ln-230-story-prioritizer by levnikolaevich/claude-code-skills
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-230-story-prioritizerPaths: 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}.
结合市场调研,使用 RICE 评分法评估故事。为史诗生成统一的优先级排序表。
在以下情况使用此技能:
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
不要在以下情况使用:
谁调用此技能:
| 参数 | 必需 | 描述 | 默认值 |
|---|---|---|---|
| epic | 是 | 史诗 ID 或 "Epic N" 格式 | - |
| stories | 否 | 要排序的特定故事 ID | 史诗中的所有故事 |
| depth | 否 | 调研深度 (quick/standard/deep) | "standard" |
depth 选项:
quick - 每个故事 2-3 分钟,每种类型 1 次 WebSearchstandard - 每个故事 5-7 分钟,每种类型 2-3 次 WebSearchdeep - 每个故事 8-10 分钟,全面调研docs/market/[epic-slug]/
└── prioritization.md # 汇总表 + RICE 详情 + 来源
表格列(根据用户需求):
| 优先级 | 客户问题 | 功能 | 解决方案 | 理由 | 影响 | 市场 | 来源 | 竞争 |
|---|---|---|---|---|---|---|---|---|
| P0 | 用户痛点 | 故事标题 | 技术方法 | 重要性原因 | 业务影响 | $XB | [链接] | 蓝海 1-3 / 红海 4-5 |
| 输入 | 必需 | 来源 | 描述 |
|---|---|---|---|
epicId | 是 | args, kanban, user | 要处理的史诗 |
解析: 史诗解析链。状态过滤器: 活跃(计划中/已开始)
必读: 加载 shared/references/tools_config_guide.md, shared/references/storage_mode_detection.md, shared/references/input_resolution_pattern.md
提取:task_provider = 任务管理 → 提供商
| 工具 | 用途 | 示例查询 |
|---|---|---|
| WebSearch | 市场规模、竞争对手 | "[领域] 市场规模 {current_year}" |
| mcp__Ref | 行业报告 | "[领域] 市场分析报告" |
| Task provider | 加载故事 | IF linear: list_issues / ELSE: Glob story.md |
| Glob | 检查现有文件 | "docs/market/[epic]/*" |
目标: 验证输入并准备上下文。
流程:
解析 epicId: 根据指南运行史诗解析链。
加载史诗详情:
get_project(query=epicId)Read("docs/tasks/epics/epic-{N}-*/epic.md")自动发现配置:
docs/tasks/kanban_board.md 获取团队 ID检查现有优先级排序:
Glob: docs/market/[epic-slug]/prioritization.md
创建输出目录:
mkdir -p docs/market/[epic-slug]/
输出: 史诗元数据、输出路径、现有检查结果
目标: 仅使用元数据构建故事队列(提高令牌效率)。
流程:
从史诗查询故事: IF task_provider == "linear":
list_issues(project=Epic.id, label="user-story")
ELSE (文件模式):
Glob("docs/tasks/epics/epic-{N}-*/stories/*/story.md")
仅提取元数据:
过滤故事:
构建处理队列:
输出: 故事队列(ID + 标题),每个故事约 50 个令牌
目标: 对每个故事:加载描述、调研、计算 RICE 分数。
关键: 为提高令牌效率,逐个处理故事!
IF task_provider == "linear":
get_issue(id=storyId, includeRelations=false)
ELSE (文件模式):
Read("docs/tasks/epics/epic-{N}-*/stories/us{NNN}-*/story.md")
从故事中提取:
WebSearch 查询(基于深度):
"[客户问题领域] 市场规模 TAM {current_year}"
"[功能类型] 行业市场预测"
mcp__Ref 查询:
"[领域] 市场分析 Gartner Statista"
提取:
置信度映射:
WebSearch 查询:
"[功能] 竞争对手 替代方案 {current_year}"
"[解决方案方法] 市场领导者"
统计竞争对手并分类:
| 找到的竞争对手 | 竞争指数 | 海洋类型 |
|---|---|---|
| 0 | 1 | 蓝海 |
| 1-2 | 2 | 新兴 |
| 3-5 | 3 | 成长中 |
| 6-10 | 4 | 成熟 |
10 | 5 | 红海
RICE = (Reach x Impact x Confidence) / Effort
Reach (1-10): 每季度受影响的用户数
| 分数 | 用户数 | 指标 |
|---|---|---|
| 1-2 | <500 | 小众,单一用户画像 |
| 3-4 | 500-2K | 部门级别 |
| 5-6 | 2K-5K | 组织范围 |
| 7-8 | 5K-10K | 多组织 |
| 9-10 | >10K | 平台范围 |
Impact (0.25-3.0): 业务价值
| 分数 | 级别 | 指标 |
|---|---|---|
| 0.25 | 最小 | 锦上添花 |
| 0.5 | 低 | 生活质量改善 |
| 1.0 | 中 | 效率提升 |
| 2.0 | 高 | 收入驱动 |
| 3.0 | 巨大 | 战略差异化 |
Confidence (0.5-1.0): 数据质量(来自步骤 3.2)
数据置信度评估:
针对每个 RICE 因素,评估数据置信度级别:
| 置信度 | 标准 | 分数调整 |
|---|---|---|
| 高 | 多个权威来源(Gartner, Statista, SEC 文件) | 因素按原值使用 |
| 中 | 1-2 个来源,质量参差不齐(博客 + 报告) | 显示因素 ±25% 范围 |
| 低 | 无来源,仅团队估算 | 显示因素 ±50% 范围 |
输出: 在优先级排序表中显示每个因素的置信度 + RICE 范围(乐观/悲观),以明确不确定性。
Effort (1-10): 人月
| 分数 | 时间 | 故事指标 |
|---|---|---|
| 1-2 | <2 周 | 3 个验收标准,简单的增删改查 |
| 3-4 | 2-4 周 | 4 个验收标准,集成 |
| 5-6 | 1-2 个月 | 5 个验收标准,复杂逻辑 |
| 7-8 | 2-3 个月 | 外部依赖 |
| 9-10 | 3+ 个月 | 新基础设施 |
| 优先级 | RICE 阈值 | 竞争覆盖规则 |
|---|---|---|
| P0 (关键) | >= 30 | 或 竞争指数 = 1(蓝海垄断) |
| P1 (高) | >= 15 | 或 竞争指数 <= 2(新兴市场) |
| P2 (中) | >= 5 | - |
| P3 (低) | < 5 | 竞争指数 = 5(红海)强制设为 P3 |
每个故事的输出: 优先级排序表的完整行
目标: 创建统一的 Markdown 输出。
流程:
排序结果:
生成 Markdown:
保存文件:
Write: docs/market/[epic-slug]/prioritization.md
输出: 保存的 prioritization.md
目标: 显示结果和建议。
输出格式:
## 优先级排序完成
**史诗:** [Epic N - 名称]
**已分析的故事:** X
**耗时:** Y 分钟
### 优先级分布:
- P0 (关键): X 个故事 - 尽快实施
- P1 (高): X 个故事 - 下一个冲刺
- P2 (中): X 个故事 - 待办事项列表
- P3 (低): X 个故事 - 考虑推迟
### 前 3 个优先级:
1. [故事标题] - RICE: X, 市场: $XB, 竞争: 蓝海/红海
### 保存至:
docs/market/[epic-slug]/prioritization.md
### 后续步骤:
1. 与利益相关者一起评审表格
2. 首先为 P0/P1 故事运行 ln-300
3. 考虑削减 P3 故事
| 深度 | 每个故事 | 总计(10 个故事) |
|---|---|---|
| quick | 2-3 分钟 | 20-30 分钟 |
| standard | 5-7 分钟 | 50-70 分钟 |
| deep | 8-10 分钟 | 80-100 分钟 |
时间管理规则:
加载模式:
内存管理:
在工作流中的位置:
ln-210 (范围 → 史诗)
↓
ln-220 (史诗 → 故事)
↓
ln-230 (每个故事的 RICE → 优先级排序表) ← 本技能
↓
ln-300 (故事 → 任务)
依赖项:
下游使用:
基本用法:
ln-230-story-prioritizer epic="Epic 7"
带参数:
ln-230-story-prioritizer epic="Epic 7: Translation API" depth="deep"
特定故事:
ln-230-story-prioritizer epic="Epic 7" stories="US001,US002,US003"
示例输出 (docs/market/translation-api/prioritization.md):
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。
shared/references/tools_config_guide.mdshared/references/storage_mode_detection.mdshared/references/research_tool_fallback.md| 文件 | 用途 |
|---|---|
| prioritization_template.md | 输出 Markdown 模板 |
| rice_scoring_guide.md | RICE 因素量表和示例 |
| research_queries.md | 按领域分类的 WebSearch 查询模板 |
| competition_index.md | 蓝海/红海分类规则 |
版本: 1.0.0 最后更新: 2025-12-23
每周安装次数
154
仓库
GitHub 星标数
245
首次出现
Jan 24, 2026
安全审计
安装于
claude-code140
gemini-cli138
codex138
cursor138
opencode138
github-copilot133
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}.
Evaluate Stories using RICE scoring with market research. Generate consolidated prioritization table for Epic.
Use this skill when:
Do NOT use when:
Who calls this skill:
| Parameter | Required | Description | Default |
|---|---|---|---|
| epic | Yes | Epic ID or "Epic N" format | - |
| stories | No | Specific Story IDs to prioritize | All in Epic |
| depth | No | Research depth (quick/standard/deep) | "standard" |
depth options:
quick - 2-3 min/Story, 1 WebSearch per typestandard - 5-7 min/Story, 2-3 WebSearches per typedeep - 8-10 min/Story, comprehensive researchdocs/market/[epic-slug]/
└── prioritization.md # Consolidated table + RICE details + sources
Table columns (from user requirements):
| Priority | Customer Problem | Feature | Solution | Rationale | Impact | Market | Sources | Competition |
|---|---|---|---|---|---|---|---|---|
| P0 | User pain point | Story title | Technical approach | Why important | Business impact | $XB | [Link] | Blue 1-3 / Red 4-5 |
| Input | Required | Source | Description |
|---|---|---|---|
epicId | Yes | args, kanban, user | Epic to process |
Resolution: Epic Resolution Chain. Status filter: Active (planned/started)
MANDATORY READ: Load shared/references/tools_config_guide.md, shared/references/storage_mode_detection.md, shared/references/input_resolution_pattern.md
Extract: task_provider = Task Management → Provider
| Tool | Purpose | Example Query |
|---|---|---|
| WebSearch | Market size, competitors | "[domain] market size {current_year}" |
| mcp__Ref | Industry reports | "[domain] market analysis report" |
| Task provider | Load Stories | IF linear: list_issues / ELSE: Glob story.md |
| Glob | Check existing | "docs/market/[epic]/*" |
Objective: Validate input and prepare context.
Process:
Resolve epicId: Run Epic Resolution Chain per guide.
Load Epic details:
get_project(query=epicId)Read("docs/tasks/epics/epic-{N}-*/epic.md")Auto-discover configuration:
docs/tasks/kanban_board.md for Team IDCheck existing prioritization:
Glob: docs/market/[epic-slug]/prioritization.md
Create output directory:
Output: Epic metadata, output path, existing check result
Objective: Build Story queue with metadata only (token efficiency).
Process:
Query Stories from Epic: IF task_provider == "linear":
list_issues(project=Epic.id, label="user-story")
ELSE (file mode):
Glob("docs/tasks/epics/epic-{N}-*/stories/*/story.md")
2. Extract metadata only:
* Story ID, title, status
* **DO NOT** load full descriptions yet
3. Filter Stories:
* Exclude: Done, Cancelled, Archived
* Include: Backlog, Todo, In Progress
4. Build processing queue:
* Order by: existing priority (if any), then by ID
* Count: N Stories to process
Output: Story queue (ID + title), ~50 tokens/Story
Objective: For EACH Story: load description, research, score RICE.
Critical: Process Stories ONE BY ONE for token efficiency!
IF task_provider == "linear":
get_issue(id=storyId, includeRelations=false)
ELSE (file mode):
Read("docs/tasks/epics/epic-{N}-*/stories/us{NNN}-*/story.md")
Extract from Story:
WebSearch queries (based on depth):
"[customer problem domain] market size TAM {current_year}"
"[feature type] industry market forecast"
mcp__Ref query:
"[domain] market analysis Gartner Statista"
Extract:
Confidence mapping:
WebSearch queries:
"[feature] competitors alternatives {current_year}"
"[solution approach] market leaders"
Count competitors and classify:
| Competitors Found | Competition Index | Ocean Type |
|---|---|---|
| 0 | 1 | Blue Ocean |
| 1-2 | 2 | Emerging |
| 3-5 | 3 | Growing |
| 6-10 | 4 | Mature |
10 | 5 | Red Ocean
RICE = (Reach x Impact x Confidence) / Effort
Reach (1-10): Users affected per quarter
| Score | Users | Indicators |
|---|---|---|
| 1-2 | <500 | Niche, single persona |
| 3-4 | 500-2K | Department-level |
| 5-6 | 2K-5K | Organization-wide |
| 7-8 | 5K-10K | Multi-org |
| 9-10 | >10K | Platform-wide |
Impact (0.25-3.0): Business value
| Score | Level | Indicators |
|---|---|---|
| 0.25 | Minimal | Nice-to-have |
| 0.5 | Low | QoL improvement |
| 1.0 | Medium | Efficiency gain |
| 2.0 | High | Revenue driver |
| 3.0 | Massive | Strategic differentiator |
Confidence (0.5-1.0): Data quality (from Step 3.2)
Data Confidence Assessment:
For each RICE factor, assess data confidence level:
| Confidence | Criteria | Score Modifier |
|---|---|---|
| HIGH | Multiple authoritative sources (Gartner, Statista, SEC filings) | Factor used as-is |
| MEDIUM | 1-2 sources, mixed quality (blog + report) | Factor ±25% range shown |
| LOW | No sources, team estimate only | Factor ±50% range shown |
Output: Show confidence per factor in prioritization table + RICE range (optimistic/pessimistic) to make uncertainty explicit.
Effort (1-10): Person-months
| Score | Time | Story Indicators |
|---|---|---|
| 1-2 | <2 weeks | 3 AC, simple CRUD |
| 3-4 | 2-4 weeks | 4 AC, integration |
| 5-6 | 1-2 months | 5 AC, complex logic |
| 7-8 | 2-3 months | External dependencies |
| 9-10 | 3+ months | New infrastructure |
| Priority | RICE Threshold | Competition Override |
|---|---|---|
| P0 (Critical) | >= 30 | OR Competition = 1 (Blue Ocean monopoly) |
| P1 (High) | >= 15 | OR Competition <= 2 (Emerging market) |
| P2 (Medium) | >= 5 | - |
| P3 (Low) | < 5 | Competition = 5 (Red Ocean) forces P3 |
Output per Story: Complete row for prioritization table
Objective: Create consolidated markdown output.
Process:
Sort results:
Generate markdown:
Save file:
Write: docs/market/[epic-slug]/prioritization.md
Output: Saved prioritization.md
Objective: Display results and recommendations.
Output format:
## Prioritization Complete
**Epic:** [Epic N - Name]
**Stories analyzed:** X
**Time elapsed:** Y minutes
### Priority Distribution:
- P0 (Critical): X Stories - Implement ASAP
- P1 (High): X Stories - Next sprint
- P2 (Medium): X Stories - Backlog
- P3 (Low): X Stories - Consider deferring
### Top 3 Priorities:
1. [Story Title] - RICE: X, Market: $XB, Competition: Blue/Red
### Saved to:
docs/market/[epic-slug]/prioritization.md
### Next Steps:
1. Review table with stakeholders
2. Run ln-300 for P0/P1 Stories first
3. Consider cutting P3 Stories
| Depth | Per-Story | Total (10 Stories) |
|---|---|---|
| quick | 2-3 min | 20-30 min |
| standard | 5-7 min | 50-70 min |
| deep | 8-10 min | 80-100 min |
Time management rules:
Loading pattern:
Memory management:
Position in workflow:
ln-210 (Scope → Epics)
↓
ln-220 (Epic → Stories)
↓
ln-230 (RICE per Story → prioritization table) ← THIS SKILL
↓
ln-300 (Story → Tasks)
Dependencies:
Downstream usage:
Basic usage:
ln-230-story-prioritizer epic="Epic 7"
With parameters:
ln-230-story-prioritizer epic="Epic 7: Translation API" depth="deep"
Specific Stories:
ln-230-story-prioritizer epic="Epic 7" stories="US001,US002,US003"
Example output (docs/market/translation-api/prioritization.md):
| Priority | Customer Problem | Feature | Solution | Rationale | Impact | Market | Sources | Competition |
|---|---|---|---|---|---|---|---|---|
| P0 | "Repeat translations cost GPU" | Translation Memory | Redis cache, 5ms lookup | 70-90% GPU cost reduction | High | $2B+ | M&M | 3 |
| P0 | "Can't translate PDF" | PDF Support | PDF parsing + layout | Enterprise blocker | High | $10B+ | Eden | 5 |
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.
shared/references/tools_config_guide.mdshared/references/storage_mode_detection.mdshared/references/research_tool_fallback.md| File | Purpose |
|---|---|
| prioritization_template.md | Output markdown template |
| rice_scoring_guide.md | RICE factor scales and examples |
| research_queries.md | WebSearch query templates by domain |
| competition_index.md | Blue/Red Ocean classification rules |
Version: 1.0.0 Last Updated: 2025-12-23
Weekly Installs
154
Repository
GitHub Stars
245
First Seen
Jan 24, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
claude-code140
gemini-cli138
codex138
cursor138
opencode138
github-copilot133
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
33,600 周安装
mkdir -p docs/market/[epic-slug]/
| P1 |
| "Need video subtitles" |
| SRT/VTT Support |
| Timing preservation |
| Blue Ocean opportunity |
| Medium |
| $5.7B |
| GMI |
| 2 |