@chongyan/autospec 1.0.2 → 1.0.3

package/plugins/benchmarks/templates/commands/test-template.yaml

@@ -1,149 +0,0 @@
-# AutoSpec Command Benchmark Template - Test
-# 适用于: 测试 test 命令（验证+修复+评测）
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "command-test"
-description: "Test 命令基准测试 - 统一测试命令"
-
-type: command
-target: test
-
-testCases:
-  - name: "validation-only"
-    input: "/autospec:test"
-    complexity: 1
-    expectedBehaviors:
-      - "执行编译检查"
-      - "执行测试"
-      - "执行 Lint 检查"
-      - "执行类型检查"
-    expectedOutput:
-      - "验证报告"
-      - "各项验证结果"
-    successCriteria:
-      - "验证步骤完整"
-      - "结果报告清晰"
-    qualityMetrics:
-      - "验证执行率 = 100%"
-      - "报告完整率 >= 95%"
-    maxDuration: 300
-
-  - name: "validation-with-fix"
-    input: "/autospec:test --fix"
-    complexity: 3
-    expectedBehaviors:
-      - "执行 Layer1 验证"
-      - "问题分析"
-      - "修复分类"
-      - "执行修复"
-      - "效果验证"
-    expectedOutput:
-      - "验证报告"
-      - "问题分析报告"
-      - "修复记录"
-    successCriteria:
-      - "问题分类准确"
-      - "修复有效"
-      - "退化检测正确"
-    qualityMetrics:
-      - "修复有效率 >= 85%"
-      - "退化检出率 = 100%"
-    maxDuration: 600
-
-  - name: "subsystem-test"
-    input: "/autospec:test --subsystem=backend --fix"
-    complexity: 3
-    expectedBehaviors:
-      - "读取 config.json 获取子系统配置"
-      - "只验证指定子系统"
-      - "执行子系统修复"
-    successCriteria:
-      - "子系统识别正确"
-      - "验证范围准确"
-    qualityMetrics:
-      - "子系统验证准确率 = 100%"
-    maxDuration: 450
-
-  - name: "ai-evaluation"
-    input: "/autospec:test --scope=evaluation"
-    complexity: 5
-    expectedBehaviors:
-      - "检测 AI/模型组件"
-      - "加载评测数据集"
-      - "执行效果评测"
-      - "生成评测报告"
-    expectedOutput:
-      - "评测报告"
-      - "指标结果"
-      - "Badcase 分析"
-    successCriteria:
-      - "评测方案执行完整"
-      - "指标计算准确"
-    qualityMetrics:
-      - "评测完整率 = 100%"
-      - "Badcase 检出率 >= 90%"
-    maxDuration: 900
-
-  - name: "git-repo-test"
-    input: "/autospec:test https://github.com/{org}/{repo} --branch main"
-    complexity: 5
-    expectedBehaviors:
-      - "克隆 git 仓库"
-      - "检出指定分支"
-      - "执行验证"
-    successCriteria:
-      - "git 克隆成功"
-      - "验证执行完整"
-    qualityMetrics:
-      - "仓库测试成功率 >= 95%"
-    maxDuration: 600
-
-  - name: "deep-analysis"
-    input: "/autospec:test --deep --fix"
-    complexity: 5
-    expectedBehaviors:
-      - "执行完整验证"
-      - "深度问题分析"
-      - "根因识别"
-      - "全面修复"
-    expectedOutput:
-      - "深度分析报告"
-      - "根因分析"
-      - "质量评分"
-    successCriteria:
-      - "根因识别准确"
-      - "质量提升明显"
-    qualityMetrics:
-      - "根因识别率 >= 90%"
-      - "质量提升 >= 10%"
-    maxDuration: 900
-
-  - name: "unit-test-scope"
-    input: "/autospec:test --scope=unit"
-    complexity: 1
-    expectedBehaviors:
-      - "只执行单元测试"
-      - "跳过集成测试"
-    successCriteria:
-      - "测试范围准确"
-    qualityMetrics:
-      - "单元测试覆盖率 >= 95%"
-    maxDuration: 180
-
-  - name: "integration-test-scope"
-    input: "/autospec:test --scope=integration --fix"
-    complexity: 3
-    expectedBehaviors:
-      - "执行集成测试"
-      - "识别集成问题"
-      - "修复集成问题"
-    successCriteria:
-      - "集成测试执行完整"
-    qualityMetrics:
-      - "集成测试覆盖率 = 100%"
-    maxDuration: 450
-
-successCriteria:
-  passRate: 90
-  avgDuration: 450

package/plugins/benchmarks/templates/pipeline/agile-template.yaml

@@ -1,84 +0,0 @@
-# AutoSpec Pipeline Benchmark Template - Agile
-# 适用于: 敏捷迭代开发模式
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "agile-{project-name}"
-description: "敏捷迭代开发模式 benchmark"
-
-type: pipeline
-scenario:
-  name: "敏捷迭代功能"
-  input: "在现有系统中添加一个评论功能"
-  complexity: 3
-  expectedStages:
-    - exploration
-    - requirement
-    - design
-    - implementation
-    - testing
-
-stageCriteria:
-  exploration:
-    expectedArtifacts:
-      - "clarifications.md"
-    layer1Check:
-      - "澄清问题已记录"
-    layer2Check:
-      - "问题质量"
-    maxDuration: 180
-
-  requirement:
-    expectedArtifacts:
-      - "requirement.md"
-    layer1Check:
-      - "字段完整性 >= 85%"
-    layer2Check:
-      - "需求清晰度"
-    maxDuration: 300
-
-  design:
-    expectedArtifacts:
-      - "design.md"
-    layer1Check:
-      - "设计文档存在"
-    layer2Check:
-      - "设计简洁性"
-    maxDuration: 300
-
-  implementation:
-    expectedArtifacts:
-      - "代码文件"
-    layer1Check:
-      - "编译通过"
-      - "测试通过"
-    layer2Check:
-      - "代码简洁"
-    maxDuration: 600
-
-  testing:
-    expectedArtifacts:
-      - "test-report.md"
-    layer1Check:
-      - "测试通过"
-    layer2Check:
-      - "覆盖关键路径"
-    maxDuration: 300
-
-pipelineMetrics:
-  expected:
-    totalDuration: 1680
-    maxRollbacks: 1
-    layer1PassRate: 85
-    layer2PassRate: 80
-    artifactCompletionRate: 90
-
-qualityThresholds:
-  pass:
-    overallScore: 75
-    layer1PassRate: 80
-    layer2PassRate: 75
-  excellent:
-    overallScore: 85
-    layer1PassRate: 90
-    layer2PassRate: 85

package/plugins/benchmarks/templates/pipeline/experiment-template.yaml

@@ -1,92 +0,0 @@
-# AutoSpec Pipeline Benchmark Template - Experiment
-# 适用于: 技术探索 / AI 功能验证
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "experiment-{project-name}"
-description: "实验模式 benchmark"
-
-type: pipeline
-scenario:
-  name: "技术探索实验"
-  input: "验证 {technology} 用于 {use-case} 的可行性"
-  complexity: 3
-  expectedStages:
-    - requirement
-    - design
-    - implement
-    - test
-    - deliver
-
-stageCriteria:
-  requirement:
-    expectedArtifacts:
-      - "specs/experiment/requirement.md"
-      - "specs/experiment/hypothesis.md"
-    layer1Check:
-      - "实验目标清晰"
-      - "假设可验证"
-    layer2Check:
-      - "成功指标明确"
-    maxDuration: 300
-
-  design:
-    expectedArtifacts:
-      - "specs/experiment/design.md"
-      - "specs/experiment/evaluation.md"
-    layer1Check:
-      - "实验设计合理"
-      - "评测方案可行"
-    layer2Check:
-      - "备选方案准备"
-    maxDuration: 450
-
-  implement:
-    expectedArtifacts:
-      - "src/ 原型代码"
-      - "experiments/ 实验脚本"
-    layer1Check:
-      - "原型可运行"
-      - "实验脚本可执行"
-    layer2Check:
-      - "数据收集完整"
-    maxDuration: 900
-
-  test:
-    expectedArtifacts:
-      - "experiments/results.md"
-    layer1Check:
-      - "实验执行完成"
-      - "结果记录完整"
-    layer2Check:
-      - "效果评估客观"
-    maxDuration: 600
-
-  deliver:
-    expectedArtifacts:
-      - "experiments/conclusion.md"
-    layer1Check:
-      - "结论清晰"
-    layer2Check:
-      - "知识沉淀完整"
-    maxDuration: 300
-
-pipelineMetrics:
-  expected:
-    totalDuration: 2550
-    maxRollbacks: 1
-    layer1PassRate: 85
-    layer2PassRate: 80
-    artifactCompletionRate: 90
-    successRate: 70
-    learningOutcome: 80
-
-qualityThresholds:
-  pass:
-    overallScore: 75
-    layer1PassRate: 80
-    layer2PassRate: 75
-  excellent:
-    overallScore: 85
-    layer1PassRate: 90
-    layer2PassRate: 85

package/plugins/benchmarks/templates/pipeline/hotfix-template.yaml

@@ -1,81 +0,0 @@
-# AutoSpec Pipeline Benchmark Template - Hotfix
-# 适用于: 紧急 Bug 修复模式
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "hotfix-{project-name}"
-description: "热修复模式 benchmark"
-
-type: pipeline
-scenario:
-  name: "紧急 Bug 修复"
-  input: "修复生产环境 {bug-description} 的紧急 bug"
-  complexity: 1
-  expectedStages:
-    - requirement
-    - implement
-    - test
-    - deliver
-
-stageCriteria:
-  requirement:
-    expectedArtifacts:
-      - "specs/hotfix-{id}/bug-report.md"
-    layer1Check:
-      - "bug 描述清晰"
-      - "复现步骤完整"
-    layer2Check:
-      - "影响范围明确"
-      - "快速确认"
-    maxDuration: 180
-
-  implement:
-    expectedArtifacts:
-      - "最小化修复代码"
-      - "回归测试"
-    layer1Check:
-      - "修复有效"
-      - "无新 bug 引入"
-    layer2Check:
-      - "最小化改动"
-    maxDuration: 300
-
-  test:
-    expectedArtifacts:
-      - "快速测试报告"
-    layer1Check:
-      - "bug 验证通过"
-      - "关键路径回归通过"
-    layer2Check:
-      - "测试覆盖合理"
-    maxDuration: 180
-
-  deliver:
-    expectedArtifacts:
-      - "发布说明"
-      - "复盘报告"
-    layer1Check:
-      - "发布就绪"
-    layer2Check:
-      - "复盘完整"
-    maxDuration: 120
-
-pipelineMetrics:
-  expected:
-    totalDuration: 780
-    maxRollbacks: 0
-    layer1PassRate: 95
-    layer2PassRate: 90
-    artifactCompletionRate: 100
-    fixTime: 300
-    deployTime: 120
-
-qualityThresholds:
-  pass:
-    overallScore: 90
-    layer1PassRate: 95
-    layer2PassRate: 90
-  excellent:
-    overallScore: 95
-    layer1PassRate: 100
-    layer2PassRate: 95

package/plugins/benchmarks/templates/pipeline/waterfall-template.yaml

@@ -1,106 +0,0 @@
-# AutoSpec Pipeline Benchmark Template - Waterfall
-# 适用于: 标准瀑布流开发模式
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "waterfall-{project-name}"
-description: "标准瀑布流开发模式 benchmark"
-
-type: pipeline
-scenario:
-  name: "标准功能开发"
-  input: "实现一个用户管理模块，包含增删改查功能"
-  complexity: 5
-  expectedStages:
-    - exploration
-    - requirement
-    - design
-    - implementation
-    - testing
-    - delivery
-
-stageCriteria:
-  exploration:
-    expectedArtifacts:
-      - "clarifications.md"
-      - "requirement.md"
-    layer1Check:
-      - "文件存在性"
-      - "Schema 合规"
-    layer2Check:
-      - "需求完整性"
-      - "边界条件覆盖"
-    maxDuration: 300
-
-  requirement:
-    expectedArtifacts:
-      - "requirement.md"
-    layer1Check:
-      - "字段完整性 >= 90%"
-      - "无空值字段"
-    layer2Check:
-      - "需求可测试性"
-      - "验收标准明确"
-    maxDuration: 600
-
-  design:
-    expectedArtifacts:
-      - "design.md"
-      - "contracts/api.yaml"
-    layer1Check:
-      - "设计文档完整"
-      - "API 契约规范"
-    layer2Check:
-      - "架构合理性"
-      - "可扩展性评估"
-    maxDuration: 900
-
-  implementation:
-    expectedArtifacts:
-      - "代码文件"
-    layer1Check:
-      - "编译通过"
-      - "单元测试通过"
-      - "Lint 无错误"
-    layer2Check:
-      - "代码质量"
-      - "设计忠实度"
-    maxDuration: 1800
-
-  testing:
-    expectedArtifacts:
-      - "test-report.md"
-    layer1Check:
-      - "测试用例执行"
-      - "覆盖率达标"
-    layer2Check:
-      - "测试充分性"
-      - "边界覆盖"
-    maxDuration: 600
-
-  delivery:
-    expectedArtifacts:
-      - "delivery.md"
-    layer1Check:
-      - "文档完整"
-    layer2Check:
-      - "发布就绪性"
-    maxDuration: 300
-
-pipelineMetrics:
-  expected:
-    totalDuration: 4500
-    maxRollbacks: 2
-    layer1PassRate: 90
-    layer2PassRate: 85
-    artifactCompletionRate: 95
-
-qualityThresholds:
-  pass:
-    overallScore: 80
-    layer1PassRate: 85
-    layer2PassRate: 80
-  excellent:
-    overallScore: 90
-    layer1PassRate: 95
-    layer2PassRate: 90

package/plugins/benchmarks/templates/skills/agile-iteration-template.yaml

@@ -1,78 +0,0 @@
-# AutoSpec Skill Benchmark Template - Agile-Iteration
-# 适用于: 测试 agile-iteration skill
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "skill-agile-iteration"
-description: "Agile-Iteration Skill 基准测试 - 敏捷故事循环"
-
-type: skill
-target: agile-iteration
-
-testCases:
-  - name: "single-story"
-    input:
-      context: "使用敏捷模式开发单个用户故事"
-    complexity: 1
-    expectedBehaviors:
-      - "加载故事列表"
-      - "执行故事设计"
-      - "执行故事编码"
-      - "执行故事审查"
-      - "更新故事状态"
-    expectedOutput:
-      - "stories/{id}/design.md"
-      - "代码变更"
-      - "更新后的 stories.md"
-    successCriteria:
-      - "故事设计完整"
-      - "审查通过"
-      - "状态更新正确"
-    qualityMetrics:
-      - "故事完成率 = 100%"
-      - "验证通过率 >= 90%"
-    maxDuration: 600
-
-  - name: "multi-story-sequential"
-    input:
-      context: "使用敏捷模式顺序执行多个用户故事"
-    complexity: 3
-    expectedBehaviors:
-      - "加载故事列表"
-      - "按优先级排序"
-      - "顺序执行每个故事"
-      - "集成测试"
-    expectedOutput:
-      - "各故事设计文档"
-      - "集成测试报告"
-    successCriteria:
-      - "所有故事完成"
-      - "集成测试通过"
-    qualityMetrics:
-      - "故事完成率 = 100%"
-      - "集成测试通过率 >= 90%"
-    maxDuration: 1200
-
-  - name: "parallel-stories"
-    input:
-      context: "使用敏捷模式并行执行无依赖的用户故事"
-    complexity: 5
-    expectedBehaviors:
-      - "分析故事依赖关系"
-      - "识别可并行故事"
-      - "并行执行故事"
-      - "处理代码冲突"
-    expectedOutput:
-      - "并行执行报告"
-      - "冲突检测结果"
-    successCriteria:
-      - "依赖分析正确"
-      - "并行执行成功"
-    qualityMetrics:
-      - "并行效率提升 >= 30%"
-      - "冲突检测准确率 >= 95%"
-    maxDuration: 900
-
-successCriteria:
-  passRate: 85
-  avgFieldCompletion: 90

package/plugins/benchmarks/templates/skills/benchmark-executor-template.yaml

@@ -1,114 +0,0 @@
-# AutoSpec Skill Benchmark Template - Benchmark-Executor
-# 适用于: 测试 benchmark-executor skill
-# init 后复制到 .autospec/benchmarks/ 后按需修改
-
-version: "1.0"
-name: "skill-benchmark-executor"
-description: "Benchmark-Executor Skill 基准测试"
-
-type: skill
-target: benchmark-executor
-
-testCases:
-  - name: "requirement-stage-evaluation"
-    input:
-      context: "执行 requirement 阶段 benchmarks 评测"
-    complexity: 3
-    expectedBehaviors:
-      - "加载 benchmarks 文件"
-      - "检测阶段产出物"
-      - "执行 Layer1 Schema 校验"
-      - "执行 Layer2 AI 审查"
-      - "计算评分与等级"
-    expectedOutput:
-      - "评测报告"
-      - "改进建议清单"
-    successCriteria:
-      - "benchmarks 加载完整"
-      - "Layer1+Layer2 执行完成"
-      - "评分计算正确"
-    qualityMetrics:
-      - "benchmarks 加载率 = 100%"
-      - "Layer1 执行率 = 100%"
-      - "评分准确率 >= 90%"
-    maxDuration: 600
-
-  - name: "design-stage-evaluation"
-    input:
-      context: "执行 design 阶段 benchmarks 评测"
-    complexity: 3
-    expectedBehaviors:
-      - "加载 design benchmarks"
-      - "检测产出物"
-      - "执行架构设计完整性检查"
-      - "执行设计-需求一致性检查"
-    expectedOutput:
-      - "design 评测报告"
-      - "一致性检查结果"
-    successCriteria:
-      - "产出物检测完整"
-      - "一致性检查执行"
-    qualityMetrics:
-      - "产出物检测率 = 100%"
-      - "一致性检查执行率 = 100%"
-    maxDuration: 600
-
-  - name: "implementation-stage-evaluation"
-    input:
-      context: "执行 implementation 阶段 benchmarks 评测"
-    complexity: 5
-    expectedBehaviors:
-      - "加载 implementation benchmarks"
-      - "执行 Layer1 验证"
-      - "执行代码-设计一致性检查"
-      - "执行代码质量基准检查"
-    expectedOutput:
-      - "implementation 评测报告"
-      - "代码质量报告"
-      - "覆盖率报告"
-    successCriteria:
-      - "Layer1 验证真实执行"
-      - "代码质量检查完整"
-    qualityMetrics:
-      - "Layer1 执行率 = 100%"
-      - "代码检查完整率 >= 90%"
-    maxDuration: 900
-
-  - name: "multi-system-evaluation"
-    input:
-      context: "执行多系统项目 benchmarks"
-    complexity: 5
-    expectedBehaviors:
-      - "识别所有子系统"
-      - "执行接口契约一致性检查"
-      - "执行跨系统设计一致性检查"
-    expectedOutput:
-      - "多系统评测报告"
-      - "契约一致性检查结果"
-    successCriteria:
-      - "子系统识别完整"
-      - "契约一致性检查执行"
-    qualityMetrics:
-      - "子系统识别率 = 100%"
-      - "契约检查执行率 = 100%"
-    maxDuration: 900
-
-  - name: "auto-trigger-evaluation"
-    input:
-      context: "产出物变更时自动触发 benchmarks"
-    complexity: 3
-    expectedBehaviors:
-      - "检测产出物变更"
-      - "自动触发 benchmarks 评测"
-      - "执行防抖处理"
-    successCriteria:
-      - "变更检测准确"
-      - "自动触发执行"
-    qualityMetrics:
-      - "变更检测率 = 100%"
-      - "自动触发执行率 = 100%"
-    maxDuration: 300
-
-successCriteria:
-  passRate: 85
-  avgFieldCompletion: 90