778694410149,{"basePath":234,"githubOwner":235,"githubRepo":236,"locale":18,"slug":237,"type":238},"skills/context-compression","muratcankoylan","Agent-Skills-for-Context-Engineering","context-compression","skill",{"_creationTime":240,"_id":241,"community":242,"display":243,"identity":247,"parentExtension":250,"providers":282,"relations":295,"tags":296,"workflow":297},1778694269038.6665,"k1754dy3wbsv2a5gr1a983zzs586njca",{"reviewCount":8},{"description":244,"installMethods":245,"name":246,"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":236},"Agent Skills for Context Engineering",{"basePath":248,"githubOwner":235,"githubRepo":236,"locale":18,"slug":236,"type":249},"","plugin",{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":257,"providers":259,"relations":276,"tags":278,"workflow":279},1778694269038.6663,"k1796gc85sm2bx753svn59gp5186mpz4",{"reviewCount":8},{"description":255,"installMethods":256,"name":246,"sourceUrl":14},"Context Engineering skills for building production-grade AI agent systems",{"claudeCode":12},{"basePath":248,"githubOwner":235,"githubRepo":236,"locale":18,"slug":236,"type":258},"marketplace",{"evaluate":260,"extract":269},{"promptVersionExtension":261,"promptVersionScoring":189,"score":262,"tags":263,"targetMarket":201,"tier":268},"3.1.0",75,[264,265,195,196,266,267],"ai","agent-skills","development","architecture","community",{"commitSha":270,"license":228,"marketplace":271,"plugin":274},"HEAD",{"name":272,"pluginCount":273},"context-engineering-marketplace",1,{"mcpCount":8,"provider":275,"skillCount":8},"classify",{"repoId":277},"kd7f12maf5nxmx5xttjx7scfnx86m1tv",[265,264,267,195,266,196],{"evaluatedAt":280,"extractAt":281,"updatedAt":280},1778694283498,1778694269038,{"evaluate":283,"extract":292},{"promptVersionExtension":188,"promptVersionScoring":189,"score":284,"tags":285,"targetMarket":201,"tier":202},95,[195,286,287,288,289,290,291],"ai-agents","prompt-engineering","multi-agent-systems","llm-operations","agent-architecture","cognitive-architecture",{"commitSha":270,"license":228,"plugin":293},{"mcpCount":8,"provider":275,"skillCount":294},14,{"parentExtensionId":252,"repoId":277},[290,286,291,195,289,288,287],{"evaluatedAt":298,"extractAt":281,"updatedAt":298},1778694291902,{"evaluate":300,"extract":302},{"promptVersionExtension":188,"promptVersionScoring":189,"score":192,"tags":301,"targetMarket":201,"tier":202},[195,196,197,198,199,200],{"commitSha":270,"license":228},{"parentExtensionId":241,"repoId":277},{"_creationTime":305,"_id":277,"identity":306,"providers":307,"workflow":615},1778694264629.3296,{"githubOwner":235,"githubRepo":236,"sourceUrl":14},{"classify":308,"discover":609,"github":612},{"commitSha":270,"extensions":309},[310,323,331,358,381,402,416,434,450,459,471,483,495,506,517,529,539,551,563,577,591,599],{"basePath":248,"description":255,"displayName":272,"installMethods":311,"rationale":312,"selectedPaths":313,"source":322,"sourceLanguage":18,"type":258},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[314,317,319],{"path":315,"priority":316},".claude-plugin/marketplace.json","mandatory",{"path":318,"priority":316},"README.md",{"path":320,"priority":321},"LICENSE","high","rule",{"basePath":248,"description":244,"displayName":195,"installMethods":324,"rationale":325,"selectedPaths":326,"source":322,"sourceLanguage":18,"type":249},{"claudeCode":236},"inline plugin source from marketplace.json at / (coalesced with duplicate plugin at .plugin)",[327,328,329],{"path":318,"priority":316},{"path":320,"priority":321},{"path":330,"priority":321},"SKILL.md",{"basePath":332,"description":333,"displayName":334,"installMethods":335,"rationale":336,"selectedPaths":337,"source":322,"sourceLanguage":18,"type":238},"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",[338,339,340,343,345,347,349,352,354,356],{"path":330,"priority":316},{"path":318,"priority":321},{"path":341,"priority":342},"examples/gertrude-stein/README.md","low",{"path":344,"priority":342},"examples/gertrude-stein/dataset_sample.jsonl",{"path":346,"priority":342},"examples/gertrude-stein/sample_outputs.md",{"path":348,"priority":342},"examples/gertrude-stein/training_config.json",{"path":350,"priority":351},"references/segmentation-strategies.md","medium",{"path":353,"priority":351},"references/tinker-format.md",{"path":355,"priority":351},"references/tinker.txt",{"path":357,"priority":342},"scripts/pipeline_example.py",{"basePath":359,"description":360,"displayName":361,"installMethods":362,"rationale":363,"selectedPaths":364,"source":322,"sourceLanguage":18,"type":238},"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",[365,366,367,369,371,373,375,377,379],{"path":330,"priority":316},{"path":318,"priority":321},{"path":368,"priority":351},"AGENT.md",{"path":370,"priority":351},"HOW-SKILLS-BUILT-THIS.md",{"path":372,"priority":351},"SKILLS-MAPPING.md",{"path":374,"priority":342},"examples/content-workflow.md",{"path":376,"priority":342},"examples/meeting-prep.md",{"path":378,"priority":351},"references/file-formats.md",{"path":380,"priority":342},"scripts/install.sh",{"basePath":382,"description":383,"displayName":384,"installMethods":385,"rationale":386,"selectedPaths":387,"source":322,"sourceLanguage":18,"type":238},"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",[388,389,390,392,394,396,398,400],{"path":330,"priority":316},{"path":318,"priority":321},{"path":391,"priority":342},"docs/agentthinking.md",{"path":393,"priority":342},"docs/interleavedthinking.md",{"path":395,"priority":342},"docs/m2-1.md",{"path":397,"priority":342},"examples/01_basic_capture.py",{"path":399,"priority":342},"examples/02_tool_usage.py",{"path":401,"priority":342},"examples/03_full_optimization.py",{"basePath":403,"description":404,"displayName":405,"installMethods":406,"rationale":407,"selectedPaths":408,"source":322,"sourceLanguage":18,"type":238},"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",[409,410,412,414],{"path":330,"priority":316},{"path":411,"priority":351},"references/optimization_summary.json",{"path":413,"priority":351},"references/optimized_prompt.txt",{"path":415,"priority":351},"references/patterns_found.json",{"basePath":417,"description":418,"displayName":419,"installMethods":420,"rationale":421,"selectedPaths":422,"source":322,"sourceLanguage":18,"type":238},"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",[423,424,426,428,430,432],{"path":330,"priority":316},{"path":425,"priority":351},"references/bias-mitigation.md",{"path":427,"priority":351},"references/evaluation-pipeline.md",{"path":429,"priority":351},"references/implementation-patterns.md",{"path":431,"priority":351},"references/metrics-guide.md",{"path":433,"priority":342},"scripts/evaluation_example.py",{"basePath":435,"description":436,"displayName":437,"installMethods":438,"rationale":439,"selectedPaths":440,"source":322,"sourceLanguage":18,"type":238},"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",[441,442,444,446,448],{"path":330,"priority":316},{"path":443,"priority":351},"references/bdi-ontology-core.md",{"path":445,"priority":351},"references/framework-integration.md",{"path":447,"priority":351},"references/rdf-examples.md",{"path":449,"priority":351},"references/sparql-competency.md",{"basePath":234,"description":10,"displayName":237,"installMethods":451,"rationale":452,"selectedPaths":453,"source":322,"sourceLanguage":18,"type":238},{"claudeCode":12},"SKILL.md frontmatter at skills/context-compression/SKILL.md",[454,455,457],{"path":330,"priority":316},{"path":456,"priority":351},"references/evaluation-framework.md",{"path":458,"priority":342},"scripts/compression_evaluator.py",{"basePath":460,"description":461,"displayName":462,"installMethods":463,"rationale":464,"selectedPaths":465,"source":322,"sourceLanguage":18,"type":238},"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",[466,467,469],{"path":330,"priority":316},{"path":468,"priority":351},"references/patterns.md",{"path":470,"priority":342},"scripts/degradation_detector.py",{"basePath":472,"description":473,"displayName":474,"installMethods":475,"rationale":476,"selectedPaths":477,"source":322,"sourceLanguage":18,"type":238},"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",[478,479,481],{"path":330,"priority":316},{"path":480,"priority":351},"references/context-components.md",{"path":482,"priority":342},"scripts/context_manager.py",{"basePath":484,"description":485,"displayName":486,"installMethods":487,"rationale":488,"selectedPaths":489,"source":322,"sourceLanguage":18,"type":238},"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",[490,491,493],{"path":330,"priority":316},{"path":492,"priority":351},"references/optimization_techniques.md",{"path":494,"priority":342},"scripts/compaction.py",{"basePath":496,"description":497,"displayName":200,"installMethods":498,"rationale":499,"selectedPaths":500,"source":322,"sourceLanguage":18,"type":238},"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",[501,502,504],{"path":330,"priority":316},{"path":503,"priority":351},"references/metrics.md",{"path":505,"priority":342},"scripts/evaluator.py",{"basePath":507,"description":508,"displayName":509,"installMethods":510,"rationale":511,"selectedPaths":512,"source":322,"sourceLanguage":18,"type":238},"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":330,"priority":316},{"path":429,"priority":351},{"path":516,"priority":342},"scripts/filesystem_context.py",{"basePath":518,"description":519,"displayName":520,"installMethods":521,"rationale":522,"selectedPaths":523,"source":322,"sourceLanguage":18,"type":238},"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":330,"priority":316},{"path":526,"priority":351},"references/infrastructure-patterns.md",{"path":528,"priority":342},"scripts/sandbox_manager.py",{"basePath":530,"description":531,"displayName":532,"installMethods":533,"rationale":534,"selectedPaths":535,"source":322,"sourceLanguage":18,"type":238},"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":330,"priority":316},{"path":538,"priority":351},"references/attention-matching-formulation.md",{"basePath":540,"description":541,"displayName":542,"installMethods":543,"rationale":544,"selectedPaths":545,"source":322,"sourceLanguage":18,"type":238},"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":330,"priority":316},{"path":548,"priority":351},"references/implementation.md",{"path":550,"priority":342},"scripts/memory_store.py",{"basePath":552,"description":553,"displayName":554,"installMethods":555,"rationale":556,"selectedPaths":557,"source":322,"sourceLanguage":18,"type":238},"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":330,"priority":316},{"path":560,"priority":351},"references/frameworks.md",{"path":562,"priority":342},"scripts/coordination.py",{"basePath":564,"description":565,"displayName":566,"installMethods":567,"rationale":568,"selectedPaths":569,"source":322,"sourceLanguage":18,"type":238},"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",[570,571,573,575],{"path":330,"priority":316},{"path":572,"priority":351},"references/case-studies.md",{"path":574,"priority":351},"references/pipeline-patterns.md",{"path":576,"priority":342},"scripts/pipeline_template.py",{"basePath":578,"description":579,"displayName":580,"installMethods":581,"rationale":582,"selectedPaths":583,"source":322,"sourceLanguage":18,"type":238},"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",[584,585,587,589],{"path":330,"priority":316},{"path":586,"priority":351},"references/architectural_reduction.md",{"path":588,"priority":351},"references/best_practices.md",{"path":590,"priority":342},"scripts/description_generator.py",{"basePath":592,"description":593,"displayName":594,"installMethods":595,"rationale":596,"selectedPaths":597,"source":322,"sourceLanguage":18,"type":238},"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",[598],{"path":330,"priority":316},{"basePath":382,"installMethods":600,"rationale":601,"selectedPaths":602,"source":322,"sourceLanguage":18,"type":608},{"pypi":384},"cli ecosystem detected at examples/interleaved-thinking",[603,605,606],{"path":604,"priority":316},"pyproject.toml",{"path":318,"priority":316},{"path":607,"priority":351},"reasoning_trace_optimizer/cli.py","cli",{"sources":610},[611],"manual",{"closedIssues90d":222,"description":613,"forks":223,"license":228,"openIssues90d":224,"pushedAt":225,"readmeSize":220,"stars":226,"topics":614},"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":616,"discoverAt":617,"extractAt":618,"githubAt":618,"updatedAt":616},1778694268713,1778694264629,1778694266904,[197,199,195,200,196,198],{"evaluatedAt":232,"extractAt":281,"updatedAt":232},[],[623,651,679,701,729,758],{"_creationTime":624,"_id":625,"community":626,"display":627,"identity":633,"providers":637,"relations":645,"tags":647,"workflow":648},1778683190010.2527,"k17czrfmwfd11e7bdndnw4wb6s86nbm7",{"reviewCount":8},{"description":628,"installMethods":629,"name":631,"sourceUrl":632},"AI session compression techniques for managing multi-turn conversations efficiently through summarization, embedding-based retrieval, and intelligent context management.",{"claudeCode":630},"bobmatnyc/claude-mpm-skills","session-compression","https://github.com/bobmatnyc/claude-mpm-skills",{"basePath":634,"githubOwner":635,"githubRepo":636,"locale":18,"slug":631,"type":238},"toolchains/ai/techniques/session-compression","bobmatnyc","claude-mpm-skills",{"evaluate":638,"extract":644},{"promptVersionExtension":188,"promptVersionScoring":189,"score":639,"tags":640,"targetMarket":201,"tier":268},91,[264,196,641,199,642,198,643],"conversation","context-management","rag",{"commitSha":270},{"repoId":646},"kd72g55e5qeqs90bk1bvkt8wbx86nkn3",[264,199,642,641,196,643,198],{"evaluatedAt":649,"extractAt":650,"updatedAt":649},1778683389769,1778683190010,{"_creationTime":652,"_id":653,"community":654,"display":655,"identity":661,"providers":665,"relations":672,"tags":675,"workflow":676},1778699234184.6143,"k17cnx0m6a27fw52yvt4zsbsxh86nd1c",{"reviewCount":8},{"description":656,"installMethods":657,"name":659,"sourceUrl":660},"Configure popular MCP servers for enhanced agent capabilities",{"claudeCode":658},"Yeachan-Heo/oh-my-claudecode","mcp-setup","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":662,"githubOwner":663,"githubRepo":664,"locale":18,"slug":659,"type":238},"skills/mcp-setup","Yeachan-Heo","oh-my-claudecode",{"evaluate":666,"extract":671},{"promptVersionExtension":188,"promptVersionScoring":189,"score":192,"tags":667,"targetMarket":201,"tier":202},[668,669,608,197,670],"mcp","configuration","tooling",{"commitSha":270},{"parentExtensionId":673,"repoId":674},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[197,608,669,668,670],{"evaluatedAt":677,"extractAt":678,"updatedAt":677},1778699492025,1778699234184,{"_creationTime":680,"_id":681,"community":682,"display":683,"identity":687,"providers":689,"relations":697,"tags":698,"workflow":699},1778699234184.6133,"k170q6m14w6ah5ygc0jr5sa54986mpx7",{"reviewCount":8},{"description":684,"installMethods":685,"name":686,"sourceUrl":660},"Deep codebase initialization with hierarchical AGENTS.md documentation",{"claudeCode":658},"deepinit",{"basePath":688,"githubOwner":663,"githubRepo":664,"locale":18,"slug":686,"type":238},"skills/deepinit",{"evaluate":690,"extract":696},{"promptVersionExtension":188,"promptVersionScoring":189,"score":192,"tags":691,"targetMarket":201,"tier":202},[692,693,197,694,695],"documentation","codebase","typescript","javascript",{"commitSha":270},{"parentExtensionId":673,"repoId":674},[197,693,692,695,694],{"evaluatedAt":700,"extractAt":678,"updatedAt":700},1778699437749,{"_creationTime":702,"_id":703,"community":704,"display":705,"identity":711,"providers":715,"relations":723,"tags":725,"workflow":726},1778696691708.297,"k174kx68t1r1znb9ws0ndvkpt586nx68",{"reviewCount":8},{"description":706,"installMethods":707,"name":709,"sourceUrl":710},"Agent skill for worker-specialist - invoke with $agent-worker-specialist",{"claudeCode":708},"ruvnet/ruflo","agent-worker-specialist","https://github.com/ruvnet/ruflo",{"basePath":712,"githubOwner":713,"githubRepo":714,"locale":18,"slug":709,"type":238},".agents/skills/agent-worker-specialist","ruvnet","ruflo",{"evaluate":716,"extract":722},{"promptVersionExtension":188,"promptVersionScoring":189,"score":192,"tags":717,"targetMarket":201,"tier":202},[197,718,719,720,721],"orchestration","task-execution","coordination","progress-reporting",{"commitSha":270},{"repoId":724},"kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[197,720,718,721,719],{"evaluatedAt":727,"extractAt":728,"updatedAt":727},1778698724168,1778696691708,{"_creationTime":730,"_id":731,"community":732,"display":733,"identity":739,"providers":743,"relations":751,"tags":754,"workflow":755},1778696595410.5657,"k17bk9m02r7jkbzzqapbzfvq8h86m6qn",{"reviewCount":8},{"description":734,"installMethods":735,"name":737,"sourceUrl":738},"Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.",{"claudeCode":736},"rohitg00/pro-workflow","orchestrate","https://github.com/rohitg00/pro-workflow",{"basePath":740,"githubOwner":741,"githubRepo":742,"locale":18,"slug":737,"type":238},"skills/orchestrate","rohitg00","pro-workflow",{"evaluate":744,"extract":750},{"promptVersionExtension":188,"promptVersionScoring":189,"score":192,"tags":745,"targetMarket":201,"tier":202},[746,197,747,748,749],"llm-ops","workflow","memory","knowledge-management",{"commitSha":270},{"parentExtensionId":752,"repoId":753},"k17fxtjcfh5gvxdrhv2dmgn1t986mdhv","kd7am4e918eq98hrd9s31jm4vs86nn0b",[197,749,746,748,747],{"evaluatedAt":756,"extractAt":757,"updatedAt":756},1778696881233,1778696595410,{"_creationTime":759,"_id":760,"community":761,"display":762,"identity":768,"providers":772,"relations":779,"tags":782,"workflow":783},1778683790179.7805,"k175gdavh4ddb920rs1v4jc92586n0ke",{"reviewCount":8},{"description":763,"installMethods":764,"name":766,"sourceUrl":767},"Initializes an optional repo-local agent collaboration preference file at `.ai/swe.json` by running a short interview or a zero-question quick mode. Use when a user says `initialize agent settings for this repo`, `set up my local agent prefs here`, `run quick init for this project`, or `create .ai/swe.json for how I like to work`. Do NOT use for `npm init`, project scaffolding, dependency installation, or environment bootstrap.",{"claudeCode":765},"ckorhonen/swe-skills","init","https://github.com/ckorhonen/swe-skills",{"basePath":769,"githubOwner":770,"githubRepo":771,"locale":18,"slug":766,"type":238},"skills/init","ckorhonen","swe-skills",{"evaluate":773,"extract":778},{"promptVersionExtension":188,"promptVersionScoring":189,"score":192,"tags":774,"targetMarket":201,"tier":202},[669,775,197,776,777],"preferences","local","developer-tools",{"commitSha":270},{"parentExtensionId":780,"repoId":781},"k17d2yq229g61qvea0x8t60w1h86mgr8","kd7b5kvzw3q7dgvym5bdx3m53986mann",[197,669,777,776,775],{"evaluatedAt":784,"extractAt":785,"updatedAt":784},1778683991127,1778683790179]