[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69BBW15M2B4WV89PSW58DCT":3,"skill-same:01M69BBW15M2B4WV89PSW58DCT":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M69BBW15M2B4WV89PSW58DCT","resource-estimation",null,"Explains QDK circuit resource-estimation parameters, result forms, and conceptual construction of custom QRE architecture and ISA studies. Use when estimating a stored circuit, choosing estimate_circuit parameters, interpreting estimates, or generating Python code for a custom qdk.qre analysis.","microsoft\u002Fqdk-chemistry","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69BBG6XE87Y59T0QRGM63H2",80,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fresource-estimation\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"resource estimation","estimation","python","architecture","code","analysis","use","forms","circuit","python code","for","estimate","custom","result","ISA","when","2026-11-10 10:12:30",false,"---\nname: resource-estimation\nversion: 'v2.3.1'\ndescription: 'Explains QDK circuit resource-estimation parameters, result forms, and conceptual construction of custom QRE architecture and ISA studies. Use when estimating a stored circuit, choosing estimate_circuit parameters, interpreting estimates, or generating Python code for a custom qdk.qre analysis.'\n---\n\n# Circuit Resource Estimation\n\nChoose between exactly two paths:\n\n1. **Stored-circuit tool path** — call `estimate_circuit` with the parameter\n   objects documented below. Use this for a concise estimate of an existing\n   project circuit.\n2. **Direct QDK code path** — generate Python that uses `qdk.qre` directly,\n   after inspecting the installed QDK API. Use this when the user needs more\n   control over architectures, trace transforms, ISA enumeration, result\n   columns, comparisons, or plots.\n\nDo not present these as successive steps. They are alternative interfaces for\ndifferent levels of control.\n\n## Path 1: Estimate a stored circuit\n\nUse `estimate_circuit` to apply the estimator exposed by a stored QDK Chemistry\n`Circuit`. The tool returns its result inline and does not create another\nproject artifact.\n\nThe tool accepts `project_name`, `circuit_filename`, and optional `params`.\n`params` is either one estimator-parameter object or a list of objects for a\nbatch comparison. Omit it to use QDK defaults. MCP calls use the camel-case JSON\nfield names below; Python code that constructs `EstimatorParams` uses the\ncorresponding snake-case attributes.\n\n## Parameter objects\n\nA parameter object may contain:\n\n| Field | Purpose |\n|---|---|\n| `qubitParams` | Selects a built-in physical-qubit model or describes a custom one. |\n| `qecScheme` | Selects a built-in error-correction scheme or describes a custom one. |\n| `distillationUnitSpecifications` | Supplies custom magic-state distillation units. |\n| `constraints` | Restricts runtime, physical qubits, factories, or logical depth. |\n| `errorBudget` | Sets the total error budget or partitions it by source. |\n| `estimateType` | Requests `singlePoint` or `frontier`. |\n\nA list applies independent parameter objects to the same circuit. Use it to\ncompare assumptions rather than making separate tool calls.\n\n### Physical-qubit parameters\n\n`qubitParams.name` accepts these built-in models:\n\n- `qubit_gate_us_e3`\n- `qubit_gate_us_e4`\n- `qubit_gate_ns_e3`\n- `qubit_gate_ns_e4`\n- `qubit_maj_ns_e4`\n- `qubit_maj_ns_e6`\n\nInstead of `name`, a custom model can use the fields\n`instructionSet`, `oneQubitMeasurementTime`,\n`twoQubitJointMeasurementTime`, `oneQubitGateTime`, `twoQubitGateTime`,\n`tGateTime`, `oneQubitMeasurementErrorRate`,\n`twoQubitJointMeasurementErrorRate`, `oneQubitGateErrorRate`,\n`twoQubitGateErrorRate`, `tGateErrorRate`, and `idleErrorRate`.\nMeasurement-error fields accept either one probability or an object with\n`process` and `readout` probabilities. Time values use the duration strings\naccepted by QDK.\n\n### Error correction\n\n`qecScheme.name` accepts `surface_code` or `floquet_code`. A custom scheme can\ninstead use `errorCorrectionThreshold`, `crossingPrefactor`,\n`distanceCoefficientPower`, `logicalCycleTime`,\n`physicalQubitsPerLogicalQubit`, and `maxCodeDistance`. Formula fields use the\nexpression syntax accepted by the QDK estimator.\n\n### Error budget and constraints\n\n`errorBudget` may be a probability strictly between zero and one, or an object\nwith `logical`, `tstates`, and `rotations` probabilities. A partition describes\nhow the total failure budget is divided among logical errors, distilled\nT states, and synthesized rotations.\n\n`constraints` may contain `logicalDepthFactor`, `maxTFactories`, `maxDuration`,\nand `maxPhysicalQubits`. `maxDuration` and `maxPhysicalQubits` are alternative\nspace\u002Ftime constraints and cannot be supplied together.\n\n### Distillation units\n\nEach `distillationUnitSpecifications` item can contain `name`, `displayName`,\n`numInputTs`, `numOutputTs`, `failureProbabilityFormula`,\n`outputErrorRateFormula`, `physicalQubitSpecification`,\n`logicalQubitSpecification`, and\n`logicalQubitSpecificationFirstRoundOverride`. A protocol-specific\nspecification supplies `numUnitQubits` and `durationInQubitCycleTime`.\n\nCustom qubit, QEC, formula, and distillation settings are coupled. Generate them\nonly from a coherent hardware model; do not combine individually plausible\nvalues without checking the QDK estimator's validation rules.\n\n## Results\n\nA single parameter object returns one estimator result. A parameter list returns\na list in the same order. Depending on `estimateType`, a result can include a\nsingle selected estimate or frontier entries. Common sections include logical\ncounts, physical counts, formatted counts, logical-qubit\u002FQEC information,\nT-factory data, report data, and assumptions. Inspect status and error fields\nbefore reading resource counts.\n\n## Path 2: Generate direct `qdk.qre` code\n\nWhen the stored-circuit tool is too restrictive, generate a Python version of\nthe workflow using `qdk.qre` directly. First inspect the installed `qdk.qre`\nmodules, callable signatures, model classes, query constructors, instruction\nidentifiers, property keys, and result-table methods. Do not infer the current\nAPI from this skill alone: QDK evolves independently of QDK Chemistry.\n\nAfter that inspection, generated code should have roughly this shape, adapted\nto the APIs actually present and with models, ranges, and transforms chosen for\nthe requested study:\n\n```python\nfrom qdk.qre import LatticeSurgery, PSSPC, estimate, plot_estimates\nfrom qdk.qre.models import Majorana, RoundBasedFactory, ThreeAux\n\n# `circuit` may be loaded from a QDK Chemistry project or produced by a\n# chemistry circuit-building workflow.\napplication = circuit.get_qre_application()\n\n# Describe physical operations independently of the logical circuit.\narchitecture = Majorana(error_rate=physical_error_rate)\n\n# Transform application operations into logical operations supported by the\n# selected code. Lists ask QRE to enumerate alternatives.\ntrace_query = (\n   application.q()\n   * PSSPC.q(num_ts_per_rotation=rotation_t_counts)\n   * LatticeSurgery.q(slow_down_factor=slow_down_factors)\n)\n\n# Enumerate compatible compute-code and magic-state-factory implementations.\ncompute_code = ThreeAux.q(distance=compute_distances)\nfactory_code = ThreeAux.q(distance=factory_distances)\nisa_query = compute_code * RoundBasedFactory.q(\n   code_query=factory_code,\n   use_cache=True,\n)\n\nresults = estimate(\n   application=application,\n   architecture=architecture,\n   isa_query=isa_query,\n   trace_query=trace_query,\n   max_error=max_error,\n   use_graph=use_graph,\n   name=study_name,\n)\n\n# The table can be enriched, inspected, compared, or plotted.\nframe = results.as_frame()\nfigure = plot_estimates([results], runtime_unit=\"s\")\n```\n\nThis is a code-generation path, not another MCP estimation function. The code\nis intentionally a skeleton: an agent should use what it learned from the\ninstalled QDK to replace its Majorana, `ThreeAux`, factory, transform, and sweep\nchoices when the requested hardware model or scientific comparison differs.\n\nConceptually, generated code can:\n\n1. Load or construct a QDK Chemistry `Circuit`, then call\n   `get_qre_application()`.\n2. Select or construct an architecture containing physical-operation times and\n   error rates.\n3. Build a trace query from the application and compatible transforms. This may\n   sweep rotation-synthesis choices with `PSSPC` and logical-operation timing\n   choices with `LatticeSurgery` when the installed API supports them.\n4. Build an ISA query from compatible QEC and factory models. This may sweep\n   compute-code distances independently from factory code distances using\n   `ThreeAux` and `RoundBasedFactory` when those are suitable and available.\n5. Call `qdk.qre.estimate` with the application, architecture, ISA query, trace\n   query, and error limit.\n6. Enrich the returned table with query provenance and derived properties,\n   convert it to a data frame, compare several tables, or use `plot_estimates`\n   to visualize physical-qubit\u002Fruntime Pareto fronts.\n\nDirect QDK code permits more customization than `estimate_circuit`: an agent\ncan vary trace transforms, instruction implementations, code and factory\nfamilies, independent parameter sweeps, architecture models, error composition,\npost-processing, graph pruning, custom result columns, and comparative plots.\nThe generated architecture and query graph should follow the scientific\nquestion rather than copy the illustrative skeleton unchanged.\n\nBefore generating code, inspect the installed `qdk.qre` API and the relevant\nmodel\u002Fquery classes because this interface evolves independently of the stored\ncircuit format. Keep architecture, QEC, factory, and trace assumptions visible\nin generated output. Use `use_graph=False` when completeness of the enumerated\nPareto frontier is more important than pruning cost.\n","# Circuit Resource Estimation\n\nChoose between exactly two paths:\n\n1. **Stored-circuit tool path** — call `estimate_circuit` with the parameter\n   objects documented below. Use this for a concise estimate of an existing\n   project circuit.\n2. **Direct QDK code path** — generate Python that uses `qdk.qre` directly,\n   after inspecting the installed QDK API. Use this when the user needs more\n   control over architectures, trace transforms, ISA enumeration, result\n   columns, comparisons, or plots.\n\nDo not present these as successive steps. They are alternative interfaces for\ndifferent levels of control.\n\n## Path 1: Estimate a stored circuit\n\nUse `estimate_circuit` to apply the estimator exposed by a stored QDK Chemistry\n`Circuit`. The tool returns its result inline and does not create another\nproject artifact.\n\nThe tool accepts `project_name`, `circuit_filename`, and optional `params`.\n`params` is either one estimator-parameter object or a list of objects for a\nbatch comparison. Omit it to use QDK defaults. MCP calls use the camel-case JSON\nfield names below; Python code that constructs `EstimatorParams` uses the\ncorresponding snake-case attributes.\n\n## Parameter objects\n\nA parameter object may contain:\n\n| Field | Purpose |\n|---|---|\n| `qubitParams` | Selects a built-in physical-qubit model or describes a custom one. |\n| `qecScheme` | Selects a built-in error-correction scheme or describes a custom one. |\n| `distillationUnitSpecifications` | Supplies custom magic-state distillation units. |\n| `constraints` | Restricts runtime, physical qubits, factories, or logical depth. |\n| `errorBudget` | Sets the total error budget or partitions it by source. |\n| `estimateType` | Requests `singlePoint` or `frontier`. |\n\nA list applies independent parameter objects to the same circuit. Use it to\ncompare assumptions rather than making separate tool calls.\n\n### Physical-qubit parameters\n\n`qubitParams.name` accepts these built-in models:\n\n- `qubit_gate_us_e3`\n- `qubit_gate_us_e4`\n- `qubit_gate_ns_e3`\n- `qubit_gate_ns_e4`\n- `qubit_maj_ns_e4`\n- `qubit_maj_ns_e6`\n\nInstead of `name`, a custom model can use the fields\n`instructionSet`, `oneQubitMeasurementTime`,\n`twoQubitJointMeasurementTime`, `oneQubitGateTime`, `twoQubitGateTime`,\n`tGateTime`, `oneQubitMeasurementErrorRate`,\n`twoQubitJointMeasurementErrorRate`, `oneQubitGateErrorRate`,\n`twoQubitGateErrorRate`, `tGateErrorRate`, and `idleErrorRate`.\nMeasurement-error fields accept either one probability or an object with\n`process` and `readout` probabilities. Time values use the duration strings\naccepted by QDK.\n\n### Error correction\n\n`qecScheme.name` accepts `surface_code` or `floquet_code`. A custom scheme can\ninstead use `errorCorrectionThreshold`, `crossingPrefactor`,\n`distanceCoefficientPower`, `logicalCycleTime`,\n`physicalQubitsPerLogicalQubit`, and `maxCodeDistance`. Formula fields use the\nexpression syntax accepted by the QDK estimator.\n\n### Error budget and constraints\n\n`errorBudget` may be a probability strictly between zero and one, or an object\nwith `logical`, `tstates`, and `rotations` probabilities. A partition describes\nhow the total failure budget is divided among logical errors, distilled\nT states, and synthesized rotations.\n\n`constraints` may contain `logicalDepthFactor`, `maxTFactories`, `maxDuration`,\nand `maxPhysicalQubits`. `maxDuration` and `maxPhysicalQubits` are alternative\nspace\u002Ftime constraints and cannot be supplied together.\n\n### Distillation units\n\nEach `distillationUnitSpecifications` item can contain `name`, `displayName`,\n`numInputTs`, `numOutputTs`, `failureProbabilityFormula`,\n`outputErrorRateFormula`, `physicalQubitSpecification`,\n`logicalQubitSpecification`, and\n`logicalQubitSpecificationFirstRoundOverride`. A protocol-specific\nspecification supplies `numUnitQubits` and `durationInQubitCycleTime`.\n\nCustom qubit, QEC, formula, and distillation settings are coupled. Generate them\nonly from a coherent hardware model; do not combine individually plausible\nvalues without checking the QDK estimator's validation rules.\n\n## Results\n\nA single parameter object returns one estimator result. A parameter list returns\na list in the same order. Depending on `estimateType`, a result can include a\nsingle selected estimate or frontier entries. Common sections include logical\ncounts, physical counts, formatted counts, logical-qubit\u002FQEC information,\nT-factory data, report data, and assumptions. Inspect status and error fields\nbefore reading resource counts.\n\n## Path 2: Generate direct `qdk.qre` code\n\nWhen the stored-circuit tool is too restrictive, generate a Python version of\nthe workflow using `qdk.qre` directly. First inspect the installed `qdk.qre`\nmodules, callable signatures, model classes, query constructors, instruction\nidentifiers, property keys, and result-table methods. Do not infer the current\nAPI from this skill alone: QDK evolves independently of QDK Chemistry.\n\nAfter that inspection, generated code should have roughly this shape, adapted\nto the APIs actually present and with models, ranges, and transforms chosen for\nthe requested study:\n\n```python\nfrom qdk.qre import LatticeSurgery, PSSPC, estimate, plot_estimates\nfrom qdk.qre.models import Majorana, RoundBasedFactory, ThreeAux\n\n# `circuit` may be loaded from a QDK Chemistry project or produced by a\n# chemistry circuit-building workflow.\napplication = circuit.get_qre_application()\n\n# Describe physical operations independently of the logical circuit.\narchitecture = Majorana(error_rate=physical_error_rate)\n\n# Transform application operations into logical operations supported by the\n# selected code. Lists ask QRE to enumerate alternatives.\ntrace_query = (\n   application.q()\n   * PSSPC.q(num_ts_per_rotation=rotation_t_counts)\n   * LatticeSurgery.q(slow_down_factor=slow_down_factors)\n)\n\n# Enumerate compatible compute-code and magic-state-factory implementations.\ncompute_code = ThreeAux.q(distance=compute_distances)\nfactory_code = ThreeAux.q(distance=factory_distances)\nisa_query = compute_code * RoundBasedFactory.q(\n   code_query=factory_code,\n   use_cache=True,\n)\n\nresults = estimate(\n   application=application,\n   architecture=architecture,\n   isa_query=isa_query,\n   trace_query=trace_query,\n   max_error=max_error,\n   use_graph=use_graph,\n   name=study_name,\n)\n\n# The table can be enriched, inspected, compared, or plotted.\nframe = results.as_frame()\nfigure = plot_estimates([results], runtime_unit=\"s\")\n```\n\nThis is a code-generation path, not another MCP estimation function. The code\nis intentionally a skeleton: an agent should use what it learned from the\ninstalled QDK to replace its Majorana, `ThreeAux`, factory, transform, and sweep\nchoices when the requested hardware model or scientific comparison differs.\n\nConceptually, generated code can:\n\n1. Load or construct a QDK Chemistry `Circuit`, then call\n   `get_qre_application()`.\n2. Select or construct an architecture containing physical-operation times and\n   error rates.\n3. Build a trace query from the application and compatible transforms. This may\n   sweep rotation-synthesis choices with `PSSPC` and logical-operation timing\n   choices with `LatticeSurgery` when the installed API supports them.\n4. Build an ISA query from compatible QEC and factory models. This may sweep\n   compute-code distances independently from factory code distances using\n   `ThreeAux` and `RoundBasedFactory` when those are suitable and available.\n5. Call `qdk.qre.estimate` with the application, architecture, ISA query, trace\n   query, and error limit.\n6. Enrich the returned table with query provenance and derived properties,\n   convert it to a data frame, compare several tables, or use `plot_estimates`\n   to visualize physical-qubit\u002Fruntime Pareto fronts.\n\nDirect QDK code permits more customization than `estimate_circuit`: an agent\ncan vary trace transforms, instruction implementations, code and factory\nfamilies, independent parameter sweeps, architecture models, error composition,\npost-processing, graph pruning, custom result columns, and comparative plots.\nThe generated architecture and query graph should follow the scientific\nquestion rather than copy the illustrative skeleton unchanged.\n\nBefore generating code, inspect the installed `qdk.qre` API and the relevant\nmodel\u002Fquery classes because this interface evolves independently of the stored\ncircuit format. Keep architecture, QEC, factory, and trace assumptions visible\nin generated output. Use `use_graph=False` when completeness of the enumerated\nPareto frontier is more important than pruning cost.\n",{"name":5,"version":40,"description":7},"v2.3.1","main","2cea285592fe2b5b6cff541edae0f1fb05c45fb4","copilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fresource-estimation",40,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry","https:\u002F\u002Fmicrosoft.github.io\u002Fqdk-chemistry\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 14:32:36",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add microsoft\u002Fqdk-chemistry --skill resource-estimation",{"tool":57,"command":58},"bunx","bunx skills add microsoft\u002Fqdk-chemistry --skill resource-estimation",{"tool":60,"command":61},"pnpm","pnpm dlx skills add microsoft\u002Fqdk-chemistry --skill resource-estimation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fresource-estimation\u002FSKILL.md",true,[65,71,75],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fexamples.md","REFERENCE","参考文档",1013,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fskywalking-banyandb\u002Fblob\u002Fmain\u002Fskills\u002Fbydbql\u002Freferences\u002Fexamples.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fsafety.md",449,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fskywalking-banyandb\u002Fblob\u002Fmain\u002Fskills\u002Fbydbql\u002Freferences\u002Fsafety.md",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fsyntax.md",12041,"https:\u002F\u002Fgithub.com\u002Fapache\u002Fskywalking-banyandb\u002Fblob\u002Fmain\u002Fskills\u002Fbydbql\u002Freferences\u002Fsyntax.md",[80,94,106,119,134,144],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":91,"publishedAt":35},"01M69BBXVWD81T6JK7PHBTFFTR","visualization","Describes QDK Chemistry visualization tools, their inputs, and their outputs.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fvisualization\u002FSKILL.md",[86],{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",[82,92,93],"Tools","outputs",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":35},"01M69BBSNFR7ENF192CZEY631G","remote-execution","Describes the QDK Chemistry remote execution API and job lifecycle.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fremote-execution\u002FSKILL.md",[],[101,102,103,104,105],"remote","execution","remote execution","lifecycle","api",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":35},"01M69BBR8WK693P0NCD70CXHPX","qdk-chemistry-overview","Describes the QDK Chemistry interfaces and the artifact types they read and write.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fqdk-chemistry-overview\u002FSKILL.md",[],[113,114,115,116,117,118],"overview","qdk chemistry overview","write","read","types","artifact",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":128,"publishedAt":35},"01M69BBPRPDBZJ3Q535X6SGSCK","qdk-chemistry-mcp","Describes the QDK Chemistry MCP tool interface, return envelope, and tool categories.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fqdk-chemistry-mcp\u002FSKILL.md",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000023","Skill与智能体开发",[129,130,131,132,133],"qdk chemistry mcp","MCP","interface","tool","categories",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":35},"01M69BBN3NVVND6YHA88F7C7RQ","qdk-chemistry-coding","Describes the Python API for discovering, configuring, and executing QDK Chemistry algorithms.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002Fcopilot-plugins\u002Fqdk-chemistry\u002Fskills\u002Fqdk-chemistry-coding\u002FSKILL.md",[],[141,142,105,143,29,21],"coding","qdk chemistry coding","algorithms",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":35},"01M69BBKDAJRQABT35BEAS0R4Z","memory-aware-build","Compile QDK Chemistry with memory-aware parallelism. Use this skill whenever building the C++ code, Python package, or dependencies, especially on machines with limited RAM or after an out-of-memory compiler failure.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fqdk-chemistry\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmemory-aware-build\u002FSKILL.md",[],[151,152,153,154,21,155,23,156,157,158,159,25],"memory","memory aware build","build","with","compiler","c++","compile","dependencies","package"]