ln-513-auto-test-planner

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Automated Test Planner

自动化测试规划器

Creates Story test task with comprehensive automated test coverage (E2E/Integration/Unit) based on Risk-Based Testing methodology and REAL manual testing results.
基于基于风险的测试方法论和实际手动测试结果,创建具备全面自动化测试覆盖(E2E/集成/单元测试)的Story测试任务。

Purpose & Scope

目的与范围

  • Create comprehensive test task for Story automation
  • Calculate risk-based priorities (Impact × Probability)
  • Generate 11-section test plan from manual test results
  • Delegate to ln-301-task-creator (CREATE) or ln-302-task-replanner (REPLAN)
  • NOT for: manual testing (ln-512), research (ln-511), orchestration (ln-510)
  • 创建具备全面自动化测试覆盖的Story测试任务
  • 计算基于风险的测试优先级(影响 × 概率)
  • 生成基于手动测试结果的11节测试计划
  • 委派任务至ln-301-task-creator(创建模式)或ln-302-task-replanner(重规划模式)
  • 不适用场景:手动测试(ln-512)、研究(ln-511)、编排(ln-510)

When to Use This Skill

何时使用该技能

This skill should be used when:
  • Invoked by ln-510-test-planner after ln-511 research and ln-512 manual testing
  • All implementation tasks in Story are Done
  • Manual testing results documented in Linear comment (from ln-512)
  • Research findings available in Linear comment (from ln-511)
Prerequisites:
  • All implementation Tasks in Story status = Done
  • ln-511-test-researcher completed (research comment exists)
  • ln-512-manual-tester completed (manual test results in Linear comment)
Automation: Supports
autoApprove: true
(default when invoked by ln-510) to skip manual confirmation.
应在以下场景使用本技能:
  • 由ln-510-test-planner调用,且在ln-511研究和ln-512手动测试完成之后
  • Story中的所有实现任务均已完成
  • 手动测试结果已记录在Linear评论中(来自ln-512)
  • 研究结果已在Linear评论中可用(来自ln-511)
前置条件:
  • Story中的所有实现任务状态 = 已完成
  • ln-511-test-researcher已完成(存在研究评论)
  • ln-512-manual-tester已完成(手动测试结果在Linear评论中)
自动化支持: 支持
autoApprove: true
(由ln-510调用时默认启用),可跳过手动确认。

When NOT to Use

何时不使用

Do NOT use if:
  • Manual testing NOT completed → Wait for ln-512
  • Research NOT completed → Wait for ln-511
  • Implementation tasks NOT all Done → Complete impl tasks first
请勿在以下场景使用:
  • 手动测试未完成 → 等待ln-512完成
  • 研究未完成 → 等待ln-511完成
  • 实现任务未全部完成 → 先完成所有实现任务

Workflow

工作流程

Phase 1: Discovery (Automated)

阶段1:自动发现

Auto-discovers Team ID from
docs/tasks/kanban_board.md
(see CLAUDE.md "Configuration Auto-Discovery").
Input: Story ID from orchestrator (ln-510)
docs/tasks/kanban_board.md
自动发现团队ID(参见CLAUDE.md中的“配置自动发现”)。
输入: 来自编排器(ln-510)的Story ID

Phase 2: Story + Tasks Analysis (NO Dialog)

阶段2:Story与任务分析(无交互)

Step 0: Study Project Test Files
  1. Scan for test-related files:
    • tests/README.md (commands, setup, environment)
    • Test configs (jest.config.js, vitest.config.ts, pytest.ini)
    • Existing test structure (tests/, tests/ directories)
    • Coverage config (.coveragerc, coverage.json)
  2. Extract: test commands, framework, patterns, coverage thresholds
  3. Ensures test planning aligns with project practices
Step 1: Load Research and Manual Test Results
  1. Fetch Story from Linear (must have label "user-story")
  2. Extract Story.id (UUID) - Use UUID, NOT short ID (required for Linear API)
  3. Load research comment (from ln-511): "## Test Research: {Feature}"
  4. Load manual test results comment (from ln-512): "## Manual Testing Results"
    • If not found → ERROR: Run ln-510-test-planner pipeline first
  5. Parse sections: AC results (PASS/FAIL), Edge Cases, Error Handling, Integration flows
  6. Map to test design: PASSED AC → E2E, Edge cases → Unit, Errors → Error handling, Flows → Integration
Step 2: Analyze Story + Tasks
  1. Parse Story: Goal, Test Strategy, Technical Notes
  2. Fetch all child Tasks (parentId = Story.id, status = Done) from Linear
  3. Analyze each Task:
    • Components implemented
    • Business logic added
    • Integration points created
    • Conditional branches (if/else/switch)
  4. Identify what needs testing
步骤0:研究项目测试文件
  1. 扫描测试相关文件:
    • tests/README.md(命令、设置、环境)
    • 测试配置文件(jest.config.js、vitest.config.ts、pytest.ini)
    • 现有测试结构(tests/、tests/目录)
    • 覆盖率配置文件(.coveragerc、coverage.json)
  2. 提取:测试命令、框架、模式、覆盖率阈值
  3. 确保测试规划与项目实践保持一致
步骤1:加载研究与手动测试结果
  1. 从Linear获取Story(必须带有“user-story”标签)
  2. 提取Story.id(UUID)- 使用UUID,而非短ID(Linear API要求)
  3. 加载来自ln-511的研究评论:"## Test Research: {Feature}"
  4. 加载来自ln-512的手动测试结果评论:"## Manual Testing Results"
    • 若未找到 → 错误:先运行ln-510-test-planner流水线
  5. 解析各部分:AC结果(通过/失败)、边缘情况、错误处理、集成流程
  6. 映射至测试设计:通过的AC → E2E测试,边缘情况 → 单元测试,错误场景 → 错误处理测试,流程 → 集成测试
步骤2:分析Story与任务
  1. 解析Story:目标、测试策略、技术说明
  2. 从Linear获取所有子任务(parentId = Story.id,状态 = 已完成)
  3. 分析每个任务:
    • 已实现的组件
    • 新增的业务逻辑
    • 创建的集成点
    • 条件分支(if/else/switch)
  4. 确定需要测试的内容

Phase 3: Parsing Strategy for Manual Test Results

阶段3:手动测试结果解析策略

Process: Locate Linear comment with "Manual Testing Results" header → Verify Format Version 1.0 → Extract structured sections (Acceptance Criteria, Test Results by AC, Edge Cases, Error Handling, Integration Testing) using regex → Validate (at least 1 PASSED AC, AC count matches Story, completeness check) → Map parsed data to test design structure
Error Handling: Missing comment → ERROR (run ln-512 first), Missing format version → WARNING (try legacy parsing), Required section missing → ERROR (re-run ln-512), No PASSED AC → ERROR (fix implementation)
流程: 定位带有“Manual Testing Results”标题的Linear评论 → 验证格式版本1.0 → 使用正则表达式提取结构化部分(验收标准、按AC分类的测试结果、边缘情况、错误处理、集成测试) → 验证(至少1个通过的AC,AC数量与Story匹配,完整性检查) → 将解析后的数据映射至测试设计结构
错误处理: 缺少评论 → 错误(先运行ln-512),缺少格式版本 → 警告(尝试旧版解析),缺少必填部分 → 错误(重新运行ln-512),无通过的AC → 错误(修复实现)

Phase 4: Risk-Based Test Planning (Automated)

阶段4:基于风险的测试规划(自动化)

Reference: See
references/risk_based_testing_guide.md
for complete methodology.
E2E-First Approach: Prioritize by business risk (Priority = Impact x Probability), not coverage metrics.
Workflow:
Step 1: Risk Assessment
Calculate Priority for each scenario from manual testing:
Priority = Business Impact (1-5) x Probability (1-5)
Decision Criteria:
  • Priority >=15 → MUST test
  • Priority 9-14 → SHOULD test if not covered
  • Priority <=8 → SKIP (manual testing sufficient)
Step 2: E2E Test Selection (2-5): Baseline 2 (positive + negative) ALWAYS + 0-3 additional (Priority >=15 only)
Step 3: Unit Test Selection (0-15): DEFAULT 0. Add ONLY for complex business logic (Priority >=15): financial, security, algorithms
Step 4: Integration Test Selection (0-8): DEFAULT 0. Add ONLY if E2E gaps AND Priority >=15: rollback, concurrency, external API errors
Step 5: Validation: Limits 2-28 total (realistic goal: 2-7). Auto-trim if >7 (keep 2 baseline + top 5 by Priority)
参考: 完整方法论请参见
references/risk_based_testing_guide.md
E2E优先方法: 按业务风险排序(优先级 = 影响 × 概率),而非覆盖率指标。
工作流程:
步骤1:风险评估
计算手动测试中每个场景的优先级:
Priority = Business Impact (1-5) x Probability (1-5)
决策标准:
  • 优先级 >=15 → 必须测试
  • 优先级 9-14 → 若未覆盖则应测试
  • 优先级 <=8 → 跳过(手动测试已足够)
步骤2:E2E测试选择(2-5个): 始终包含2个基线测试(正向+反向) + 0-3个额外测试(仅优先级>=15的场景)
步骤3:单元测试选择(0-15个): 默认0个。仅为复杂业务逻辑(优先级>=15)添加:财务、安全、算法相关场景
步骤4:集成测试选择(0-8个): 默认0个。仅当E2E测试存在缺口且优先级>=15时添加:回滚、并发、外部API错误场景
步骤5:验证: 限制总测试数为2-28个(合理目标:2-7个)。若超过7个则自动裁剪(保留2个基线测试 + 优先级最高的5个场景)

Phase 5: Test Task Generation (Automated)

阶段5:测试任务生成(自动化)

Generates complete test task per
test_task_template.md
(11 sections):
Sections 1-7: Context, Risk Matrix, E2E/Integration/Unit Tests (with Priority scores + justifications), Coverage, DoD
Section 8: Existing Tests to Fix (analysis of affected tests from implementation tasks)
Section 9: Infrastructure Changes (packages, Docker, configs - based on test dependencies)
Section 10: Documentation Updates (README, CHANGELOG, tests/README, config docs)
Section 11: Legacy Code Cleanup (deprecated patterns, backward compat, dead code)
Shows preview for review.
根据
test_task_template.md
生成完整的测试任务(11节):
第1-7节: 上下文、风险矩阵、E2E/集成/单元测试(含优先级分数+理由)、覆盖率、完成定义(DoD)
第8节: 需要修复的现有测试(分析实现任务影响的测试)
第9节: 基础设施变更(依赖的包、Docker、配置)
第10节: 文档更新(README、CHANGELOG、tests/README、配置文档)
第11节: 遗留代码清理(已弃用模式、向后兼容、死代码)
显示预览供审核。

Phase 6: Confirmation & Delegation

阶段6:确认与委派

Step 1: Preview generated test plan (always displayed for transparency)
Step 2: Confirmation logic:
  • autoApprove: true (default from ln-510) → proceed automatically
  • Manual run → prompt user to type "confirm"
Step 3: Check for existing test task
Query Linear:
list_issues(parentId=Story.id, labels=["tests"])
Decision:
  • Count = 0CREATE MODE (Step 4a)
  • Count >= 1REPLAN MODE (Step 4b)
Step 4a: CREATE MODE (if Count = 0)
Invoke ln-301-task-creator worker with taskType: "test"
Pass to worker:
  • taskType, teamId, storyData (Story.id, title, AC, Technical Notes, Context)
  • researchFindings (from ln-511 comment)
  • manualTestResults (from ln-512 comment)
  • testPlan (e2eTests, integrationTests, unitTests, riskPriorityMatrix)
  • infrastructureChanges, documentationUpdates, legacyCleanup
Worker returns: Task URL + summary
Step 4b: REPLAN MODE (if Count >= 1)
Invoke ln-302-task-replanner worker with taskType: "test"
Pass to worker:
  • Same data as CREATE MODE + existingTaskIds
Worker returns: Operations summary + warnings
Step 5: Return summary to orchestrator (ln-510)

步骤1: 显示生成的测试计划预览(始终显示以保证透明度)
步骤2: 确认逻辑:
  • autoApprove: true(ln-510调用时默认启用)→ 自动执行
  • 手动运行 → 提示用户输入"confirm"
步骤3: 检查现有测试任务
查询Linear:
list_issues(parentId=Story.id, labels=["tests"])
决策:
  • 数量 = 0创建模式(步骤4a)
  • 数量 >=1重规划模式(步骤4b)
步骤4a:创建模式(数量=0时)
调用ln-301-task-creator工作单元,taskType: "test"
传递给工作单元的参数:
  • taskType、teamId、storyData(Story.id、标题、AC、技术说明、上下文)
  • researchFindings(来自ln-511的评论)
  • manualTestResults(来自ln-512的评论)
  • testPlan(e2eTests、integrationTests、unitTests、riskPriorityMatrix)
  • infrastructureChanges、documentationUpdates、legacyCleanup
工作单元返回: 任务URL + 摘要
步骤4b:重规划模式(数量>=1时)
调用ln-302-task-replanner工作单元,taskType: "test"
传递给工作单元的参数:
  • 与创建模式相同的参数 + existingTaskIds
工作单元返回: 操作摘要 + 警告
步骤5: 向编排器(ln-510)返回摘要

Definition of Done

完成定义

Research and Manual Results Loaded:
  • Research comment "## Test Research: {Feature}" found (from ln-511)
  • Manual test results "## Manual Testing Results" found (from ln-512)
  • At least 1 AC marked as PASSED
Risk-Based Test Plan Generated:
  • Risk Priority Matrix calculated for all scenarios
  • E2E tests (2-5): Baseline 2 + additional 0-3 with Priority >=15
  • Integration tests (0-8): ONLY if E2E doesn't cover AND Priority >=15
  • Unit tests (0-15): ONLY complex business logic with Priority >=15
  • Total tests: 2-7 realistic goal (hard limit: 2-28)
  • No framework/library testing: Each test validates OUR business logic only
Test Task Description Complete (11 sections):
  • All 11 sections populated per template
  • Risk Priority Matrix included
  • Each test beyond baseline 2 justified
Worker Delegation Executed:
  • CREATE MODE: Delegated to ln-301-task-creator
  • REPLAN MODE: Delegated to ln-302-task-replanner
  • Linear Issue URL returned
Output:
  • CREATE MODE: Linear Issue URL + confirmation
  • REPLAN MODE: Operations summary + URLs
已加载研究与手动测试结果:
  • 找到来自ln-511的研究评论"## Test Research: {Feature}"
  • 找到来自ln-512的手动测试结果"## Manual Testing Results"
  • 至少1个AC标记为通过
已生成基于风险的测试计划:
  • 已为所有场景计算风险优先级矩阵
  • E2E测试(2-5个):2个基线测试 + 0-3个优先级>=15的额外测试
  • 集成测试(0-8个):仅当E2E未覆盖且优先级>=15时添加
  • 单元测试(0-15个):仅为优先级>=15的复杂业务逻辑添加
  • 总测试数:合理目标2-7个(硬限制:2-28个)
  • 无框架/库测试:每个测试仅验证我们的业务逻辑
测试任务描述完整(11节):
  • 已按模板填充所有11节内容
  • 包含风险优先级矩阵
  • 基线测试之外的每个测试均有理由说明
已执行工作单元委派:
  • 创建模式:已委派至ln-301-task-creator
  • 重规划模式:已委派至ln-302-task-replanner
  • 返回Linear Issue URL
输出:
  • 创建模式: Linear Issue URL + 确认信息
  • 重规划模式: 操作摘要 + URL

Reference Files

参考文件

  • Risk-based testing methodology:
    shared/references/risk_based_testing.md
  • Auto-discovery patterns:
    shared/references/auto_discovery_pattern.md
  • 基于风险的测试方法论:
    shared/references/risk_based_testing.md
  • 自动发现模式:
    shared/references/auto_discovery_pattern.md

risk_based_testing_guide.md

risk_based_testing_guide.md

Purpose: Risk-Based Testing methodology (detailed guide)
Location: references/risk_based_testing_guide.md
目的:基于风险的测试方法论(详细指南)
位置references/risk_based_testing_guide.md

test_task_template.md (CENTRALIZED)

test_task_template.md(集中管理)

Location:
shared/templates/test_task_template.md
Usage: Workers (ln-301, ln-302) load via Template Loading logic
位置
shared/templates/test_task_template.md
使用方式:工作单元(ln-301、ln-302)通过模板加载逻辑加载

Best Practices

最佳实践

Minimum Viable Testing: Start with 2 E2E tests (positive + negative). Add more ONLY with critical justification. Realistic goal: 2-7 tests per Story.
Risk-Based Testing: Prioritize by Business Impact x Probability. E2E-first from ACTUAL manual testing results. Priority >=15 scenarios covered by tests.
Expected-Based Testing: For deterministic tests, compare actual vs expected using
diff
. See ln-512-manual-tester Test Design Principles.

Version: 1.0.0 (Initial release - extracted from ln-510-test-planner) Last Updated: 2026-01-15
最小可行测试: 从2个E2E测试(正向+反向)开始。仅在有充分理由时添加更多测试。合理目标:每个Story 2-7个测试。
基于风险的测试: 按业务影响×概率排序优先级。基于实际手动测试结果优先进行E2E测试。覆盖优先级>=15的场景。
基于预期的测试: 对于确定性测试,使用
diff
比较实际结果与预期结果。参见ln-512-manual-tester测试设计原则

版本: 1.0.0(初始版本 - 从ln-510-test-planner提取) 最后更新: 2026-01-15