[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-cloud-context-engineering-workflow":3,"mdc-opk2yf-key":35,"related-org-google-cloud-context-engineering-workflow":1335,"related-repo-google-cloud-context-engineering-workflow":1520},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":24,"repoUrl":25,"updatedAt":26,"license":27,"forks":28,"topics":29,"repo":30,"sourceUrl":33,"mdContent":34},"context-engineering-workflow","optimize context sets for Gemini data agents","Context engineering for Gemini Data Analytics API's data agent developer platform tools. Generates, evaluates, and iteratively optimizes a ContextSet (Templates, Facets, Value Searches) to maximize Natural-Language-to-SQL translation accuracy. Use this skill to run the automated setup, NL-SQL pair evaluation dataset generation and expansion, bootstrapping, scoring, and optimization pipeline. For manual authoring standards and schema syntax rules, see the context-generation-guide skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"google-cloud","Google Cloud","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-cloud.png","GoogleCloudPlatform",[13,17,20,23],{"name":14,"slug":15,"type":16},"Agent Context","agent-context","tag",{"name":18,"slug":19,"type":16},"Data Analysis","data-analysis",{"name":21,"slug":22,"type":16},"Gemini","gemini",{"name":9,"slug":8,"type":16},34,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fdb-context-enrichment","2026-07-18T05:13:44.430929",null,11,[],{"repoUrl":25,"stars":24,"forks":28,"topics":31,"description":32},[],"A context engineering agent designed to generate, manage, and optimize structured context sets from your database schemas. It bridges the gap between Large Language Models (LLMs) and databases by compiling, evaluating, and maintaining the precise operational context needed for highly accurate natural language-to-SQL query generation.","https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fdb-context-enrichment\u002Ftree\u002FHEAD\u002Fplugin\u002Fskills\u002Fcontext-engineering-workflow","---\nname: context-engineering-workflow\ndescription: Context engineering for Gemini Data Analytics API's data agent developer platform tools. Generates, evaluates, and iteratively optimizes a ContextSet (Templates, Facets, Value Searches) to maximize Natural-Language-to-SQL translation accuracy. Use this skill to run the automated setup, NL-SQL pair evaluation dataset generation and expansion, bootstrapping, scoring, and optimization pipeline. For manual authoring standards and schema syntax rules, see the context-generation-guide skill.\n---\n\n# Skill: Context Engineering Orchestrator\n\nYou are an expert context engineering agent. Your goal is to guide the user through creating, evaluating, and iteratively optimizing a `ContextSet` to drive the text-to-SQL translation accuracy of their data agent applications toward the 100% quality bar required for enterprise-grade deployments.\n\nRefer to [context-generation-guide\u002FSKILL.md](..\u002Fcontext-generation-guide\u002FSKILL.md) for how to edit a ContextSet.\n\n---\n\n## The Optimization Lifecycle & Phase Flow\n\nTo build high-performing data applications, context engineers typically follow a systematic, iterative optimization lifecycle (Hill-Climbing). \n\n```mermaid\nflowchart TD\n    Start([Start]) --> Setup[Setup & Connection\nScaffolds workspace & connections]\n    Setup --> Prep{Has Golden Dataset?}\n    \n    Prep -- No --> DatasetPrep[Dataset Prep & Expansion\nBuilds reference ground-truth]\n    DatasetPrep --> Bootstrap[Baseline Context Bootstrapping\nGenerates initial context from schema]\n    Prep -- Yes --> Bootstrap\n    \n    Bootstrap --> Evaluate[Evaluation Scoring\nScores context using Evalbench]\n    Evaluate --> Loop{Tuning Target Met?}\n    \n    Loop -- No --> Hillclimb[Optimization & Hill-Climbing\nGap Analysis & Context Mutation]\n    Hillclimb --> Evaluate\n    \n    Loop -- Yes --> End([End - Context Deployed!])\n```\n\n---\n\n## Workflow Phases, Rationales & Entry Prerequisites\n\n---\n\n### Setup & Connection Configuration Phase\n*   **Reference**: [context-engineering-init](..\u002Fcontext-engineering-init\u002FSKILL.md)\n*   **Goal**: Scaffold the local `autoctx\u002F` workspace and establish verified database connections.\n*   **Rationale**: Readonly-database access is an input for evaluation dataset prep and expand, baseline context bootstrapping, \n*   **Entry Prerequisites**:\n    *   *None*.\n\n---\n\n### Evaluation Dataset Prep & Expansion Phase\n*   **Reference**: [context-engineering-dataset-generation](..\u002Fcontext-engineering-dataset-generation\u002FSKILL.md)\n*   **Mandatory Deliverables**: `evalset_environment_inputs.md`, `evalset_gen_plan.md`, `evalset_report_pair_level.md`, and `evalset_report_dataset_level.md`.\n*   **Mandatory Action**: You MUST read the reference file above before starting this phase and you MUST read any files referenced within it to understand the dataset generation process.\n*   **Goal**: Build a high-quality \"golden\" ground-truth dataset and associated audit reports.\n*   **Rationale**: A representative ground-truth dataset and formal audit trails are required to objectively measure and verify translation accuracy improvements.\n*   **Entry Prerequisites**:\n    *   [ ] **Workspace Configured**: The Setup & Connection Configuration phase has been completed, meaning `autoctx\u002Ftools.yaml` is active.\n\n---\n\n### Baseline Context Bootstrapping Phase\n*   **Reference**: [context-engineering-bootstrap](..\u002Fcontext-engineering-bootstrap\u002FSKILL.md)\n*   **Goal**: Deduce query concepts and generate a baseline `ContextSet` (templates, facets, value searches) directly from database schemas and metadata.\n*   **Rationale**: Establishes the baseline context set as the starting point for optimization.\n*   **Entry Prerequisites**:\n    *   [ ] **Workspace Configured**: The Setup & Connection Configuration phase has been completed, meaning `autoctx\u002Ftools.yaml` is active.\n\n---\n\n### Run Evaluation And Score\n*   **Reference**: [context-engineering-evaluate](..\u002Fcontext-engineering-evaluate\u002FSKILL.md)\n*   **Goal**: Run a structured Evalbench evaluation to score the accuracy of a specific context set and identify exact query failures.\n*   **Rationale**: Quantitatively measures context effectiveness, identifying precise query failures.\n*   **Entry Prerequisites**:\n    *   [ ] **Workspace Configured**: The Setup & Connection Configuration phase has been completed, meaning `autoctx\u002Ftools.yaml` is active.\n    *   [ ] **Context Set Available**: A local context set JSON file is available on disk (either the baseline from the Baseline Bootstrapping phase, or a path to a user-supplied custom context set).\n    *   [ ] **Golden Dataset Available**: A local golden evaluation dataset JSON file is available on disk (either from the Evaluation Dataset Prep phase, or a path to a user-supplied custom dataset).\n    *   [ ] **GCP Context ID Provided**: The user has provided their GCP console `context_set_id` representing the uploaded context set.\n\n---\n\n### Optimization & Hill-Climbing Phase\n*   **Reference**: [context-engineering-hillclimb](..\u002Fcontext-engineering-hillclimb\u002FSKILL.md)\n*   **Goal**: Analyze evaluation failures to perform a Gap Analysis and apply targeted context mutations to iteratively improve performance.\n*   **Rationale**: Closes the loop by analyzing failures to generate targeted optimizations.\n*   **Entry Prerequisites**:\n    *   [ ] **Evaluation Completed**: The Evaluation Scoring phase has been executed; the active experiment folder contains an `eval_reports\u002F` directory with at least one completed evaluation run (containing `scores.csv` and `summary.csv`).\n    *   [ ] **Base Context Available**: The base context set file that was evaluated in the target run is available on disk.\n\n---\n\n## Workspace Folder Structure & Evolution\n\nThe Autoctx workflows generate and interact with a structured workspace to maintain state and trace progress across iterations. \n\n### Workspace Folder Layout\n*   `autoctx\u002F`: The dedicated workspace directory.\n    *   `tools.yaml`: Configuration file for the Toolbox MCP Server.\n    *   `state.md`: Summary of the experiment state, active experiment, and run history.\n    *   `experiments\u002F`: Root directory for all experiments.\n        *   `\u003Cexperiment_name>\u002F`: Specific experiment directory.\n            *   `bootstrap_context.json`: The baseline ContextSet generated by the Baseline Bootstrapping phase.\n            *   `eval_configs\u002F`: Directory containing Evalbench configurations.\n            *   `eval_reports\u002F`: Directory containing evaluation output runs.\n            *   `hillclimb\u002F`: Directory containing hill-climbing iteration artifacts.\n                *   `gap_analysis_vN.md`: Analysis of missing contexts at iteration `N`.\n                *   `improved_context_vN.json`: The mutated ContextSet at iteration `N`.\n\n### Workspace Evolution Lifecycle\n1.  **Post-Initialization**: `tools.yaml`, `state.md`, and an empty `experiments\u002F` directory appear in `autoctx\u002F` after the Setup & Connection Configuration phase.\n2.  **Post-Bootstrap**: `autoctx\u002Fexperiments\u002F\u003Cexperiment_name>\u002Fbootstrap_context.json` is generated by the Baseline Bootstrapping phase.\n3.  **Post-Evaluation**: `eval_configs\u002F` and `eval_reports\u002F` appear inside the experiment folder after the Evaluation Scoring phase.\n4.  **Post-Hill-Climbing**: `hillclimb\u002F` appears with `gap_analysis_vN.md` and `improved_context_vN.json` after the Optimization & Hill-Climbing phase, and `state.md` is updated.\n5.  **Tuning Loop**: Iteratively evaluates `improved_context_vN.json` and generates `improved_context_v(N+1).json` until target accuracy is achieved.\n\n## Safety & Protocol\n\n*   **Missing Dataset**:\n    *   If the user's request requires **evaluating, scoring, or optimizing** a context set (e.g., running evaluations, tuning, or hill-climbing):\n        *   Validate if an evaluation dataset exists.\n        *   **Mandatory Halt & Guide**: If no evaluation dataset exists, you are **strictly forbidden** from executing any context bootstrapping, tuning, or evaluation operations in this turn. You must immediately halt, stop calling tools, and yield the turn. Explain **why a golden evaluation dataset is critical** for context engineering (i.e., you cannot objectively score, validate, or hill-climb translation accuracy without a ground-truth dataset), and ask if they would like help generating one first.\n\n*   **Critical API Error Protocol**:\n    *   Seek guidance from the user if you run into results where retrying is unlikely to solve the issue.\n    *   Examples:`503` or `429` error, `UNAVAILABLE` or `RESOURCE_EXHAUSTED` status code.\n    *   Why: These errors are often associated with quota issues, and retrying the request immediately will not resolve the issue. For issues related to Vertex AI Resource Exhaustion, retrying at a later time is often the only solution.\n\n*   **Skill Prerequisites & Troubleshooting**:\n    *   If you encounter any environmental, connection, or execution errors, verify that all preconditions are met. Types of preconditions:\n        *   *Google Cloud Service APIs enablement*\n        *   *IAM Roles & Access*\n        *   *Database Instance Permissions*\n        *   *Development Environment*: Application Default Credentials (ADC) and Python package manager (`uv`) ",{"data":36,"body":37},{"name":4,"description":6},{"type":38,"children":39},"root",[40,49,64,78,82,89,94,283,286,292,295,302,376,379,385,510,513,519,592,595,601,720,723,729,830,833,839,844,850,997,1003,1143,1149,1329],{"type":41,"tag":42,"props":43,"children":45},"element","h1",{"id":44},"skill-context-engineering-orchestrator",[46],{"type":47,"value":48},"text","Skill: Context Engineering Orchestrator",{"type":41,"tag":50,"props":51,"children":52},"p",{},[53,55,62],{"type":47,"value":54},"You are an expert context engineering agent. Your goal is to guide the user through creating, evaluating, and iteratively optimizing a ",{"type":41,"tag":56,"props":57,"children":59},"code",{"className":58},[],[60],{"type":47,"value":61},"ContextSet",{"type":47,"value":63}," to drive the text-to-SQL translation accuracy of their data agent applications toward the 100% quality bar required for enterprise-grade deployments.",{"type":41,"tag":50,"props":65,"children":66},{},[67,69,76],{"type":47,"value":68},"Refer to ",{"type":41,"tag":70,"props":71,"children":73},"a",{"href":72},"..\u002Fcontext-generation-guide\u002FSKILL.md",[74],{"type":47,"value":75},"context-generation-guide\u002FSKILL.md",{"type":47,"value":77}," for how to edit a ContextSet.",{"type":41,"tag":79,"props":80,"children":81},"hr",{},[],{"type":41,"tag":83,"props":84,"children":86},"h2",{"id":85},"the-optimization-lifecycle-phase-flow",[87],{"type":47,"value":88},"The Optimization Lifecycle & Phase Flow",{"type":41,"tag":50,"props":90,"children":91},{},[92],{"type":47,"value":93},"To build high-performing data applications, context engineers typically follow a systematic, iterative optimization lifecycle (Hill-Climbing).",{"type":41,"tag":95,"props":96,"children":101},"pre",{"className":97,"code":98,"language":99,"meta":100,"style":100},"language-mermaid shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","flowchart TD\n    Start([Start]) --> Setup[Setup & Connection\nScaffolds workspace & connections]\n    Setup --> Prep{Has Golden Dataset?}\n    \n    Prep -- No --> DatasetPrep[Dataset Prep & Expansion\nBuilds reference ground-truth]\n    DatasetPrep --> Bootstrap[Baseline Context Bootstrapping\nGenerates initial context from schema]\n    Prep -- Yes --> Bootstrap\n    \n    Bootstrap --> Evaluate[Evaluation Scoring\nScores context using Evalbench]\n    Evaluate --> Loop{Tuning Target Met?}\n    \n    Loop -- No --> Hillclimb[Optimization & Hill-Climbing\nGap Analysis & Context Mutation]\n    Hillclimb --> Evaluate\n    \n    Loop -- Yes --> End([End - Context Deployed!])\n","mermaid","",[102],{"type":41,"tag":56,"props":103,"children":104},{"__ignoreMap":100},[105,116,125,134,143,152,161,170,179,188,197,204,213,222,231,239,248,257,266,274],{"type":41,"tag":106,"props":107,"children":110},"span",{"class":108,"line":109},"line",1,[111],{"type":41,"tag":106,"props":112,"children":113},{},[114],{"type":47,"value":115},"flowchart TD\n",{"type":41,"tag":106,"props":117,"children":119},{"class":108,"line":118},2,[120],{"type":41,"tag":106,"props":121,"children":122},{},[123],{"type":47,"value":124},"    Start([Start]) --> Setup[Setup & Connection\n",{"type":41,"tag":106,"props":126,"children":128},{"class":108,"line":127},3,[129],{"type":41,"tag":106,"props":130,"children":131},{},[132],{"type":47,"value":133},"Scaffolds workspace & connections]\n",{"type":41,"tag":106,"props":135,"children":137},{"class":108,"line":136},4,[138],{"type":41,"tag":106,"props":139,"children":140},{},[141],{"type":47,"value":142},"    Setup --> Prep{Has Golden Dataset?}\n",{"type":41,"tag":106,"props":144,"children":146},{"class":108,"line":145},5,[147],{"type":41,"tag":106,"props":148,"children":149},{},[150],{"type":47,"value":151},"    \n",{"type":41,"tag":106,"props":153,"children":155},{"class":108,"line":154},6,[156],{"type":41,"tag":106,"props":157,"children":158},{},[159],{"type":47,"value":160},"    Prep -- No --> DatasetPrep[Dataset Prep & Expansion\n",{"type":41,"tag":106,"props":162,"children":164},{"class":108,"line":163},7,[165],{"type":41,"tag":106,"props":166,"children":167},{},[168],{"type":47,"value":169},"Builds reference ground-truth]\n",{"type":41,"tag":106,"props":171,"children":173},{"class":108,"line":172},8,[174],{"type":41,"tag":106,"props":175,"children":176},{},[177],{"type":47,"value":178},"    DatasetPrep --> Bootstrap[Baseline Context Bootstrapping\n",{"type":41,"tag":106,"props":180,"children":182},{"class":108,"line":181},9,[183],{"type":41,"tag":106,"props":184,"children":185},{},[186],{"type":47,"value":187},"Generates initial context from schema]\n",{"type":41,"tag":106,"props":189,"children":191},{"class":108,"line":190},10,[192],{"type":41,"tag":106,"props":193,"children":194},{},[195],{"type":47,"value":196},"    Prep -- Yes --> Bootstrap\n",{"type":41,"tag":106,"props":198,"children":199},{"class":108,"line":28},[200],{"type":41,"tag":106,"props":201,"children":202},{},[203],{"type":47,"value":151},{"type":41,"tag":106,"props":205,"children":207},{"class":108,"line":206},12,[208],{"type":41,"tag":106,"props":209,"children":210},{},[211],{"type":47,"value":212},"    Bootstrap --> Evaluate[Evaluation Scoring\n",{"type":41,"tag":106,"props":214,"children":216},{"class":108,"line":215},13,[217],{"type":41,"tag":106,"props":218,"children":219},{},[220],{"type":47,"value":221},"Scores context using Evalbench]\n",{"type":41,"tag":106,"props":223,"children":225},{"class":108,"line":224},14,[226],{"type":41,"tag":106,"props":227,"children":228},{},[229],{"type":47,"value":230},"    Evaluate --> Loop{Tuning Target Met?}\n",{"type":41,"tag":106,"props":232,"children":234},{"class":108,"line":233},15,[235],{"type":41,"tag":106,"props":236,"children":237},{},[238],{"type":47,"value":151},{"type":41,"tag":106,"props":240,"children":242},{"class":108,"line":241},16,[243],{"type":41,"tag":106,"props":244,"children":245},{},[246],{"type":47,"value":247},"    Loop -- No --> Hillclimb[Optimization & Hill-Climbing\n",{"type":41,"tag":106,"props":249,"children":251},{"class":108,"line":250},17,[252],{"type":41,"tag":106,"props":253,"children":254},{},[255],{"type":47,"value":256},"Gap Analysis & Context Mutation]\n",{"type":41,"tag":106,"props":258,"children":260},{"class":108,"line":259},18,[261],{"type":41,"tag":106,"props":262,"children":263},{},[264],{"type":47,"value":265},"    Hillclimb --> Evaluate\n",{"type":41,"tag":106,"props":267,"children":269},{"class":108,"line":268},19,[270],{"type":41,"tag":106,"props":271,"children":272},{},[273],{"type":47,"value":151},{"type":41,"tag":106,"props":275,"children":277},{"class":108,"line":276},20,[278],{"type":41,"tag":106,"props":279,"children":280},{},[281],{"type":47,"value":282},"    Loop -- Yes --> End([End - Context Deployed!])\n",{"type":41,"tag":79,"props":284,"children":285},{},[],{"type":41,"tag":83,"props":287,"children":289},{"id":288},"workflow-phases-rationales-entry-prerequisites",[290],{"type":47,"value":291},"Workflow Phases, Rationales & Entry Prerequisites",{"type":41,"tag":79,"props":293,"children":294},{},[],{"type":41,"tag":296,"props":297,"children":299},"h3",{"id":298},"setup-connection-configuration-phase",[300],{"type":47,"value":301},"Setup & Connection Configuration Phase",{"type":41,"tag":303,"props":304,"children":305},"ul",{},[306,324,342,352],{"type":41,"tag":307,"props":308,"children":309},"li",{},[310,316,318],{"type":41,"tag":311,"props":312,"children":313},"strong",{},[314],{"type":47,"value":315},"Reference",{"type":47,"value":317},": ",{"type":41,"tag":70,"props":319,"children":321},{"href":320},"..\u002Fcontext-engineering-init\u002FSKILL.md",[322],{"type":47,"value":323},"context-engineering-init",{"type":41,"tag":307,"props":325,"children":326},{},[327,332,334,340],{"type":41,"tag":311,"props":328,"children":329},{},[330],{"type":47,"value":331},"Goal",{"type":47,"value":333},": Scaffold the local ",{"type":41,"tag":56,"props":335,"children":337},{"className":336},[],[338],{"type":47,"value":339},"autoctx\u002F",{"type":47,"value":341}," workspace and establish verified database connections.",{"type":41,"tag":307,"props":343,"children":344},{},[345,350],{"type":41,"tag":311,"props":346,"children":347},{},[348],{"type":47,"value":349},"Rationale",{"type":47,"value":351},": Readonly-database access is an input for evaluation dataset prep and expand, baseline context bootstrapping,",{"type":41,"tag":307,"props":353,"children":354},{},[355,360,362],{"type":41,"tag":311,"props":356,"children":357},{},[358],{"type":47,"value":359},"Entry Prerequisites",{"type":47,"value":361},":\n",{"type":41,"tag":303,"props":363,"children":364},{},[365],{"type":41,"tag":307,"props":366,"children":367},{},[368,374],{"type":41,"tag":369,"props":370,"children":371},"em",{},[372],{"type":47,"value":373},"None",{"type":47,"value":375},".",{"type":41,"tag":79,"props":377,"children":378},{},[],{"type":41,"tag":296,"props":380,"children":382},{"id":381},"evaluation-dataset-prep-expansion-phase",[383],{"type":47,"value":384},"Evaluation Dataset Prep & Expansion Phase",{"type":41,"tag":303,"props":386,"children":387},{},[388,402,441,451,460,469],{"type":41,"tag":307,"props":389,"children":390},{},[391,395,396],{"type":41,"tag":311,"props":392,"children":393},{},[394],{"type":47,"value":315},{"type":47,"value":317},{"type":41,"tag":70,"props":397,"children":399},{"href":398},"..\u002Fcontext-engineering-dataset-generation\u002FSKILL.md",[400],{"type":47,"value":401},"context-engineering-dataset-generation",{"type":41,"tag":307,"props":403,"children":404},{},[405,410,411,417,419,425,426,432,434,440],{"type":41,"tag":311,"props":406,"children":407},{},[408],{"type":47,"value":409},"Mandatory Deliverables",{"type":47,"value":317},{"type":41,"tag":56,"props":412,"children":414},{"className":413},[],[415],{"type":47,"value":416},"evalset_environment_inputs.md",{"type":47,"value":418},", ",{"type":41,"tag":56,"props":420,"children":422},{"className":421},[],[423],{"type":47,"value":424},"evalset_gen_plan.md",{"type":47,"value":418},{"type":41,"tag":56,"props":427,"children":429},{"className":428},[],[430],{"type":47,"value":431},"evalset_report_pair_level.md",{"type":47,"value":433},", and ",{"type":41,"tag":56,"props":435,"children":437},{"className":436},[],[438],{"type":47,"value":439},"evalset_report_dataset_level.md",{"type":47,"value":375},{"type":41,"tag":307,"props":442,"children":443},{},[444,449],{"type":41,"tag":311,"props":445,"children":446},{},[447],{"type":47,"value":448},"Mandatory Action",{"type":47,"value":450},": You MUST read the reference file above before starting this phase and you MUST read any files referenced within it to understand the dataset generation process.",{"type":41,"tag":307,"props":452,"children":453},{},[454,458],{"type":41,"tag":311,"props":455,"children":456},{},[457],{"type":47,"value":331},{"type":47,"value":459},": Build a high-quality \"golden\" ground-truth dataset and associated audit reports.",{"type":41,"tag":307,"props":461,"children":462},{},[463,467],{"type":41,"tag":311,"props":464,"children":465},{},[466],{"type":47,"value":349},{"type":47,"value":468},": A representative ground-truth dataset and formal audit trails are required to objectively measure and verify translation accuracy improvements.",{"type":41,"tag":307,"props":470,"children":471},{},[472,476,477],{"type":41,"tag":311,"props":473,"children":474},{},[475],{"type":47,"value":359},{"type":47,"value":361},{"type":41,"tag":303,"props":478,"children":481},{"className":479},[480],"contains-task-list",[482],{"type":41,"tag":307,"props":483,"children":486},{"className":484},[485],"task-list-item",[487,493,495,500,502,508],{"type":41,"tag":488,"props":489,"children":492},"input",{"disabled":490,"type":491},true,"checkbox",[],{"type":47,"value":494}," ",{"type":41,"tag":311,"props":496,"children":497},{},[498],{"type":47,"value":499},"Workspace Configured",{"type":47,"value":501},": The Setup & Connection Configuration phase has been completed, meaning ",{"type":41,"tag":56,"props":503,"children":505},{"className":504},[],[506],{"type":47,"value":507},"autoctx\u002Ftools.yaml",{"type":47,"value":509}," is active.",{"type":41,"tag":79,"props":511,"children":512},{},[],{"type":41,"tag":296,"props":514,"children":516},{"id":515},"baseline-context-bootstrapping-phase",[517],{"type":47,"value":518},"Baseline Context Bootstrapping Phase",{"type":41,"tag":303,"props":520,"children":521},{},[522,536,552,561],{"type":41,"tag":307,"props":523,"children":524},{},[525,529,530],{"type":41,"tag":311,"props":526,"children":527},{},[528],{"type":47,"value":315},{"type":47,"value":317},{"type":41,"tag":70,"props":531,"children":533},{"href":532},"..\u002Fcontext-engineering-bootstrap\u002FSKILL.md",[534],{"type":47,"value":535},"context-engineering-bootstrap",{"type":41,"tag":307,"props":537,"children":538},{},[539,543,545,550],{"type":41,"tag":311,"props":540,"children":541},{},[542],{"type":47,"value":331},{"type":47,"value":544},": Deduce query concepts and generate a baseline ",{"type":41,"tag":56,"props":546,"children":548},{"className":547},[],[549],{"type":47,"value":61},{"type":47,"value":551}," (templates, facets, value searches) directly from database schemas and metadata.",{"type":41,"tag":307,"props":553,"children":554},{},[555,559],{"type":41,"tag":311,"props":556,"children":557},{},[558],{"type":47,"value":349},{"type":47,"value":560},": Establishes the baseline context set as the starting point for optimization.",{"type":41,"tag":307,"props":562,"children":563},{},[564,568,569],{"type":41,"tag":311,"props":565,"children":566},{},[567],{"type":47,"value":359},{"type":47,"value":361},{"type":41,"tag":303,"props":570,"children":572},{"className":571},[480],[573],{"type":41,"tag":307,"props":574,"children":576},{"className":575},[485],[577,580,581,585,586,591],{"type":41,"tag":488,"props":578,"children":579},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":582,"children":583},{},[584],{"type":47,"value":499},{"type":47,"value":501},{"type":41,"tag":56,"props":587,"children":589},{"className":588},[],[590],{"type":47,"value":507},{"type":47,"value":509},{"type":41,"tag":79,"props":593,"children":594},{},[],{"type":41,"tag":296,"props":596,"children":598},{"id":597},"run-evaluation-and-score",[599],{"type":47,"value":600},"Run Evaluation And Score",{"type":41,"tag":303,"props":602,"children":603},{},[604,618,627,636],{"type":41,"tag":307,"props":605,"children":606},{},[607,611,612],{"type":41,"tag":311,"props":608,"children":609},{},[610],{"type":47,"value":315},{"type":47,"value":317},{"type":41,"tag":70,"props":613,"children":615},{"href":614},"..\u002Fcontext-engineering-evaluate\u002FSKILL.md",[616],{"type":47,"value":617},"context-engineering-evaluate",{"type":41,"tag":307,"props":619,"children":620},{},[621,625],{"type":41,"tag":311,"props":622,"children":623},{},[624],{"type":47,"value":331},{"type":47,"value":626},": Run a structured Evalbench evaluation to score the accuracy of a specific context set and identify exact query failures.",{"type":41,"tag":307,"props":628,"children":629},{},[630,634],{"type":41,"tag":311,"props":631,"children":632},{},[633],{"type":47,"value":349},{"type":47,"value":635},": Quantitatively measures context effectiveness, identifying precise query failures.",{"type":41,"tag":307,"props":637,"children":638},{},[639,643,644],{"type":41,"tag":311,"props":640,"children":641},{},[642],{"type":47,"value":359},{"type":47,"value":361},{"type":41,"tag":303,"props":645,"children":647},{"className":646},[480],[648,667,682,697],{"type":41,"tag":307,"props":649,"children":651},{"className":650},[485],[652,655,656,660,661,666],{"type":41,"tag":488,"props":653,"children":654},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":657,"children":658},{},[659],{"type":47,"value":499},{"type":47,"value":501},{"type":41,"tag":56,"props":662,"children":664},{"className":663},[],[665],{"type":47,"value":507},{"type":47,"value":509},{"type":41,"tag":307,"props":668,"children":670},{"className":669},[485],[671,674,675,680],{"type":41,"tag":488,"props":672,"children":673},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":676,"children":677},{},[678],{"type":47,"value":679},"Context Set Available",{"type":47,"value":681},": A local context set JSON file is available on disk (either the baseline from the Baseline Bootstrapping phase, or a path to a user-supplied custom context set).",{"type":41,"tag":307,"props":683,"children":685},{"className":684},[485],[686,689,690,695],{"type":41,"tag":488,"props":687,"children":688},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":691,"children":692},{},[693],{"type":47,"value":694},"Golden Dataset Available",{"type":47,"value":696},": A local golden evaluation dataset JSON file is available on disk (either from the Evaluation Dataset Prep phase, or a path to a user-supplied custom dataset).",{"type":41,"tag":307,"props":698,"children":700},{"className":699},[485],[701,704,705,710,712,718],{"type":41,"tag":488,"props":702,"children":703},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":706,"children":707},{},[708],{"type":47,"value":709},"GCP Context ID Provided",{"type":47,"value":711},": The user has provided their GCP console ",{"type":41,"tag":56,"props":713,"children":715},{"className":714},[],[716],{"type":47,"value":717},"context_set_id",{"type":47,"value":719}," representing the uploaded context set.",{"type":41,"tag":79,"props":721,"children":722},{},[],{"type":41,"tag":296,"props":724,"children":726},{"id":725},"optimization-hill-climbing-phase",[727],{"type":47,"value":728},"Optimization & Hill-Climbing Phase",{"type":41,"tag":303,"props":730,"children":731},{},[732,746,755,764],{"type":41,"tag":307,"props":733,"children":734},{},[735,739,740],{"type":41,"tag":311,"props":736,"children":737},{},[738],{"type":47,"value":315},{"type":47,"value":317},{"type":41,"tag":70,"props":741,"children":743},{"href":742},"..\u002Fcontext-engineering-hillclimb\u002FSKILL.md",[744],{"type":47,"value":745},"context-engineering-hillclimb",{"type":41,"tag":307,"props":747,"children":748},{},[749,753],{"type":41,"tag":311,"props":750,"children":751},{},[752],{"type":47,"value":331},{"type":47,"value":754},": Analyze evaluation failures to perform a Gap Analysis and apply targeted context mutations to iteratively improve performance.",{"type":41,"tag":307,"props":756,"children":757},{},[758,762],{"type":41,"tag":311,"props":759,"children":760},{},[761],{"type":47,"value":349},{"type":47,"value":763},": Closes the loop by analyzing failures to generate targeted optimizations.",{"type":41,"tag":307,"props":765,"children":766},{},[767,771,772],{"type":41,"tag":311,"props":768,"children":769},{},[770],{"type":47,"value":359},{"type":47,"value":361},{"type":41,"tag":303,"props":773,"children":775},{"className":774},[480],[776,815],{"type":41,"tag":307,"props":777,"children":779},{"className":778},[485],[780,783,784,789,791,797,799,805,807,813],{"type":41,"tag":488,"props":781,"children":782},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":785,"children":786},{},[787],{"type":47,"value":788},"Evaluation Completed",{"type":47,"value":790},": The Evaluation Scoring phase has been executed; the active experiment folder contains an ",{"type":41,"tag":56,"props":792,"children":794},{"className":793},[],[795],{"type":47,"value":796},"eval_reports\u002F",{"type":47,"value":798}," directory with at least one completed evaluation run (containing ",{"type":41,"tag":56,"props":800,"children":802},{"className":801},[],[803],{"type":47,"value":804},"scores.csv",{"type":47,"value":806}," and ",{"type":41,"tag":56,"props":808,"children":810},{"className":809},[],[811],{"type":47,"value":812},"summary.csv",{"type":47,"value":814},").",{"type":41,"tag":307,"props":816,"children":818},{"className":817},[485],[819,822,823,828],{"type":41,"tag":488,"props":820,"children":821},{"disabled":490,"type":491},[],{"type":47,"value":494},{"type":41,"tag":311,"props":824,"children":825},{},[826],{"type":47,"value":827},"Base Context Available",{"type":47,"value":829},": The base context set file that was evaluated in the target run is available on disk.",{"type":41,"tag":79,"props":831,"children":832},{},[],{"type":41,"tag":83,"props":834,"children":836},{"id":835},"workspace-folder-structure-evolution",[837],{"type":47,"value":838},"Workspace Folder Structure & Evolution",{"type":41,"tag":50,"props":840,"children":841},{},[842],{"type":47,"value":843},"The Autoctx workflows generate and interact with a structured workspace to maintain state and trace progress across iterations.",{"type":41,"tag":296,"props":845,"children":847},{"id":846},"workspace-folder-layout",[848],{"type":47,"value":849},"Workspace Folder Layout",{"type":41,"tag":303,"props":851,"children":852},{},[853],{"type":41,"tag":307,"props":854,"children":855},{},[856,861,863],{"type":41,"tag":56,"props":857,"children":859},{"className":858},[],[860],{"type":47,"value":339},{"type":47,"value":862},": The dedicated workspace directory.\n",{"type":41,"tag":303,"props":864,"children":865},{},[866,877,888],{"type":41,"tag":307,"props":867,"children":868},{},[869,875],{"type":41,"tag":56,"props":870,"children":872},{"className":871},[],[873],{"type":47,"value":874},"tools.yaml",{"type":47,"value":876},": Configuration file for the Toolbox MCP Server.",{"type":41,"tag":307,"props":878,"children":879},{},[880,886],{"type":41,"tag":56,"props":881,"children":883},{"className":882},[],[884],{"type":47,"value":885},"state.md",{"type":47,"value":887},": Summary of the experiment state, active experiment, and run history.",{"type":41,"tag":307,"props":889,"children":890},{},[891,897,899],{"type":41,"tag":56,"props":892,"children":894},{"className":893},[],[895],{"type":47,"value":896},"experiments\u002F",{"type":47,"value":898},": Root directory for all experiments.\n",{"type":41,"tag":303,"props":900,"children":901},{},[902],{"type":41,"tag":307,"props":903,"children":904},{},[905,911,913],{"type":41,"tag":56,"props":906,"children":908},{"className":907},[],[909],{"type":47,"value":910},"\u003Cexperiment_name>\u002F",{"type":47,"value":912},": Specific experiment directory.\n",{"type":41,"tag":303,"props":914,"children":915},{},[916,927,938,948],{"type":41,"tag":307,"props":917,"children":918},{},[919,925],{"type":41,"tag":56,"props":920,"children":922},{"className":921},[],[923],{"type":47,"value":924},"bootstrap_context.json",{"type":47,"value":926},": The baseline ContextSet generated by the Baseline Bootstrapping phase.",{"type":41,"tag":307,"props":928,"children":929},{},[930,936],{"type":41,"tag":56,"props":931,"children":933},{"className":932},[],[934],{"type":47,"value":935},"eval_configs\u002F",{"type":47,"value":937},": Directory containing Evalbench configurations.",{"type":41,"tag":307,"props":939,"children":940},{},[941,946],{"type":41,"tag":56,"props":942,"children":944},{"className":943},[],[945],{"type":47,"value":796},{"type":47,"value":947},": Directory containing evaluation output runs.",{"type":41,"tag":307,"props":949,"children":950},{},[951,957,959],{"type":41,"tag":56,"props":952,"children":954},{"className":953},[],[955],{"type":47,"value":956},"hillclimb\u002F",{"type":47,"value":958},": Directory containing hill-climbing iteration artifacts.\n",{"type":41,"tag":303,"props":960,"children":961},{},[962,980],{"type":41,"tag":307,"props":963,"children":964},{},[965,971,973,979],{"type":41,"tag":56,"props":966,"children":968},{"className":967},[],[969],{"type":47,"value":970},"gap_analysis_vN.md",{"type":47,"value":972},": Analysis of missing contexts at iteration ",{"type":41,"tag":56,"props":974,"children":976},{"className":975},[],[977],{"type":47,"value":978},"N",{"type":47,"value":375},{"type":41,"tag":307,"props":981,"children":982},{},[983,989,991,996],{"type":41,"tag":56,"props":984,"children":986},{"className":985},[],[987],{"type":47,"value":988},"improved_context_vN.json",{"type":47,"value":990},": The mutated ContextSet at iteration ",{"type":41,"tag":56,"props":992,"children":994},{"className":993},[],[995],{"type":47,"value":978},{"type":47,"value":375},{"type":41,"tag":296,"props":998,"children":1000},{"id":999},"workspace-evolution-lifecycle",[1001],{"type":47,"value":1002},"Workspace Evolution Lifecycle",{"type":41,"tag":1004,"props":1005,"children":1006},"ol",{},[1007,1043,1060,1082,1118],{"type":41,"tag":307,"props":1008,"children":1009},{},[1010,1015,1016,1021,1022,1027,1029,1034,1036,1041],{"type":41,"tag":311,"props":1011,"children":1012},{},[1013],{"type":47,"value":1014},"Post-Initialization",{"type":47,"value":317},{"type":41,"tag":56,"props":1017,"children":1019},{"className":1018},[],[1020],{"type":47,"value":874},{"type":47,"value":418},{"type":41,"tag":56,"props":1023,"children":1025},{"className":1024},[],[1026],{"type":47,"value":885},{"type":47,"value":1028},", and an empty ",{"type":41,"tag":56,"props":1030,"children":1032},{"className":1031},[],[1033],{"type":47,"value":896},{"type":47,"value":1035}," directory appear in ",{"type":41,"tag":56,"props":1037,"children":1039},{"className":1038},[],[1040],{"type":47,"value":339},{"type":47,"value":1042}," after the Setup & Connection Configuration phase.",{"type":41,"tag":307,"props":1044,"children":1045},{},[1046,1051,1052,1058],{"type":41,"tag":311,"props":1047,"children":1048},{},[1049],{"type":47,"value":1050},"Post-Bootstrap",{"type":47,"value":317},{"type":41,"tag":56,"props":1053,"children":1055},{"className":1054},[],[1056],{"type":47,"value":1057},"autoctx\u002Fexperiments\u002F\u003Cexperiment_name>\u002Fbootstrap_context.json",{"type":47,"value":1059}," is generated by the Baseline Bootstrapping phase.",{"type":41,"tag":307,"props":1061,"children":1062},{},[1063,1068,1069,1074,1075,1080],{"type":41,"tag":311,"props":1064,"children":1065},{},[1066],{"type":47,"value":1067},"Post-Evaluation",{"type":47,"value":317},{"type":41,"tag":56,"props":1070,"children":1072},{"className":1071},[],[1073],{"type":47,"value":935},{"type":47,"value":806},{"type":41,"tag":56,"props":1076,"children":1078},{"className":1077},[],[1079],{"type":47,"value":796},{"type":47,"value":1081}," appear inside the experiment folder after the Evaluation Scoring phase.",{"type":41,"tag":307,"props":1083,"children":1084},{},[1085,1090,1091,1096,1098,1103,1104,1109,1111,1116],{"type":41,"tag":311,"props":1086,"children":1087},{},[1088],{"type":47,"value":1089},"Post-Hill-Climbing",{"type":47,"value":317},{"type":41,"tag":56,"props":1092,"children":1094},{"className":1093},[],[1095],{"type":47,"value":956},{"type":47,"value":1097}," appears with ",{"type":41,"tag":56,"props":1099,"children":1101},{"className":1100},[],[1102],{"type":47,"value":970},{"type":47,"value":806},{"type":41,"tag":56,"props":1105,"children":1107},{"className":1106},[],[1108],{"type":47,"value":988},{"type":47,"value":1110}," after the Optimization & Hill-Climbing phase, and ",{"type":41,"tag":56,"props":1112,"children":1114},{"className":1113},[],[1115],{"type":47,"value":885},{"type":47,"value":1117}," is updated.",{"type":41,"tag":307,"props":1119,"children":1120},{},[1121,1126,1128,1133,1135,1141],{"type":41,"tag":311,"props":1122,"children":1123},{},[1124],{"type":47,"value":1125},"Tuning Loop",{"type":47,"value":1127},": Iteratively evaluates ",{"type":41,"tag":56,"props":1129,"children":1131},{"className":1130},[],[1132],{"type":47,"value":988},{"type":47,"value":1134}," and generates ",{"type":41,"tag":56,"props":1136,"children":1138},{"className":1137},[],[1139],{"type":47,"value":1140},"improved_context_v(N+1).json",{"type":47,"value":1142}," until target accuracy is achieved.",{"type":41,"tag":83,"props":1144,"children":1146},{"id":1145},"safety-protocol",[1147],{"type":47,"value":1148},"Safety & Protocol",{"type":41,"tag":303,"props":1150,"children":1151},{},[1152,1209,1267],{"type":41,"tag":307,"props":1153,"children":1154},{},[1155,1160,1162],{"type":41,"tag":311,"props":1156,"children":1157},{},[1158],{"type":47,"value":1159},"Missing Dataset",{"type":47,"value":1161},":",{"type":41,"tag":303,"props":1163,"children":1164},{},[1165],{"type":41,"tag":307,"props":1166,"children":1167},{},[1168,1170,1175,1177],{"type":47,"value":1169},"If the user's request requires ",{"type":41,"tag":311,"props":1171,"children":1172},{},[1173],{"type":47,"value":1174},"evaluating, scoring, or optimizing",{"type":47,"value":1176}," a context set (e.g., running evaluations, tuning, or hill-climbing):\n",{"type":41,"tag":303,"props":1178,"children":1179},{},[1180,1185],{"type":41,"tag":307,"props":1181,"children":1182},{},[1183],{"type":47,"value":1184},"Validate if an evaluation dataset exists.",{"type":41,"tag":307,"props":1186,"children":1187},{},[1188,1193,1195,1200,1202,1207],{"type":41,"tag":311,"props":1189,"children":1190},{},[1191],{"type":47,"value":1192},"Mandatory Halt & Guide",{"type":47,"value":1194},": If no evaluation dataset exists, you are ",{"type":41,"tag":311,"props":1196,"children":1197},{},[1198],{"type":47,"value":1199},"strictly forbidden",{"type":47,"value":1201}," from executing any context bootstrapping, tuning, or evaluation operations in this turn. You must immediately halt, stop calling tools, and yield the turn. Explain ",{"type":41,"tag":311,"props":1203,"children":1204},{},[1205],{"type":47,"value":1206},"why a golden evaluation dataset is critical",{"type":47,"value":1208}," for context engineering (i.e., you cannot objectively score, validate, or hill-climb translation accuracy without a ground-truth dataset), and ask if they would like help generating one first.",{"type":41,"tag":307,"props":1210,"children":1211},{},[1212,1217,1218],{"type":41,"tag":311,"props":1213,"children":1214},{},[1215],{"type":47,"value":1216},"Critical API Error Protocol",{"type":47,"value":1161},{"type":41,"tag":303,"props":1219,"children":1220},{},[1221,1226,1262],{"type":41,"tag":307,"props":1222,"children":1223},{},[1224],{"type":47,"value":1225},"Seek guidance from the user if you run into results where retrying is unlikely to solve the issue.",{"type":41,"tag":307,"props":1227,"children":1228},{},[1229,1231,1237,1239,1245,1247,1253,1254,1260],{"type":47,"value":1230},"Examples:",{"type":41,"tag":56,"props":1232,"children":1234},{"className":1233},[],[1235],{"type":47,"value":1236},"503",{"type":47,"value":1238}," or ",{"type":41,"tag":56,"props":1240,"children":1242},{"className":1241},[],[1243],{"type":47,"value":1244},"429",{"type":47,"value":1246}," error, ",{"type":41,"tag":56,"props":1248,"children":1250},{"className":1249},[],[1251],{"type":47,"value":1252},"UNAVAILABLE",{"type":47,"value":1238},{"type":41,"tag":56,"props":1255,"children":1257},{"className":1256},[],[1258],{"type":47,"value":1259},"RESOURCE_EXHAUSTED",{"type":47,"value":1261}," status code.",{"type":41,"tag":307,"props":1263,"children":1264},{},[1265],{"type":47,"value":1266},"Why: These errors are often associated with quota issues, and retrying the request immediately will not resolve the issue. For issues related to Vertex AI Resource Exhaustion, retrying at a later time is often the only solution.",{"type":41,"tag":307,"props":1268,"children":1269},{},[1270,1275,1276],{"type":41,"tag":311,"props":1271,"children":1272},{},[1273],{"type":47,"value":1274},"Skill Prerequisites & Troubleshooting",{"type":47,"value":1161},{"type":41,"tag":303,"props":1277,"children":1278},{},[1279],{"type":41,"tag":307,"props":1280,"children":1281},{},[1282,1284],{"type":47,"value":1283},"If you encounter any environmental, connection, or execution errors, verify that all preconditions are met. Types of preconditions:\n",{"type":41,"tag":303,"props":1285,"children":1286},{},[1287,1295,1303,1311],{"type":41,"tag":307,"props":1288,"children":1289},{},[1290],{"type":41,"tag":369,"props":1291,"children":1292},{},[1293],{"type":47,"value":1294},"Google Cloud Service APIs enablement",{"type":41,"tag":307,"props":1296,"children":1297},{},[1298],{"type":41,"tag":369,"props":1299,"children":1300},{},[1301],{"type":47,"value":1302},"IAM Roles & Access",{"type":41,"tag":307,"props":1304,"children":1305},{},[1306],{"type":41,"tag":369,"props":1307,"children":1308},{},[1309],{"type":47,"value":1310},"Database Instance Permissions",{"type":41,"tag":307,"props":1312,"children":1313},{},[1314,1319,1321,1327],{"type":41,"tag":369,"props":1315,"children":1316},{},[1317],{"type":47,"value":1318},"Development Environment",{"type":47,"value":1320},": Application Default Credentials (ADC) and Python package manager (",{"type":41,"tag":56,"props":1322,"children":1324},{"className":1323},[],[1325],{"type":47,"value":1326},"uv",{"type":47,"value":1328},")",{"type":41,"tag":1330,"props":1331,"children":1332},"style",{},[1333],{"type":47,"value":1334},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1336,"total":1519},[1337,1355,1369,1391,1405,1416,1430,1447,1464,1477,1493,1503],{"slug":1338,"name":1338,"fn":1339,"description":1340,"org":1341,"tags":1342,"stars":1352,"repoUrl":1353,"updatedAt":1354},"kb-search","search and extract local knowledge base documents","Allows listing, searching and extracting information from local knowledge base documents for information about tables\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1343,1346,1349],{"name":1344,"slug":1345,"type":16},"Documentation","documentation",{"name":1347,"slug":1348,"type":16},"Knowledge Base","knowledge-base",{"name":1350,"slug":1351,"type":16},"Search","search",6749,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fknowledge-catalog","2026-07-12T07:38:52.157375",{"slug":1356,"name":1357,"fn":1358,"description":1359,"org":1360,"tags":1361,"stars":1352,"repoUrl":1353,"updatedAt":1368},"knowledgecatalogdiscoveryagent","knowledge_catalog_discovery_agent","search and rank Knowledge Catalog data entries","Analyzes user queries, extracts relevant predicates, and utilizes Knowledge Catalog Search to find and rank the most relevant data entries. Engages with the user throughout the process.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1362,1363,1364,1367],{"name":18,"slug":19,"type":16},{"name":9,"slug":8,"type":16},{"name":1365,"slug":1366,"type":16},"Knowledge Management","knowledge-management",{"name":1350,"slug":1351,"type":16},"2026-07-12T07:38:22.196851",{"slug":1370,"name":1370,"fn":1371,"description":1372,"org":1373,"tags":1374,"stars":1388,"repoUrl":1389,"updatedAt":1390},"contributing","contribute to Cloud Foundation Fabric","End-to-end workflow for contributing to Cloud Foundation Fabric: triaging GitHub issues, proactive feature development, validating with tests and Policy Troubleshooter, and submitting sanitized Pull Requests. Use when addressing a Fabric GitHub issue, developing a module or FAST stage change, or preparing a branch for a pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1375,1378,1381,1384,1385],{"name":1376,"slug":1377,"type":16},"Automation","automation",{"name":1379,"slug":1380,"type":16},"Engineering","engineering",{"name":1382,"slug":1383,"type":16},"GitHub","github",{"name":9,"slug":8,"type":16},{"name":1386,"slug":1387,"type":16},"Pull Requests","pull-requests",2062,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fcloud-foundation-fabric","2026-07-31T06:23:36.935005",{"slug":1392,"name":1392,"fn":1393,"description":1394,"org":1395,"tags":1396,"stars":1388,"repoUrl":1389,"updatedAt":1404},"fabric-builder","generate Terraform code for Google Cloud","Generates idiomatic Cloud Foundation Fabric (CFF) Terraform code using CFF modules. Use when users ask to create GCP resources, use Fabric modules, or generate Terraform code for Google Cloud.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1397,1398,1401],{"name":9,"slug":8,"type":16},{"name":1399,"slug":1400,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":1402,"slug":1403,"type":16},"Terraform","terraform","2026-07-12T07:38:23.514555",{"slug":1406,"name":1406,"fn":1407,"description":1408,"org":1409,"tags":1410,"stars":1388,"repoUrl":1389,"updatedAt":1415},"fast-0-org-setup-prereqs","prepare prerequisites for FAST 0-org-setup","Guides the user step-by-step through the prerequisites for the FAST 0-org-setup stage, supporting both Standard GCP and Google Cloud Dedicated (GCD) environments. Use when a user asks to prepare or run prerequisites for 0-org-setup or bootstrap the FAST landing zone.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1411,1412],{"name":9,"slug":8,"type":16},{"name":1413,"slug":1414,"type":16},"Operations","operations","2026-07-12T07:38:28.127148",{"slug":1417,"name":1417,"fn":1418,"description":1419,"org":1420,"tags":1421,"stars":1427,"repoUrl":1428,"updatedAt":1429},"agent-aware-cli","design agent-aware command-line interfaces","Guide for designing and implementing command-line interfaces (CLIs) that are equally usable by human developers and automated coding agents. Use when the user wants to build a CLI, apply CLI best practices, or use Go with Cobra and Viper.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1422,1425,1426],{"name":1423,"slug":1424,"type":16},"CLI","cli",{"name":1379,"slug":1380,"type":16},{"name":9,"slug":8,"type":16},1150,"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fvertex-ai-creative-studio","2026-07-12T07:39:08.41406",{"slug":1431,"name":1431,"fn":1432,"description":1433,"org":1434,"tags":1435,"stars":1427,"repoUrl":1428,"updatedAt":1446},"build-mcp-genmedia","build and configure GenAI MCP servers","Builds the mcp-genmedia Go MCP servers (nanobanana, veo, lyria, gemini-multimodal, chirp3-hd, avtool) from source and wires them into settings.json. Use this skill whenever the MCP tools are missing or broken — typically at the start of a new session, after a container restart, or when \u002Ftmp has been wiped. The prebuilt binaries in \u002Fworkspace\u002F.local\u002Fbin\u002F have no exec bit and live on a noexec mount; this skill compiles fresh executables into \u002Ftmp\u002Fbin\u002F where execution is allowed.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1436,1439,1440,1443],{"name":1437,"slug":1438,"type":16},"API Development","api-development",{"name":9,"slug":8,"type":16},{"name":1441,"slug":1442,"type":16},"LLM","llm",{"name":1444,"slug":1445,"type":16},"MCP","mcp","2026-07-12T07:39:10.911302",{"slug":1448,"name":1448,"fn":1449,"description":1450,"org":1451,"tags":1452,"stars":1427,"repoUrl":1428,"updatedAt":1463},"genmedia-audio-engineer","synthesize and mix audio content","Expert in audio synthesis, music generation, and mixing. Use when creating podcasts, background scores, or multi-track audio layering using mcp-chirp3-go, mcp-lyria-go, mcp-gemini-go, mcp-nanobanana-go, and mcp-avtool-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1453,1456,1459,1460],{"name":1454,"slug":1455,"type":16},"Audio","audio",{"name":1457,"slug":1458,"type":16},"Creative","creative",{"name":9,"slug":8,"type":16},{"name":1461,"slug":1462,"type":16},"Vertex AI","vertex-ai","2026-07-12T07:39:16.623879",{"slug":1465,"name":1465,"fn":1466,"description":1467,"org":1468,"tags":1469,"stars":1427,"repoUrl":1428,"updatedAt":1476},"genmedia-image-artist","generate and edit AI images","Expert in AI image generation and editing. Use when the user needs high-quality textures, character-consistent visuals, or image-to-image editing using mcp-nanobanana-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1470,1471,1472,1475],{"name":1457,"slug":1458,"type":16},{"name":9,"slug":8,"type":16},{"name":1473,"slug":1474,"type":16},"Image Generation","image-generation",{"name":1461,"slug":1462,"type":16},"2026-07-12T07:39:15.372822",{"slug":1478,"name":1478,"fn":1479,"description":1480,"org":1481,"tags":1482,"stars":1427,"repoUrl":1428,"updatedAt":1492},"genmedia-producer","produce multi-step media content","Expert media production assistant. Use when requested to help with storyboarding, podcast creation, audio assembly, or complex multi-step media workflows using the GenMedia MCP servers (Veo, Lyria, Gemini TTS, NanoBanana).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1483,1484,1485,1486,1489],{"name":1454,"slug":1455,"type":16},{"name":1457,"slug":1458,"type":16},{"name":9,"slug":8,"type":16},{"name":1487,"slug":1488,"type":16},"Media","media",{"name":1490,"slug":1491,"type":16},"Video","video","2026-07-12T07:39:09.672849",{"slug":1494,"name":1494,"fn":1495,"description":1496,"org":1497,"tags":1498,"stars":1427,"repoUrl":1428,"updatedAt":1502},"genmedia-video-editor","edit and compose video content","Expert in video composition, editing, and format conversion. Use when the user wants to generate high-quality video, overlay images on video, concatenate clips, create GIFs, or sync audio to video using mcp-avtool-go and mcp-veo-go.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1499,1500,1501],{"name":1457,"slug":1458,"type":16},{"name":9,"slug":8,"type":16},{"name":1490,"slug":1491,"type":16},"2026-07-12T07:39:13.749081",{"slug":1504,"name":1504,"fn":1505,"description":1506,"org":1507,"tags":1508,"stars":1427,"repoUrl":1428,"updatedAt":1518},"genmedia-voice-director","generate expressive text-to-speech with Gemini","Expert in casting, directing, and generating expressive text-to-speech using Gemini TTS. Use this when the user needs virtual voice actor personas, expressive speech generation, or multiple variations of a voiceover (like \"take 3 on the bounce\").",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1509,1510,1511,1512,1515],{"name":1454,"slug":1455,"type":16},{"name":1457,"slug":1458,"type":16},{"name":21,"slug":22,"type":16},{"name":1513,"slug":1514,"type":16},"Speech","speech",{"name":1516,"slug":1517,"type":16},"Text-to-Speech","text-to-speech","2026-07-12T07:39:17.86673",80,{"items":1521,"total":163},[1522,1538,1552,1562,1574,1586,1593],{"slug":535,"name":535,"fn":1523,"description":1524,"org":1525,"tags":1526,"stars":24,"repoUrl":25,"updatedAt":1537},"bootstrap initial ContextSet for database enrichment","Guides the agent to bootstrap an initial ContextSet (templates, facets, and value searches) by deducing key information from the database schema and generating a ContextSet file.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1527,1530,1533,1536],{"name":1528,"slug":1529,"type":16},"Context","context",{"name":1531,"slug":1532,"type":16},"Data Modeling","data-modeling",{"name":1534,"slug":1535,"type":16},"Database","database",{"name":9,"slug":8,"type":16},"2026-07-18T05:47:56.797107",{"slug":401,"name":401,"fn":1539,"description":1540,"org":1541,"tags":1542,"stars":24,"repoUrl":25,"updatedAt":1551},"generate golden SQL evaluation datasets","Generate or expand a golden evaluation dataset of SQL\u002FQuestion (NLQ+SQL) pairs for evaluating NL-to-SQL translation accuracy on a target database.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1543,1544,1547,1548],{"name":18,"slug":19,"type":16},{"name":1545,"slug":1546,"type":16},"Evals","evals",{"name":9,"slug":8,"type":16},{"name":1549,"slug":1550,"type":16},"SQL","sql","2026-07-18T05:47:55.878915",{"slug":617,"name":617,"fn":1553,"description":1554,"org":1555,"tags":1556,"stars":24,"repoUrl":25,"updatedAt":1561},"evaluate ContextSet against golden datasets","Guides the agent to execute an evaluation of a ContextSet against a golden NLQ+SQL dataset using the Evalbench framework.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1557,1558,1559,1560],{"name":18,"slug":19,"type":16},{"name":1545,"slug":1546,"type":16},{"name":9,"slug":8,"type":16},{"name":1549,"slug":1550,"type":16},"2026-07-18T05:47:52.594607",{"slug":745,"name":745,"fn":1563,"description":1564,"org":1565,"tags":1566,"stars":24,"repoUrl":25,"updatedAt":1573},"improve ContextSet via hill-climbing iterations","Guides the agent to perform hill-climbing iterations to improve a ContextSet based on Evalbench evaluation results.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1567,1568,1569,1570],{"name":18,"slug":19,"type":16},{"name":1545,"slug":1546,"type":16},{"name":9,"slug":8,"type":16},{"name":1571,"slug":1572,"type":16},"Optimization","optimization","2026-07-18T05:47:54.951176",{"slug":323,"name":323,"fn":1575,"description":1576,"org":1577,"tags":1578,"stars":24,"repoUrl":25,"updatedAt":1585},"initialize context engineering and database connections","Orchestrates the initialization workflow for context engineering, and provides helper workflow for setting up database connections by creating or updating tools.yaml configurations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1579,1582,1583,1584],{"name":1580,"slug":1581,"type":16},"Configuration","configuration",{"name":1534,"slug":1535,"type":16},{"name":1379,"slug":1380,"type":16},{"name":9,"slug":8,"type":16},"2026-07-18T05:47:59.493278",{"slug":4,"name":4,"fn":5,"description":6,"org":1587,"tags":1588,"stars":24,"repoUrl":25,"updatedAt":26},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1589,1590,1591,1592],{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":9,"slug":8,"type":16},{"slug":1594,"name":1594,"fn":1595,"description":1596,"org":1597,"tags":1598,"stars":24,"repoUrl":25,"updatedAt":1603},"context-generation-guide","generate context items for database enrichment","Guidelines and best practices for generating context items (Templates, Facets, Value Searches). Use this skill whenever the user asks to create, author, or generate context for database enrichment, or asks for examples and instructions on how to write templates, facets, or value searches. It helps bridge the gap between LLMs and structured databases. For running the automated generation, evaluation, and tuning lifecycle, see the context-engineering-workflow skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1599,1600,1601,1602],{"name":14,"slug":15,"type":16},{"name":1534,"slug":1535,"type":16},{"name":1344,"slug":1345,"type":16},{"name":9,"slug":8,"type":16},"2026-07-18T05:13:43.403052"]