ln-200-scope-decomposer by levnikolaevich/claude-code-skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-200-scope-decomposer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 文件所在目录并向上返回一级以找到仓库根目录。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。
从范围到用户故事,通过史诗和故事协调器进行完整计划分解的顶层编排器。
协调新计划的完整分解流水线:
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
此技能应在以下情况使用:
替代方案: 如需精细控制,请手动调用协调器:
在以下情况下请不要使用:
ln-200-scope-decomposer 是纯粹的协调器 - 它不直接执行工作:
协调器:
关键约束: 史诗 N 的故事必须在史诗 N+1 开始前完成(ln-220 包含用户交互 — 跨史诗的交互式对话无法并行化)。
为何顺序执行?
示例: 6 个史诗 → ln-220 被顺序调用 6 次(史诗 0 → 史诗 1 → 史诗 2 → ... → 史诗 5)
保留编号: 史诗 0 保留给基础设施史诗(如果由 ln-210 提议)。
编号规则:
决策: ln-210-epic-coordinator 阶段 1 步骤 3 自动确定是否需要基础设施史诗(新项目、多技术栈、安全/监控要求)。
团队 ID: 从 docs/tasks/kanban_board.md 的 Linear 配置表中自动发现(参见 CLAUDE.md 的“配置自动发现”部分)。
后备方案: 如果缺少 kanban_board.md → ln-210-epic-coordinator 将直接询问用户
从 docs/tasks/kanban_board.md 自动发现团队 ID。
验证:
编排器层面无用户确认 - 协调器处理所有用户交互。
输出: 团队 ID(如果未找到则为 None)
目标: 为计划创建所有史诗。
委托给 ln-210-epic-coordinator:
🔄 [ORCHESTRATOR] 阶段 2:将史诗创建委托给 ln-210-epic-coordinator
Skill(skill: "ln-210-epic-coordinator")
ln-210-epic-coordinator 将:
完成后: 在 Linear 中创建史诗,更新 kanban_board.md。
输出: 创建 3-7 个史诗(如果适用,史诗 0 用于基础设施,史诗 1-N 用于业务领域)
目标: 为每个史诗创建故事(顺序处理)。
顺序循环逻辑:
FOR EACH Epic (Epic 0, Epic 1, ..., Epic N):
1. 为当前史诗调用 ln-220-story-coordinator
2. 等待完成
3. 验证故事已在 kanban_board.md 中创建
4. 移至下一个史诗
| 条件 | 操作 |
|---|---|
| 所有史诗已处理(故事 + 可选的 RICE) | 停止 — 进入总结阶段 |
| ln-220 对某个史诗失败(协调器错误) | 停止 — 报告部分结果,列出已完成的史诗 |
| 用户在故事确认期间取消 | 停止 — 报告已完成的史诗,跳过剩余部分 |
| 故事总数超过 80 | 停止 — 警告:“范围可能过大。继续吗?” |
每个史诗的调用:
🔄 [ORCHESTRATOR] 阶段 3:将史诗 N 的故事创建委托给 ln-220-story-coordinator
Skill(skill: "ln-220-story-coordinator", epic_number="Epic N")
ln-220-story-coordinator 将(每个史诗):
顺序约束说明:
每个史诗后: 在 Linear 中创建故事,更新 kanban_board.md。
输出: 总计 30-60 个故事(每个史诗 5-10 个 × 3-7 个史诗)
TodoWrite 格式(强制): 在开始前将阶段和史诗迭代添加到待办事项:
- Phase 1: Discovery (in_progress)
- Phase 2: Delegate to ln-210-epic-coordinator (pending)
- Phase 3: Delegate to ln-220 for Epic 0 (pending)
- Phase 3: Delegate to ln-220 for Epic 1 (pending)
- Phase 3: Delegate to ln-220 for Epic 2 (pending)
... (每个史诗一个待办事项)
- Phase 4: Delegate to ln-230 for Epic 0 (pending)
- Phase 4: Delegate to ln-230 for Epic 1 (pending)
... (每个史诗一个待办事项,可选)
- Phase 5: Summary (pending)
开始时标记为进行中,协调器返回成功时标记为已完成。
目标: 使用市场研究,通过 RICE 评分对每个史诗的故事进行优先级排序。
可选: 询问用户“为所有史诗运行 RICE 优先级排序吗?”如果用户拒绝,则跳至阶段 5。
顺序循环逻辑:
FOR EACH Epic (Epic 0, Epic 1, ..., Epic N):
1. 为当前史诗调用 ln-230-story-prioritizer
2. 等待完成
3. 验证 prioritization.md 已在 docs/market/[epic-slug]/ 中创建
4. 移至下一个史诗
每个史诗的调用:
Skill(skill: "ln-230-story-prioritizer", args: "epic=\"Epic N\"")
ln-230-story-prioritizer 将(每个史诗):
跳过条件: 如果史诗仅包含技术/基础设施故事(没有业务价值需要排序),则跳过该史诗。
每个史诗后: 优先级排序表保存到 docs/market/[epic-slug]/prioritization.md。
输出: 所有适用史诗的优先级排序表。
目标: 提供完整的分解概览。
🔄 [ORCHESTRATOR] 阶段 5:完整分解完成
计划分解摘要:
- 创建的史诗:N 个项目(史诗 0:基础设施[如果存在],史诗 1-N:业务领域)
- 创建的故事:M 个问题(按史诗细分)
- 位置:docs/tasks/kanban_board.md
后续步骤:
1. 运行 ln-310-multi-agent-validator 以验证所有故事
2. 使用 ln-400-story-executor 处理每个故事(任务 → 执行 → 完成)
或使用 ln-300-task-coordinator 为每个故事手动创建任务
输出: 包含完整分解结果的摘要消息
编排器不提示用户:
所有用户交互委托给协调器:
在完成工作前,验证所有检查点:
✅ 团队 ID 已发现(阶段 1):
✅ 史诗分解完成(阶段 2):
✅ 故事分解完成(阶段 3):
✅ RICE 优先级排序完成(阶段 4,可选):
✅ 已提供摘要(阶段 5):
输出: 包含完整分解结果的摘要消息(史诗 + 每个史诗的故事)
用户直接调用:“分解计划:[计划名称]”或“为[项目]创建史诗和故事”
ln-200-scope-decomposer 完成后:
信任协调器结果: 协调器返回摘要,编排器不重新验证。
错误处理: 如果协调器返回错误,向用户报告并停止流水线。
现实估算: 完整分解需要 2-3 小时(6 个史诗 × 平均 7 个故事 = 42 个故事)。
细分:
不要向用户提供时间估算 - 根据项目复杂性和用户响应时间而变化。
请求:
"Decompose initiative: E-commerce Platform"
执行:
阶段 1:发现
阶段 2:史诗分解
阶段 3:故事分解循环(顺序)
阶段 4:总结
🔄 [ORCHESTRATOR] 完整分解完成
计划:电子商务平台
- 创建的史诗:6 个项目(史诗 11:基础设施,史诗 12-16:业务领域)
- 创建的故事:36 个问题
- 史诗 11:6 个故事
- 史诗 12:7 个故事
- 史诗 13:5 个故事
- 史诗 14:6 个故事
- 史诗 15:7 个故事
- 史诗 16:5 个故事
- 位置:docs/tasks/kanban_board.md
后续步骤:
1. 运行 ln-310-multi-agent-validator 以验证所有故事
2. 使用 ln-400-story-executor 处理每个故事(任务 → 执行 → 完成)
结果: 通过完整流水线自动化创建了 6 个史诗 + 36 个故事
强制阅读: 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。
docs/tasks/kanban_board.md(团队 ID,下一个史诗编号)ln-210-epic-coordinator/SKILL.mdln-220-story-coordinator/SKILL.mdln-230-story-prioritizer/SKILL.mdshared/references/numbering_conventions.md(史诗 0 保留)使用表情符号前缀进行视觉区分:
目的: 帮助用户在委托给多个协调器时跟踪编排器进度。
版本: 2.0.0 最后更新: 2025-11-20
每周安装
153
仓库
GitHub 星标
245
首次出现
Jan 24, 2026
安全审计
安装于
claude-code138
opencode138
codex137
gemini-cli136
cursor134
github-copilot131
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}.
Top-level orchestrator for complete initiative decomposition from scope to User Stories through Epic and Story coordinators.
Coordinates the complete decomposition pipeline for new initiatives:
This skill should be used when:
Alternative: For granular control, invoke coordinators manually:
Do NOT use if:
ln-200-scope-decomposer is a pure coordinator - it does NOT execute work directly:
Coordinators:
CRITICAL CONSTRAINT: Epic N Stories MUST complete before Epic N+1 starts (ln-220 includes user interaction — interactive dialog cannot be parallelized across Epics).
Why sequential?
Example: 6 Epics → ln-220 invoked 6 times sequentially (Epic 0 → Epic 1 → Epic 2 → ... → Epic 5)
Reserved number: Epic 0 is reserved for Infrastructure Epic (if proposed by ln-210).
Numbering:
Decision: ln-210-epic-coordinator Phase 1 Step 3 automatically determines if Infrastructure Epic is needed (new project, multi-stack, security/monitoring requirements).
Team ID : Auto-discovered from docs/tasks/kanban_board.md Linear Configuration table (see CLAUDE.md "Configuration Auto-Discovery").
Fallback: If kanban_board.md missing → ln-210-epic-coordinator will ask user directly
Auto-discovers Team ID from docs/tasks/kanban_board.md.
Validation:
NO user confirmation at orchestrator level - coordinators handle all user interaction.
Output: Team ID (or None if not found)
Objective: Create all Epics for initiative.
Delegate to ln-210-epic-coordinator:
🔄 [ORCHESTRATOR] Phase 2: Delegating Epic creation to ln-210-epic-coordinator
Skill(skill: "ln-210-epic-coordinator")
ln-210-epic-coordinator will:
After completion: Epics created in Linear, kanban_board.md updated.
Output: 3-7 Epics created (Epic 0 for Infrastructure if applicable, Epic 1-N for business domains)
Objective: Create Stories for EACH Epic (sequential processing).
Sequential Loop Logic:
FOR EACH Epic (Epic 0, Epic 1, ..., Epic N):
1. Invoke ln-220-story-coordinator for current Epic
2. Wait for completion
3. Verify Stories created in kanban_board.md
4. Move to next Epic
| Condition | Action |
|---|---|
| All Epics processed (Stories + optional RICE) | STOP — proceed to Summary |
| ln-220 fails for an Epic (coordinator error) | STOP — report partial results, list completed Epics |
| User cancels during Story confirmation | STOP — report completed Epics, skip remaining |
| Total Story count exceeds 80 | STOP — WARN: "Scope may be too large. Continue?" |
Invocation per Epic:
🔄 [ORCHESTRATOR] Phase 3: Delegating Story creation for Epic N to ln-220-story-coordinator
Skill(skill: "ln-220-story-coordinator", epic_number="Epic N")
ln-220-story-coordinator will (per Epic):
Sequential constraint explanation:
After each Epic: Stories created in Linear, kanban_board.md updated.
Output: 30-60 Stories total (5-10 per Epic × 3-7 Epics)
TodoWrite format (mandatory): Add phases and Epic iterations to todos before starting:
- Phase 1: Discovery (in_progress)
- Phase 2: Delegate to ln-210-epic-coordinator (pending)
- Phase 3: Delegate to ln-220 for Epic 0 (pending)
- Phase 3: Delegate to ln-220 for Epic 1 (pending)
- Phase 3: Delegate to ln-220 for Epic 2 (pending)
... (one todo per Epic)
- Phase 4: Delegate to ln-230 for Epic 0 (pending)
- Phase 4: Delegate to ln-230 for Epic 1 (pending)
... (one todo per Epic, optional)
- Phase 5: Summary (pending)
Mark each as in_progress when starting, completed when coordinator returns success.
Objective: Prioritize Stories per Epic using RICE scoring with market research.
OPTIONAL: Ask user "Run RICE prioritization for all Epics?" If user declines, skip to Phase 5.
Sequential Loop Logic:
FOR EACH Epic (Epic 0, Epic 1, ..., Epic N):
1. Invoke ln-230-story-prioritizer for current Epic
2. Wait for completion
3. Verify prioritization.md created in docs/market/[epic-slug]/
4. Move to next Epic
Invocation per Epic:
Skill(skill: "ln-230-story-prioritizer", args: "epic=\"Epic N\"")
ln-230-story-prioritizer will (per Epic):
Skip condition: If Epic contains only technical/infrastructure Stories (no business value to prioritize), skip that Epic.
After each Epic: Prioritization table saved to docs/market/[epic-slug]/prioritization.md.
Output: Prioritization tables for all applicable Epics.
Objective: Provide complete decomposition overview.
🔄 [ORCHESTRATOR] Phase 5: Full decomposition complete
Initiative Decomposition Summary:
- Epics created: N Projects (Epic 0: Infrastructure [if exists], Epic 1-N: Business domains)
- Stories created: M Issues (breakdown per Epic)
- Location: docs/tasks/kanban_board.md
Next Steps:
1. Run ln-310-multi-agent-validator to validate all Stories
2. Use ln-400-story-executor to process each Story (tasks → execution → Done)
OR use ln-300-task-coordinator to create tasks manually for each Story
Output: Summary message with full decomposition results
Orchestrator does NOT prompt user:
All user interaction delegated to coordinators:
Before completing work, verify ALL checkpoints:
✅ Team ID Discovered (Phase 1):
✅ Epic Decomposition Complete (Phase 2):
✅ Story Decomposition Complete (Phase 3):
✅ RICE Prioritization Complete (Phase 4, optional):
✅ Summary Provided (Phase 5):
Output: Summary message with full decomposition results (Epics + Stories per Epic)
Users directly: "Decompose initiative: [initiative name]" or "Create epics and stories for [project]"
After ln-200-scope-decomposer completes:
Trust coordinator results: Coordinators return summary, orchestrator doesn't re-verify.
Error handling: If coordinator returns error, report to user and stop pipeline.
Realistic estimate: 2-3 hours for full decomposition (6 Epics × 7 Stories avg = 42 Stories).
Breakdown:
Do NOT provide time estimates to user - varies based on project complexity and user response time.
Request:
"Decompose initiative: E-commerce Platform"
Execution:
Phase 1: Discovery
Phase 2: Epic Decomposition
Phase 3: Story Decomposition Loop (Sequential)
Phase 4: Summary
🔄 [ORCHESTRATOR] Full decomposition complete
Initiative: E-commerce Platform
- Epics created: 6 Projects (Epic 11: Infrastructure, Epic 12-16: Business domains)
- Stories created: 36 Issues
- Epic 11: 6 Stories
- Epic 12: 7 Stories
- Epic 13: 5 Stories
- Epic 14: 6 Stories
- Epic 15: 7 Stories
- Epic 16: 5 Stories
- Location: docs/tasks/kanban_board.md
Next Steps:
1. Run ln-310-multi-agent-validator to validate all Stories
2. Use ln-400-story-executor to process each Story (tasks → execution → Done)
Result: 6 Epics + 36 Stories created through full pipeline automation
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.
docs/tasks/kanban_board.md (Team ID, Next Epic Number)ln-210-epic-coordinator/SKILL.mdln-220-story-coordinator/SKILL.mdln-230-story-prioritizer/SKILL.mdshared/references/numbering_conventions.md (Epic 0 reserved)Use emoji prefix for visual differentiation:
Purpose: Helps users track orchestrator progress when delegating to multiple coordinators.
Version: 2.0.0 Last Updated: 2025-11-20
Weekly Installs
153
Repository
GitHub Stars
245
First Seen
Jan 24, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
claude-code138
opencode138
codex137
gemini-cli136
cursor134
github-copilot131
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
Coder AI 代码助手 - 编写可运行、测试验证的代码,支持精准编辑与后台任务
3,900 周安装
协议逆向工程完全指南:Wireshark、tcpdump、Scapy实战教程与安全分析
4,000 周安装
全栈开发者技能指南:React、Node.js、TypeScript 现代 Web 开发技术栈
4,000 周安装
上下文驱动开发:AI辅助开发与团队协同的项目管理方法
4,000 周安装
内存取证技术指南:Volatility 3 实战与恶意软件分析工具
4,000 周安装
市场规模分析:TAM/SAM/SOM计算方法、框架与实战指南 | 创业融资必备
4,000 周安装