Back to Details

ln-510-test-planner

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Test Planning Orchestrator

测试规划编排器

Coordinates the complete test planning pipeline for a Story by delegating to specialized workers.
通过委派给专用工作组件，协调Story的完整测试规划流水线。

Purpose & Scope

目标与范围

  • Orchestrate test planning: research → manual testing → automated test planning
  • Delegate to workers: ln-511-test-researcher, ln-512-manual-tester, ln-513-auto-test-planner
  • No direct work — only coordination and delegation via Skill tool
  • Called by ln-500-story-quality-gate after regression tests pass
  • 编排测试规划：调研→手动测试→自动化测试规划
  • 委派给工作组件：ln-511-test-researcher、ln-512-manual-tester、ln-513-auto-test-planner
  • 不直接执行任务 — 仅通过Skill工具进行协调和委派
  • 调用方：回归测试通过后由ln-500-story-quality-gate调用

When to Use

使用场景

This skill should be used when:
  • Invoked by ln-500-story-quality-gate Pass 1 after regression tests pass
  • All implementation tasks in Story are Done
  • Need complete test planning (research + manual + auto)
Prerequisites:
  • All implementation Tasks in Story status = Done
  • Regression tests passed (ln-502)
  • Code quality checked (ln-501)
应在以下场景使用本Skill：
  • 由ln-500-story-quality-gate调用：回归测试通过后的第一阶段
  • Story中的所有实现任务均已完成
  • 需要完整的测试规划（调研+手动+自动化）
前置条件：
  • Story中所有实现任务的状态为“已完成”
  • 回归测试已通过（ln-502）
  • 代码质量已检查（ln-501）

Pipeline Overview

流水线概览

ln-510-test-planner (Orchestrator)
    │
    ├─→ ln-511-test-researcher
    │     └─→ Posts "## Test Research: {Feature}" comment
    │
    ├─→ ln-512-manual-tester
    │     └─→ Creates tests/manual/ scripts + "## Manual Testing Results" comment
    │
    └─→ ln-513-auto-test-planner
          └─→ Creates test task in Linear via ln-301/ln-302
ln-510-test-planner (Orchestrator)
    │
    ├─→ ln-511-test-researcher
    │     └─→ 发布 "## Test Research: {Feature}" 评论
    │
    ├─→ ln-512-manual-tester
    │     └─→ 创建 tests/manual/ 脚本 + "## Manual Testing Results" 评论
    │
    └─→ ln-513-auto-test-planner
          └─→ 通过ln-301/ln-302在Linear中创建测试任务

Workflow

工作流程

Phase 1: Discovery

阶段1：发现

  1. Auto-discover Team ID from 
    docs/tasks/kanban_board.md
  2. Validate Story ID provided by ln-500
Input: Story ID from ln-500-story-quality-gate
  1. 从
    docs/tasks/kanban_board.md
    自动发现Team ID
  2. 验证ln-500提供的Story ID
输入： 来自ln-500-story-quality-gate的Story ID

Phase 2: Research Delegation

阶段2：调研委派

  1. Check if research exists:
    • Search Linear comments for "## Test Research:" header
    • If found → skip to Phase 3
  2. If no research:
    • Use Skill tool to invoke 
      ln-511-test-researcher
    • Pass: Story ID
    • Wait for completion
    • Verify research comment created
  1. 检查是否已存在调研：
    • 在Linear评论中搜索"## Test Research:"标题
    • 若找到→跳至阶段3
  2. 若未找到调研：
    • 使用Skill工具调用
      ln-511-test-researcher
    • 传入参数：Story ID
    • 等待执行完成
    • 确认已创建调研评论

Phase 3: Manual Testing Delegation

阶段3：手动测试委派

  1. Check if manual testing done:
    • Search Linear comments for "## Manual Testing Results" header
    • If found with all AC passed → skip to Phase 4
  2. If manual testing needed:
    • Use Skill tool to invoke 
      ln-512-manual-tester
    • Pass: Story ID
    • Wait for completion
    • Verify results comment created
  3. If any AC failed:
    • Stop pipeline
    • Report to ln-500: "Manual testing failed, Story needs fixes"
  1. 检查是否已完成手动测试：
    • 在Linear评论中搜索"## Manual Testing Results"标题
    • 若找到且所有验收标准（AC）通过→跳至阶段4
  2. 若需要手动测试：
    • 使用Skill工具调用
      ln-512-manual-tester
    • 传入参数：Story ID
    • 等待执行完成
    • 确认已创建测试结果评论
  3. 若有验收标准未通过：
    • 停止流水线
    • 向ln-500报告："手动测试失败，Story需要修复"

Phase 4: Auto Test Planning Delegation

阶段4：自动化测试规划委派

  1. Invoke auto test planner:
    • Use Skill tool to invoke 
      ln-513-auto-test-planner
    • Pass: Story ID
    • Wait for completion
  2. Verify results:
    • Test task created in Linear (or updated if existed)
    • Return task URL to ln-500
  1. 调用自动化测试规划组件：
    • 使用Skill工具调用
      ln-513-auto-test-planner
    • 传入参数：Story ID
    • 等待执行完成
  2. 验证结果：
    • 在Linear中创建（或更新）测试任务
    • 向ln-500返回任务URL

Phase 5: Report to Caller

阶段5：向调用方报告

  1. Return summary to ln-500:
    • Research: completed / skipped (existed)
    • Manual testing: passed / failed
    • Test task: created / updated + URL
  1. 向ln-500返回总结报告：
    • 调研：已完成 / 跳过（已存在）
    • 手动测试：通过 / 失败
    • 测试任务：已创建 / 已更新 + URL

Worker Invocation (MANDATORY)

工作组件调用（强制要求）

CRITICAL: All delegations use Task tool with 
subagent_type: "general-purpose"
for context isolation.
PhaseWorkerPurpose
2ln-511-test-researcherResearch real-world problems
3ln-512-manual-testerManual AC testing via bash scripts
4ln-513-auto-test-plannerPlan E2E/Integration/Unit tests
Prompt template:
Task(description: "[Phase N] test planning via ln-51X",
     prompt: "Execute ln-51X-{worker}. Read skill from ln-51X-{worker}/SKILL.md. Story: {storyId}",
     subagent_type: "general-purpose")
Anti-Patterns:
  • ❌ Direct Skill tool invocation without Task wrapper
  • ❌ Running web searches directly (delegate to ln-511)
  • ❌ Creating bash test scripts directly (delegate to ln-512)
  • ❌ Creating test tasks directly (delegate to ln-513)
  • ❌ Skipping any phase without justification
重要提示： 所有委派均使用Task工具，并设置
subagent_type: "general-purpose"
以实现上下文隔离。
阶段工作组件用途
2ln-511-test-researcher调研实际场景问题
3ln-512-manual-tester通过bash脚本手动执行验收测试（AC）
4ln-513-auto-test-planner规划端到端（E2E）/集成/单元测试
提示模板：
Task(description: "[Phase N] test planning via ln-51X",
     prompt: "Execute ln-51X-{worker}. Read skill from ln-51X-{worker}/SKILL.md. Story: {storyId}",
     subagent_type: "general-purpose")
反模式：
  • ❌ 不通过Task包装直接调用Skill工具
  • ❌ 直接进行网络搜索（需委派给ln-511）
  • ❌ 直接创建bash测试脚本（需委派给ln-512）
  • ❌ 直接创建测试任务（需委派给ln-513）
  • ❌ 无正当理由跳过任何阶段

Critical Rules

核心规则

  • No direct work: Orchestrator only delegates, never executes tasks itself
  • Sequential execution: 511 → 512 → 513 (each depends on previous)
  • Fail-fast: If manual testing fails, stop pipeline and report
  • Skip detection: Check for existing comments before invoking workers
  • Single responsibility: Each worker does one thing well
  • 不直接执行任务：编排器仅负责委派，绝不自行执行任务
  • 顺序执行：511 → 512 → 513（每个环节依赖前一个环节的完成）
  • 快速失败：若手动测试失败，立即停止流水线并上报
  • 跳过检测：调用工作组件前先检查是否已有相关结果
  • 单一职责：每个工作组件仅专注完成一项任务

Definition of Done

完成标准

  • Story ID validated
  • Research phase: ln-511 invoked OR existing comment found
  • Manual testing phase: ln-512 invoked OR existing results found
  • Auto test planning phase: ln-513 invoked
  • Test task created/updated in Linear
  • Summary returned to ln-500-story-quality-gate
Output: Summary with phase results + test task URL
  • Story ID已验证
  • 调研阶段：已调用ln-511 或 已找到现有调研评论
  • 手动测试阶段：已调用ln-512 或 已找到现有测试结果
  • 自动化测试规划阶段：已调用ln-513
  • 在Linear中创建/更新了测试任务
  • 已向ln-500-story-quality-gate返回总结报告
输出： 包含各阶段结果的总结报告 + 测试任务URL

Reference Files

参考文件

  • Workers: 
    ../ln-511-test-researcher/SKILL.md
    , 
    ../ln-512-manual-tester/SKILL.md
    , 
    ../ln-513-auto-test-planner/SKILL.md
  • Caller: 
    ../ln-500-story-quality-gate/SKILL.md
  • Risk-based testing: 
    ../ln-513-auto-test-planner/references/risk_based_testing_guide.md
Version: 4.0.0 (Refactored to Orchestrator pattern - delegates to ln-511/512/513 workers) Last Updated: 2026-01-15
  • 工作组件：
    ../ln-511-test-researcher/SKILL.md
    , 
    ../ln-512-manual-tester/SKILL.md
    , 
    ../ln-513-auto-test-planner/SKILL.md
  • 调用方：
    ../ln-500-story-quality-gate/SKILL.md
  • 基于风险的测试：
    ../ln-513-auto-test-planner/references/risk_based_testing_guide.md
版本： 4.0.0（重构为编排器模式 - 委派给ln-511/512/513工作组件） 最后更新时间： 2026-01-15