[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-muratcankoylan-digital-brain-skill-de":3,"guides-for-muratcankoylan-digital-brain-skill":583,"similar-k17b7wd19vrarjetttm1ggnx2n86n73r-de":584},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":243,"isFallback":240,"parentExtension":249,"providers":250,"relations":255,"repo":257,"tags":580,"workflow":581},1778694269038.667,"k17b7wd19vrarjetttm1ggnx2n86n73r",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"muratcankoylan/Agent-Skills-for-Context-Engineering","Digital Brain","https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":241},1778694330628.5225,"kn7707c6gd8s77pfv80761x0e586nwfr","en",{"checks":20,"evaluatedAt":177,"extensionSummary":178,"features":179,"nonGoals":185,"practices":189,"prerequisites":194,"promptVersionExtension":196,"promptVersionScoring":197,"purpose":198,"rationale":199,"score":200,"summary":201,"tags":202,"targetMarket":208,"tier":209,"useCases":210,"workflow":215},[21,26,29,32,36,39,43,47,50,53,57,61,65,69,72,75,78,81,84,87,91,95,99,103,107,110,114,118,121,124,127,130,133,136,140,144,147,150,153,157,160,163,166,170,174],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names concrete user problems and intents, such as 'write a post', 'prepare for meeting', and 'track goals', and specifies user profiles like 'founders building in public'.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over basic prompting by providing a structured personal operating system with specialized modules and automation scripts, going beyond a thin wrapper.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for personal knowledge management, including data storage, content creation pipelines, and automation scripts, making it ready for real-world use.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on personal knowledge management and productivity, with distinct modules for identity, content, knowledge, network, and operations, maintaining a coherent domain.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's capabilities, clearly outlines its purpose, and provides specific trigger phrases and use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill uses narrow, verb-noun specialist tools and scripts (e.g., `weekly_review.py`, `stale_contacts.py`) rather than a single generalist tool.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All data file formats and their common fields are documented in `references/file-formats.md`, and module-specific instructions are provided in dedicated markdown files.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","Automation scripts use descriptive verb-noun names like `weekly_review.py` and `content_ideas.py`.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Automation scripts are designed to process specific data and return structured output, avoiding unnecessary data dumps or broad context collection.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT License, as clearly indicated by the bundled LICENSE file and referenced in the README.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on April 14, 2026, which is within the last 90 days, indicating active maintenance.",{"category":58,"check":62,"severity":63,"summary":64},"Dependency Management","not_applicable","The skill does not appear to rely on third-party dependencies that would require explicit management or vulnerability checks.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill operates on user-managed data files and does not appear to handle or require any secrets like API keys or tokens.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill processes data from structured files and scripts; there is no indication of loading untrusted external code or data that could lead to injection vulnerabilities.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill bundles all its code and data locally, with no runtime downloads or external script execution, mitigating supply-chain risks.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within its own directory structure and does not attempt to modify files outside of its project folder or use absolute paths.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls were detected in the provided scripts or instructions.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill operates on local data and does not make outbound calls to submit confidential information; all outbound destinations are documented and internal.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content and descriptions are free of hidden steering tricks, invisible characters, or malicious formatting.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","All bundled scripts are in plain, readable Python or Markdown format, with no obfuscation, base64 payloads, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill makes assumptions about file organization within its own bundle and uses relative paths, not structural assumptions about the user's project layout.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","Of the 6 issues opened in the last 90 days, 2 were closed (closure rate 33%), which is within acceptable parameters, and the total open/closed count is low.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The skill declares a `version: 1.0.0` in its SKILL.md frontmatter and has a CHANGELOG.md present, indicating clear versioning.",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Pinned dependencies","The provided Python scripts include shebangs and Python interpreter declarations, and the README indicates no external dependencies beyond standard Python libraries.",{"category":33,"check":108,"severity":63,"summary":109},"Dry-run preview","The skill operates primarily on local file management and content generation; it does not have state-changing commands or outbound data transmissions that would require a dry-run mode.",{"category":111,"check":112,"severity":63,"summary":113},"Protocol","Idempotent retry & timeouts","The skill primarily manages local files and does not involve remote calls or state-changing operations that would necessitate idempotency or timeouts.",{"category":115,"check":116,"severity":24,"summary":117},"Compliance","GDPR","The skill operates on user-defined personal data within local files; it does not submit this data to third parties or process it without user control.",{"category":115,"check":119,"severity":24,"summary":120},"Target market","The skill is designed for general personal knowledge management and content creation, with no regional or jurisdictional limitations detected; `targetMarket` is global.",{"category":92,"check":122,"severity":24,"summary":123},"Runtime stability","The skill uses standard Python and markdown, making it portable across POSIX systems. It declares its interpreter and has no exotic runtime assumptions.",{"category":44,"check":125,"severity":24,"summary":126},"README","The README file is comprehensive, detailing the skill's purpose, architecture, installation, usage examples, and design principles.",{"category":33,"check":128,"severity":24,"summary":129},"Tool surface size","The skill exposes a manageable set of automation scripts (4) and module instructions, well within the target range.",{"category":40,"check":131,"severity":24,"summary":132},"Overlapping near-synonym tools","The automation scripts have distinct verb-noun names (`weekly_review.py`, `content_ideas.py`, etc.) covering unique functionalities, avoiding synonym overlap.",{"category":44,"check":134,"severity":24,"summary":135},"Phantom features","All advertised features, such as content creation workflows and automation scripts, have corresponding implementations in the provided files.",{"category":137,"check":138,"severity":24,"summary":139},"Install","Installation instruction","The README provides clear installation instructions for both Claude Code skill usage and standalone template setup, along with usage examples.",{"category":141,"check":142,"severity":24,"summary":143},"Errors","Actionable error messages","The provided scripts and documentation imply robust error handling through file format conventions and the use of standard Python practices, with clear documentation for recovery steps.",{"category":40,"check":145,"severity":24,"summary":146},"Precise Purpose","The `SKILL.md` and README clearly define the skill's purpose, target users ('founders', 'creators'), and specific use cases like 'write a post' or 'prepare for meeting'.",{"category":40,"check":148,"severity":24,"summary":149},"Concise Frontmatter","The `SKILL.md` frontmatter is concise and self-contained, clearly stating the core capability and providing specific trigger phrases.",{"category":44,"check":151,"severity":24,"summary":152},"Concise Body","The `SKILL.md` and module instruction files are concise, with bulk material and detailed documentation deferred to `references/` files or data files.",{"category":154,"check":155,"severity":24,"summary":156},"Context","Progressive Disclosure","The skill uses a three-level loading pattern (SKILL.md → MODULE.md → data files) and links to detailed documentation in `references/`.",{"category":154,"check":158,"severity":63,"summary":159},"Forked exploration","The skill is task-oriented and does not involve deep code review or extensive exploration that would necessitate `context: fork`.",{"category":22,"check":161,"severity":24,"summary":162},"Usage examples","The `examples/` directory contains detailed, end-to-end workflows demonstrating concrete inputs, agent processes, and expected outputs.",{"category":22,"check":164,"severity":24,"summary":165},"Edge cases","The documentation outlines file format conventions, ID generation, and suggests append-only data integrity, implicitly handling edge cases like data corruption.",{"category":167,"check":168,"severity":63,"summary":169},"Code Execution","Tool Fallback","The skill does not reference external MCP servers or tools that would require fallback paths; it relies on standard Python and local file operations.",{"category":171,"check":172,"severity":24,"summary":173},"Safety","Halt on unexpected state","The documentation emphasizes append-only data integrity and specific file update protocols, implying a halt or clear error on unexpected state.",{"category":92,"check":175,"severity":24,"summary":176},"Cross-skill coupling","The skill is designed to be self-contained within its modules and does not implicitly rely on other skills being loaded concurrently.",1778694330516,"This skill provides a structured personal operating system for managing digital presence, knowledge, relationships, and goals. It uses a modular, file-based architecture (JSONL, YAML, Markdown) and includes automation scripts for tasks like content creation, meeting preparation, and weekly reviews.",[180,181,182,183,184],"Structured personal knowledge management","Modular architecture for identity, content, network, operations","Append-only data logging for history preservation","Automation scripts for content generation and reviews","Progressive disclosure for optimized context loading",[186,187,188],"Replacing a full project management suite","Handling real-time collaboration features","Managing external application integrations beyond local files",[190,191,192,193],"Context Engineering","Personal Knowledge Management","Append-only Data","Modular Design",[195],"Python 3.x runtime (for automation scripts)","3.0.0","4.4.0","To act as an AI-assisted personal operating system, enabling users to manage their digital brand, content pipeline, knowledge base, network, and productivity tasks with optimized context handling.","High quality across all checks, with one 'not_applicable' for dry-run and tool fallback due to the skill's local file-based nature. Excellent documentation and adherence to context engineering principles.",99,"Exceptional skill for personal knowledge management and content creation, built with robust context engineering principles.",[203,204,205,206,207],"personal-knowledge-management","content-creation","productivity","automation","context-engineering","global","verified",[211,212,213,214],"Writing posts and managing content calendars","Preparing for meetings with contact context","Organizing personal knowledge and bookmarks","Tracking goals and performing weekly reviews",[216,217,218,219,220,221,222],"Load identity module (voice, brand)","Reference past content/ideas","Draft content using templates","Log published content or save idea","Prepare for meetings by gathering contact/interaction data","Execute weekly review script","Update goals and todos",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"security":237,"testCoverage":239},{"hasLockfile":225},false,1778694313787,{"descriptionLength":228,"readmeSize":229},243,13763,{"closedIssues90d":231,"forks":232,"hasChangelog":225,"manifestVersion":233,"openIssues90d":234,"pushedAt":235,"stars":236},2,1237,"1.0.0",6,1776141908000,15630,{"hasNpmPackage":225,"license":238,"smitheryVerified":225},"MIT",{"hasCi":225,"hasTests":240},true,{"updatedAt":242},1778694330628,{"basePath":244,"githubOwner":245,"githubRepo":246,"locale":18,"slug":247,"type":248},"examples/digital-brain-skill","muratcankoylan","Agent-Skills-for-Context-Engineering","digital-brain-skill","skill",null,{"evaluate":251,"extract":253},{"promptVersionExtension":196,"promptVersionScoring":197,"score":200,"tags":252,"targetMarket":208,"tier":209},[203,204,205,206,207],{"commitSha":254,"license":238},"HEAD",{"repoId":256},"kd7f12maf5nxmx5xttjx7scfnx86m1tv",{"_creationTime":258,"_id":256,"identity":259,"providers":260,"workflow":576},1778694264629.3296,{"githubOwner":245,"githubRepo":246,"sourceUrl":14},{"classify":261,"discover":570,"github":573},{"commitSha":254,"extensions":262},[263,280,290,317,338,359,373,391,407,419,431,443,455,467,478,490,500,512,524,538,552,560],{"basePath":264,"description":265,"displayName":266,"installMethods":267,"rationale":268,"selectedPaths":269,"source":278,"sourceLanguage":18,"type":279},"","Context Engineering skills for building production-grade AI agent systems","context-engineering-marketplace",{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[270,273,275],{"path":271,"priority":272},".claude-plugin/marketplace.json","mandatory",{"path":274,"priority":272},"README.md",{"path":276,"priority":277},"LICENSE","high","rule","marketplace",{"basePath":264,"description":281,"displayName":207,"installMethods":282,"rationale":283,"selectedPaths":284,"source":278,"sourceLanguage":18,"type":289},"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},"inline plugin source from marketplace.json at / (coalesced with duplicate plugin at .plugin)",[285,286,287],{"path":274,"priority":272},{"path":276,"priority":277},{"path":288,"priority":277},"SKILL.md","plugin",{"basePath":291,"description":292,"displayName":293,"installMethods":294,"rationale":295,"selectedPaths":296,"source":278,"sourceLanguage":18,"type":248},"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",[297,298,299,302,304,306,308,311,313,315],{"path":288,"priority":272},{"path":274,"priority":277},{"path":300,"priority":301},"examples/gertrude-stein/README.md","low",{"path":303,"priority":301},"examples/gertrude-stein/dataset_sample.jsonl",{"path":305,"priority":301},"examples/gertrude-stein/sample_outputs.md",{"path":307,"priority":301},"examples/gertrude-stein/training_config.json",{"path":309,"priority":310},"references/segmentation-strategies.md","medium",{"path":312,"priority":310},"references/tinker-format.md",{"path":314,"priority":310},"references/tinker.txt",{"path":316,"priority":301},"scripts/pipeline_example.py",{"basePath":244,"description":10,"displayName":318,"installMethods":319,"rationale":320,"selectedPaths":321,"source":278,"sourceLanguage":18,"type":248},"digital-brain",{"claudeCode":12},"SKILL.md frontmatter at examples/digital-brain-skill/SKILL.md",[322,323,324,326,328,330,332,334,336],{"path":288,"priority":272},{"path":274,"priority":277},{"path":325,"priority":310},"AGENT.md",{"path":327,"priority":310},"HOW-SKILLS-BUILT-THIS.md",{"path":329,"priority":310},"SKILLS-MAPPING.md",{"path":331,"priority":301},"examples/content-workflow.md",{"path":333,"priority":301},"examples/meeting-prep.md",{"path":335,"priority":310},"references/file-formats.md",{"path":337,"priority":301},"scripts/install.sh",{"basePath":339,"description":340,"displayName":341,"installMethods":342,"rationale":343,"selectedPaths":344,"source":278,"sourceLanguage":18,"type":248},"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",[345,346,347,349,351,353,355,357],{"path":288,"priority":272},{"path":274,"priority":277},{"path":348,"priority":301},"docs/agentthinking.md",{"path":350,"priority":301},"docs/interleavedthinking.md",{"path":352,"priority":301},"docs/m2-1.md",{"path":354,"priority":301},"examples/01_basic_capture.py",{"path":356,"priority":301},"examples/02_tool_usage.py",{"path":358,"priority":301},"examples/03_full_optimization.py",{"basePath":360,"description":361,"displayName":362,"installMethods":363,"rationale":364,"selectedPaths":365,"source":278,"sourceLanguage":18,"type":248},"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",[366,367,369,371],{"path":288,"priority":272},{"path":368,"priority":310},"references/optimization_summary.json",{"path":370,"priority":310},"references/optimized_prompt.txt",{"path":372,"priority":310},"references/patterns_found.json",{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":278,"sourceLanguage":18,"type":248},"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",[380,381,383,385,387,389],{"path":288,"priority":272},{"path":382,"priority":310},"references/bias-mitigation.md",{"path":384,"priority":310},"references/evaluation-pipeline.md",{"path":386,"priority":310},"references/implementation-patterns.md",{"path":388,"priority":310},"references/metrics-guide.md",{"path":390,"priority":301},"scripts/evaluation_example.py",{"basePath":392,"description":393,"displayName":394,"installMethods":395,"rationale":396,"selectedPaths":397,"source":278,"sourceLanguage":18,"type":248},"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",[398,399,401,403,405],{"path":288,"priority":272},{"path":400,"priority":310},"references/bdi-ontology-core.md",{"path":402,"priority":310},"references/framework-integration.md",{"path":404,"priority":310},"references/rdf-examples.md",{"path":406,"priority":310},"references/sparql-competency.md",{"basePath":408,"description":409,"displayName":410,"installMethods":411,"rationale":412,"selectedPaths":413,"source":278,"sourceLanguage":18,"type":248},"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",[414,415,417],{"path":288,"priority":272},{"path":416,"priority":310},"references/evaluation-framework.md",{"path":418,"priority":301},"scripts/compression_evaluator.py",{"basePath":420,"description":421,"displayName":422,"installMethods":423,"rationale":424,"selectedPaths":425,"source":278,"sourceLanguage":18,"type":248},"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",[426,427,429],{"path":288,"priority":272},{"path":428,"priority":310},"references/patterns.md",{"path":430,"priority":301},"scripts/degradation_detector.py",{"basePath":432,"description":433,"displayName":434,"installMethods":435,"rationale":436,"selectedPaths":437,"source":278,"sourceLanguage":18,"type":248},"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",[438,439,441],{"path":288,"priority":272},{"path":440,"priority":310},"references/context-components.md",{"path":442,"priority":301},"scripts/context_manager.py",{"basePath":444,"description":445,"displayName":446,"installMethods":447,"rationale":448,"selectedPaths":449,"source":278,"sourceLanguage":18,"type":248},"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",[450,451,453],{"path":288,"priority":272},{"path":452,"priority":310},"references/optimization_techniques.md",{"path":454,"priority":301},"scripts/compaction.py",{"basePath":456,"description":457,"displayName":458,"installMethods":459,"rationale":460,"selectedPaths":461,"source":278,"sourceLanguage":18,"type":248},"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",[462,463,465],{"path":288,"priority":272},{"path":464,"priority":310},"references/metrics.md",{"path":466,"priority":301},"scripts/evaluator.py",{"basePath":468,"description":469,"displayName":470,"installMethods":471,"rationale":472,"selectedPaths":473,"source":278,"sourceLanguage":18,"type":248},"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",[474,475,476],{"path":288,"priority":272},{"path":386,"priority":310},{"path":477,"priority":301},"scripts/filesystem_context.py",{"basePath":479,"description":480,"displayName":481,"installMethods":482,"rationale":483,"selectedPaths":484,"source":278,"sourceLanguage":18,"type":248},"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",[485,486,488],{"path":288,"priority":272},{"path":487,"priority":310},"references/infrastructure-patterns.md",{"path":489,"priority":301},"scripts/sandbox_manager.py",{"basePath":491,"description":492,"displayName":493,"installMethods":494,"rationale":495,"selectedPaths":496,"source":278,"sourceLanguage":18,"type":248},"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",[497,498],{"path":288,"priority":272},{"path":499,"priority":310},"references/attention-matching-formulation.md",{"basePath":501,"description":502,"displayName":503,"installMethods":504,"rationale":505,"selectedPaths":506,"source":278,"sourceLanguage":18,"type":248},"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",[507,508,510],{"path":288,"priority":272},{"path":509,"priority":310},"references/implementation.md",{"path":511,"priority":301},"scripts/memory_store.py",{"basePath":513,"description":514,"displayName":515,"installMethods":516,"rationale":517,"selectedPaths":518,"source":278,"sourceLanguage":18,"type":248},"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",[519,520,522],{"path":288,"priority":272},{"path":521,"priority":310},"references/frameworks.md",{"path":523,"priority":301},"scripts/coordination.py",{"basePath":525,"description":526,"displayName":527,"installMethods":528,"rationale":529,"selectedPaths":530,"source":278,"sourceLanguage":18,"type":248},"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",[531,532,534,536],{"path":288,"priority":272},{"path":533,"priority":310},"references/case-studies.md",{"path":535,"priority":310},"references/pipeline-patterns.md",{"path":537,"priority":301},"scripts/pipeline_template.py",{"basePath":539,"description":540,"displayName":541,"installMethods":542,"rationale":543,"selectedPaths":544,"source":278,"sourceLanguage":18,"type":248},"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",[545,546,548,550],{"path":288,"priority":272},{"path":547,"priority":310},"references/architectural_reduction.md",{"path":549,"priority":310},"references/best_practices.md",{"path":551,"priority":301},"scripts/description_generator.py",{"basePath":553,"description":554,"displayName":555,"installMethods":556,"rationale":557,"selectedPaths":558,"source":278,"sourceLanguage":18,"type":248},"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",[559],{"path":288,"priority":272},{"basePath":339,"installMethods":561,"rationale":562,"selectedPaths":563,"source":278,"sourceLanguage":18,"type":569},{"pypi":341},"cli ecosystem detected at examples/interleaved-thinking",[564,566,567],{"path":565,"priority":272},"pyproject.toml",{"path":274,"priority":272},{"path":568,"priority":310},"reasoning_trace_optimizer/cli.py","cli",{"sources":571},[572],"manual",{"closedIssues90d":231,"description":574,"forks":232,"license":238,"openIssues90d":234,"pushedAt":235,"readmeSize":229,"stars":236,"topics":575},"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":577,"discoverAt":578,"extractAt":579,"githubAt":579,"updatedAt":577},1778694268713,1778694264629,1778694266904,[206,204,207,203,205],{"evaluatedAt":242,"extractAt":582,"updatedAt":242},1778694269038,[],[585,614,641,672,694,725],{"_creationTime":586,"_id":587,"community":588,"display":589,"identity":595,"providers":598,"relations":606,"tags":609,"workflow":610},1778699508743.0002,"k17aya9dv3e3bxv473f1f2r52186ndp5",{"reviewCount":8},{"description":590,"installMethods":591,"name":593,"sourceUrl":594},"Erstellen Sie öffentliche Google Docs- oder Google Sheet-Dateien, ohne OAuth zu benötigen. Verwenden Sie diese Fähigkeit, um Google Docs und Sheets zu erstellen und zu bearbeiten, keine Google-Anmeldung erforderlich. Dokumente sind unter teilbaren Links sichtbar. Die Registrierung erfolgt automatisch bei der ersten Verwendung.",{"claudeCode":592},"zagmoai/public-google-drive","public-google-drive","https://github.com/zagmoai/public-google-drive",{"basePath":264,"githubOwner":596,"githubRepo":593,"locale":597,"slug":593,"type":248},"zagmoai","de",{"evaluate":599,"extract":605},{"promptVersionExtension":196,"promptVersionScoring":197,"score":600,"tags":601,"targetMarket":208,"tier":209},100,[602,603,205,206,604],"google-docs","google-sheets","api-client",{"commitSha":254},{"repoId":607,"translatedFrom":608},"kd776ynh73t0d6samn4bnxdf3x86n8mj","k1707pszx7h026a651dp5tvaxd86m3ag",[604,206,602,603,205],{"evaluatedAt":611,"extractAt":612,"updatedAt":613},1778699485884,1778699468747,1778699508743,{"_creationTime":615,"_id":616,"community":617,"display":618,"identity":624,"providers":628,"relations":634,"tags":637,"workflow":638},1778696833339.6218,"k176gr5qszggh36kjn8a1cwehs86n2jd",{"reviewCount":8},{"description":619,"installMethods":620,"name":622,"sourceUrl":623},"Interact with Gmail - search emails, read messages, send emails, create drafts, and manage labels.\nUse when user asks to: search email, read email, send email, create email draft, mark as read,\narchive email, star email, or manage Gmail labels. Lightweight alternative to full Google\nWorkspace MCP server with standalone OAuth authentication.\n",{"claudeCode":621},"sanjay3290/ai-skills","gmail","https://github.com/sanjay3290/ai-skills",{"basePath":625,"githubOwner":626,"githubRepo":627,"locale":18,"slug":622,"type":248},"skills/gmail","sanjay3290","ai-skills",{"evaluate":629,"extract":633},{"promptVersionExtension":196,"promptVersionScoring":197,"score":600,"tags":630,"targetMarket":208,"tier":209},[622,631,632,206,205],"email","communication",{"commitSha":254},{"parentExtensionId":635,"repoId":636},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[206,632,631,622,205],{"evaluatedAt":639,"extractAt":640,"updatedAt":639},1778696939862,1778696833339,{"_creationTime":642,"_id":643,"community":644,"display":645,"identity":651,"providers":656,"relations":665,"tags":668,"workflow":669},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":646,"installMethods":647,"name":649,"sourceUrl":650},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":648},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":652,"githubOwner":653,"githubRepo":654,"locale":18,"slug":655,"type":248},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":657,"extract":664},{"promptVersionExtension":196,"promptVersionScoring":197,"score":600,"tags":658,"targetMarket":208,"tier":209},[659,660,661,662,206,569,663],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":254,"license":238},{"parentExtensionId":666,"repoId":667},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[206,569,663,660,659,662,661],{"evaluatedAt":670,"extractAt":671,"updatedAt":670},1778699613343,1778699234184,{"_creationTime":673,"_id":674,"community":675,"display":676,"identity":679,"providers":682,"relations":690,"tags":691,"workflow":692},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":677,"installMethods":678,"name":654,"sourceUrl":650},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":648},{"basePath":680,"githubOwner":653,"githubRepo":654,"locale":18,"slug":681,"type":248},"skills/ask","ask",{"evaluate":683,"extract":689},{"promptVersionExtension":196,"promptVersionScoring":197,"score":600,"tags":684,"targetMarket":208,"tier":209},[569,206,685,686,687,688],"llm","prompting","code-review","artifact-generation",{"commitSha":254,"license":238},{"parentExtensionId":666,"repoId":667},[688,206,569,687,685,686],{"evaluatedAt":693,"extractAt":671,"updatedAt":693},1778699303045,{"_creationTime":695,"_id":696,"community":697,"display":698,"identity":704,"providers":709,"relations":717,"tags":720,"workflow":721},1778699368519.5344,"k17ab0jk30pqm4zejpk383w4dn86mj8t",{"reviewCount":8},{"description":699,"installMethods":700,"name":702,"sourceUrl":703},"Verwenden Sie dies, wenn die Arbeit von den Live-Browsersitzungs- oder gerenderten Zustand des Benutzers abhängt und nicht von statischen Abrufen, insbesondere für Browser-Debugging-Kontexte oder von DevTools ausgewählte Elemente oder Anfragen, angemeldeten Dashboards oder CMS-Flows, localhost-Apps, Formularen, Uploads, Downloads, Medieninspektion, DOM- oder iframe-Inspektion, Shadow DOM oder Browserfehlern, die wie Soft-404s, Authentifizierungswände, Anti-Bot-Prüfungen oder Ratenbegrenzungen aussehen.",{"claudeCode":701},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":705,"githubOwner":706,"githubRepo":707,"locale":597,"slug":708,"type":248},"skills/use-my-browser","xixu-me","skills","use-my-browser",{"evaluate":710,"extract":716},{"promptVersionExtension":196,"promptVersionScoring":197,"score":600,"tags":711,"targetMarket":208,"tier":209},[712,713,206,714,715],"browser","debugging","ux","developer-tools",{"commitSha":254,"license":238},{"repoId":718,"translatedFrom":719},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[206,712,713,715,714],{"evaluatedAt":722,"extractAt":723,"updatedAt":724},1778699261239,1778699106670,1778699368519,{"_creationTime":726,"_id":727,"community":728,"display":729,"identity":735,"providers":738,"relations":748,"tags":752,"workflow":753},1778699276507.4565,"k17f878eas78tqr9j5r4r9vrsn86m495",{"reviewCount":8},{"description":730,"installMethods":731,"name":733,"sourceUrl":734},"Verwenden Sie dies, wenn der Benutzer X (Twitter)-Daten oder durch Bestätigung gesicherte X-Aktionen über Xquik benötigt: Tweet-Suche, Benutzer-Lookup, Follower-Extraktion, Mediendownload, Überwachung, Webhooks, MCP, SDKs, Posting, Likes, DMs und Profilaktualisierungen. Erfordert einen Xquik API-Schlüssel. Fordern Sie niemals X-Login-Materialien an.",{"claudeCode":732},"Xquik-dev/x-twitter-scraper","x-twitter-scraper","https://github.com/Xquik-dev/x-twitter-scraper",{"basePath":736,"githubOwner":737,"githubRepo":733,"locale":597,"slug":733,"type":248},"skills/x-twitter-scraper","Xquik-dev",{"evaluate":739,"extract":747},{"promptVersionExtension":196,"promptVersionScoring":197,"score":600,"tags":740,"targetMarket":208,"tier":209},[741,742,743,744,206,745,746],"twitter","x","api","data-retrieval","mcp","sdk",{"commitSha":254},{"parentExtensionId":749,"repoId":750,"translatedFrom":751},"k17axvhmvwp90strpqcd5b0h7986m80d","kd783enpnwhry153ka0z65ear186mjbh","k172e8vt4zcz50bb0vfp6ptb1n86mf90",[743,206,744,745,746,741,742],{"evaluatedAt":754,"extractAt":755,"updatedAt":756},1778699230863,1778699170774,1778699276507]