ln-520-test-planner by levnikolaevich/claude-code-skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-520-test-planner路径说明: 文件路径(
shared/、references/、../ln-*)是相对于技能仓库根目录的。如果在当前工作目录未找到,请定位此 SKILL.md 文件所在的目录,然后向上一级即为仓库根目录。如果缺少shared/目录,请通过 WebFetch 从https://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}获取文件。
通过委托给专门的执行者,协调针对一个 Story 的完整测试规划流程。
| 输入 | 是否必需 | 来源 | 描述 |
|---|---|---|---|
storyId |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 是 |
| args, git branch, kanban, user |
| 要处理的 Story |
--simplified | 否 | args | 跳过研究(ln-521)和手动测试(ln-522)。仅运行自动测试规划(ln-523)。用于快速通道模式。 |
解析方式: Story 解析链。状态过滤器: To Review
在以下情况下应使用此技能:
先决条件:
ln-520-test-planner (协调器)
│
├─→ ln-521-test-researcher
│ └─→ 发布 "## Test Research: {Feature}" 评论
│
├─→ ln-522-manual-tester
│ └─→ 创建 tests/manual/ 脚本 + "## Manual Testing Results" 评论
│
└─→ ln-523-auto-test-planner
└─→ 通过 ln-301/ln-302 在 Linear 中创建测试任务
必读: 加载 shared/references/input_resolution_pattern.md
docs/tasks/kanban_board.md 自动发现团队 ID简化模式检查点:
- 如果存在
--simplified标志 且 Story 上已存在研究评论:跳过阶段 2(研究)。进入阶段 4。- 如果存在
--simplified标志 且 没有研究评论:跳过阶段 2。进入阶段 4(ln-523 将生成最小的内联研究)。
ln-521-test-researcher简化模式检查点:
- 如果存在
--simplified标志:跳过阶段 3(手动测试)。进入阶段 4。
ln-522-manual-testerln-523-auto-test-planner关键: 所有委托都使用 Agent 工具,并设置
subagent_type: "general-purpose"以实现上下文隔离。
| 阶段 | 执行者 | 目的 |
|---|---|---|
| 2 | ln-521-test-researcher | 研究现实世界中的问题 |
| 3 | ln-522-manual-tester | 通过 bash 脚本进行手动 AC 测试 |
| 4 | ln-523-auto-test-planner | 规划 E2E/集成/单元测试 |
提示词模板:
Agent(description: "[Phase N] test planning via ln-52X",
prompt: "Execute test planning worker.
Step 1: Invoke worker:
Skill(skill: \"ln-52X-{worker}\")
CONTEXT:
Story: {storyId}",
subagent_type: "general-purpose")
反模式:
输出: 包含各阶段结果 + 测试任务 URL 的摘要
必读: 加载 shared/references/meta_analysis_protocol.md
技能类型:planning-coordinator。在所有阶段完成后运行。使用 planning-coordinator 格式输出到聊天。
../ln-521-test-researcher/SKILL.md, ../ln-522-manual-tester/SKILL.md, ../ln-523-auto-test-planner/SKILL.md../ln-500-story-quality-gate/SKILL.mdshared/references/risk_based_testing_guide.md版本: 4.0.0 最后更新: 2026-01-15
每周安装数
129
仓库
GitHub 星标数
245
首次出现
2026年2月11日
安全审计
安装于
cursor121
opencode121
gemini-cli120
codex120
github-copilot120
claude-code120
Paths: File paths (
shared/,references/,../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Ifshared/is missing, fetch files via WebFetch fromhttps://raw.githubusercontent.com/levnikolaevich/claude-code-skills/master/skills/{path}.
Coordinates the complete test planning pipeline for a Story by delegating to specialized workers.
| Input | Required | Source | Description |
|---|---|---|---|
storyId | Yes | args, git branch, kanban, user | Story to process |
--simplified | No | args | Skip research (ln-521) and manual testing (ln-522). Run only auto-test planning (ln-523). Used in fast-track mode. |
Resolution: Story Resolution Chain. Status filter: To Review
This skill should be used when:
Prerequisites:
ln-520-test-planner (Orchestrator)
│
├─→ ln-521-test-researcher
│ └─→ Posts "## Test Research: {Feature}" comment
│
├─→ ln-522-manual-tester
│ └─→ Creates tests/manual/ scripts + "## Manual Testing Results" comment
│
└─→ ln-523-auto-test-planner
└─→ Creates test task in Linear via ln-301/ln-302
MANDATORY READ: Load shared/references/input_resolution_pattern.md
docs/tasks/kanban_board.mdSimplified mode gate:
- IF
--simplifiedflag AND research comment already exists on Story: Skip Phase 2 (research). Proceed to Phase 4.- IF
--simplifiedflag AND no research comment: Skip Phase 2. Proceed to Phase 4 (ln-523 will generate minimal inline research).
Check if research exists:
If no research:
ln-521-test-researcherSimplified mode gate:
- IF
--simplifiedflag: Skip Phase 3 (manual testing). Proceed to Phase 4.
Check if manual testing done:
If manual testing needed:
ln-522-manual-testerIf any AC failed:
Invoke auto test planner:
ln-523-auto-test-plannerVerify results:
CRITICAL: All delegations use Agent tool with
subagent_type: "general-purpose"for context isolation.
| Phase | Worker | Purpose |
|---|---|---|
| 2 | ln-521-test-researcher | Research real-world problems |
| 3 | ln-522-manual-tester | Manual AC testing via bash scripts |
| 4 | ln-523-auto-test-planner | Plan E2E/Integration/Unit tests |
Prompt template:
Agent(description: "[Phase N] test planning via ln-52X",
prompt: "Execute test planning worker.
Step 1: Invoke worker:
Skill(skill: \"ln-52X-{worker}\")
CONTEXT:
Story: {storyId}",
subagent_type: "general-purpose")
Anti-Patterns:
Output: Summary with phase results + test task URL
MANDATORY READ: Load shared/references/meta_analysis_protocol.md
Skill type: planning-coordinator. Run after all phases complete. Output to chat using the planning-coordinator format.
../ln-521-test-researcher/SKILL.md, ../ln-522-manual-tester/SKILL.md, ../ln-523-auto-test-planner/SKILL.md../ln-500-story-quality-gate/SKILL.mdshared/references/risk_based_testing_guide.mdVersion: 4.0.0 Last Updated: 2026-01-15
Weekly Installs
129
Repository
GitHub Stars
245
First Seen
Feb 11, 2026
Security Audits
Gen Agent Trust HubPassSocketWarnSnykWarn
Installed on
cursor121
opencode121
gemini-cli120
codex120
github-copilot120
claude-code120
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
36,300 周安装