[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6EGDP1Q2JY08HPTFAYK3HNH":3,"skill-same:01M6EGDP1Q2JY08HPTFAYK3HNH":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6EGDP1Q2JY08HPTFAYK3HNH","ln-230-story-prioritizer",null,"RICE prioritization per Story with market research. Generates consolidated prioritization table in docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md.","levalencia\u002Fagent-god-mode","levalencia","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6962857?v=4","01M6EB0FZZ4BPQPC4HET4QY6NM","Luis Valencia ","01M6EB0G4HWHPWW0H9X7QKSAHP",3,"MIT","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-230-story-prioritizer\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33],"Story","ln 230 story prioritizer","docs","research","prioritization","market research","table","rice","Market","EPIC","2026-11-10 10:12:30",false,"---\nname: ln-230-story-prioritizer\ndescription: RICE prioritization per Story with market research. Generates consolidated prioritization table in docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md.\nlicense: MIT\n---\n\n> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# Story Prioritizer\n\nEvaluate Stories using RICE scoring with market research. Generate consolidated prioritization table for Epic.\n\n## Purpose & Scope\n\n- Prioritize Stories AFTER ln-220 creates them\n- Research market size and competition per Story\n- Calculate RICE score for each Story\n- Generate prioritization table (P0\u002FP1\u002FP2\u002FP3)\n- Output: docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n\n## When to Use\n\n**Use this skill when:**\n- Stories created by ln-220, need business prioritization\n- Planning sprint with limited capacity (which Stories first?)\n- Stakeholder review requires data-driven priorities\n- Evaluating feature ROI before implementation\n\n**Do NOT use when:**\n- Epic has no Stories yet (run ln-220 first)\n- Stories are purely technical (infrastructure, refactoring)\n- Prioritization already exists in docs\u002Fmarket\u002F\n\n**Who calls this skill:**\n- **ln-200-scope-decomposer** Phase 4 (optional, sequential per Epic)\n- **User (manual)** - standalone after ln-220-story-coordinator\n\n---\n\n## Input Parameters\n\n| Parameter | Required | Description | Default |\n|-----------|----------|-------------|---------|\n| epic | Yes | Epic ID or \"Epic N\" format | - |\n| stories | No | Specific Story IDs to prioritize | All in Epic |\n| depth | No | Research depth (quick\u002Fstandard\u002Fdeep) | \"standard\" |\n\n**depth options:**\n- `quick` - 2-3 min\u002FStory, 1 WebSearch per type\n- `standard` - 5-7 min\u002FStory, 2-3 WebSearches per type\n- `deep` - 8-10 min\u002FStory, comprehensive research\n\n---\n\n## Output Structure\n\n```\ndocs\u002Fmarket\u002F[epic-slug]\u002F\n└── prioritization.md    # Consolidated table + RICE details + sources\n```\n\n**Table columns (from user requirements):**\n\n| Priority | Customer Problem | Feature | Solution | Rationale | Impact | Market | Sources | Competition |\n|----------|------------------|---------|----------|-----------|--------|--------|---------|-------------|\n| P0 | User pain point | Story title | Technical approach | Why important | Business impact | $XB | [Link] | Blue 1-3 \u002F Red 4-5 |\n\n---\n\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `epicId` | Yes | args, kanban, user | Epic to process |\n\n**Resolution:** Epic Resolution Chain.\n**Status filter:** Active (planned\u002Fstarted)\n\n## Tools Config\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftools_config_guide.md`, `shared\u002Freferences\u002Fstorage_mode_detection.md`, `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\nExtract: `task_provider` = Task Management → Provider\n\n## Research Tools\n\n| Tool | Purpose | Example Query |\n|------|---------|---------------|\n| **WebSearch** | Market size, competitors | \"[domain] market size {current_year}\" |\n| **mcp__Ref** | Industry reports | \"[domain] market analysis report\" |\n| **Task provider** | Load Stories | IF linear: list_issues \u002F ELSE: Glob story.md |\n| **Glob** | Check existing | \"docs\u002Fmarket\u002F[epic]\u002F*\" |\n\n---\n\n## Workflow\n\n### Phase 1: Discovery (2 min)\n\n**Objective:** Validate input and prepare context.\n\n**Process:**\n\n1. **Resolve epicId:** Run Epic Resolution Chain per guide.\n\n2. **Load Epic details:**\n   - **IF task_provider == \"linear\":** `get_project(query=epicId)`\n   - **ELSE:** `Read(\"docs\u002Ftasks\u002Fepics\u002Fepic-{N}-*\u002Fepic.md\")`\n   - Extract: Epic ID, title, description\n\n3. **Auto-discover configuration:**\n   - Read `docs\u002Ftasks\u002Fkanban_board.md` for Team ID\n   - Slugify Epic title for output path\n\n4. **Check existing prioritization:**\n   ```\n   Glob: docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n   ```\n   - If exists: Ask \"Update existing or create new?\"\n   - If new: Continue\n\n5. **Create output directory:**\n   ```bash\n   mkdir -p docs\u002Fmarket\u002F[epic-slug]\u002F\n   ```\n\n**Output:** Epic metadata, output path, existing check result\n\n---\n\n### Phase 2: Load Stories Metadata (3 min)\n\n**Objective:** Build Story queue with metadata only (token efficiency).\n\n**Process:**\n\n1. **Query Stories from Epic:**\n   **IF task_provider == \"linear\":**\n   ```\n   list_issues(project=Epic.id, label=\"user-story\")\n   ```\n   **ELSE (file mode):**\n   ```\n   Glob(\"docs\u002Ftasks\u002Fepics\u002Fepic-{N}-*\u002Fstories\u002F*\u002Fstory.md\")\n   ```\n\n2. **Extract metadata only:**\n   - Story ID, title, status\n   - **DO NOT** load full descriptions yet\n\n3. **Filter Stories:**\n   - Exclude: Done, Cancelled, Archived\n   - Include: Backlog, Todo, In Progress\n\n4. **Build processing queue:**\n   - Order by: existing priority (if any), then by ID\n   - Count: N Stories to process\n\n**Output:** Story queue (ID + title), ~50 tokens\u002FStory\n\n---\n\n### Phase 3: Story-by-Story Analysis Loop (5-10 min\u002FStory)\n\n**Objective:** For EACH Story: load description, research, score RICE.\n\n**Critical:** Process Stories ONE BY ONE for token efficiency!\n\n#### Per-Story Steps:\n\n##### Step 3.1: Load Story Description\n\n**IF task_provider == \"linear\":**\n```\nget_issue(id=storyId, includeRelations=false)\n```\n\n**ELSE (file mode):**\n```\nRead(\"docs\u002Ftasks\u002Fepics\u002Fepic-{N}-*\u002Fstories\u002Fus{NNN}-*\u002Fstory.md\")\n```\n\n**Extract from Story:**\n- **Feature:** Story title\n- **Customer Problem:** From \"So that [value]\" + Context section\n- **Solution:** From Technical Notes (implementation approach)\n- **Rationale:** From AC + Success Criteria\n\n##### Step 3.2: Research Market Size\n\n**WebSearch queries (based on depth):**\n```\n\"[customer problem domain] market size TAM {current_year}\"\n\"[feature type] industry market forecast\"\n```\n\n**mcp__Ref query:**\n```\n\"[domain] market analysis Gartner Statista\"\n```\n\n**Extract:**\n- Market size: $XB (with unit: B=Billion, M=Million)\n- Growth rate: X% CAGR\n- Sources: URL + date\n\n**Confidence mapping:**\n- Industry report (Gartner, Statista) → Confidence 0.9-1.0\n- News article → Confidence 0.7-0.8\n- Blog\u002FForum → Confidence 0.5-0.6\n\n##### Step 3.3: Research Competition\n\n**WebSearch queries:**\n```\n\"[feature] competitors alternatives {current_year}\"\n\"[solution approach] market leaders\"\n```\n\n**Count competitors and classify:**\n\n| Competitors Found | Competition Index | Ocean Type |\n|-------------------|-------------------|------------|\n| 0 | 1 | Blue Ocean |\n| 1-2 | 2 | Emerging |\n| 3-5 | 3 | Growing |\n| 6-10 | 4 | Mature |\n| >10 | 5 | Red Ocean |\n\n##### Step 3.4: Calculate RICE Score\n\n```\nRICE = (Reach x Impact x Confidence) \u002F Effort\n```\n\n**Reach (1-10):** Users affected per quarter\n| Score | Users | Indicators |\n|-------|-------|------------|\n| 1-2 | \u003C500 | Niche, single persona |\n| 3-4 | 500-2K | Department-level |\n| 5-6 | 2K-5K | Organization-wide |\n| 7-8 | 5K-10K | Multi-org |\n| 9-10 | >10K | Platform-wide |\n\n**Impact (0.25-3.0):** Business value\n| Score | Level | Indicators |\n|-------|-------|------------|\n| 0.25 | Minimal | Nice-to-have |\n| 0.5 | Low | QoL improvement |\n| 1.0 | Medium | Efficiency gain |\n| 2.0 | High | Revenue driver |\n| 3.0 | Massive | Strategic differentiator |\n\n**Confidence (0.5-1.0):** Data quality (from Step 3.2)\n\n**Data Confidence Assessment:**\n\nFor each RICE factor, assess data confidence level:\n\n| Confidence | Criteria | Score Modifier |\n|------------|----------|----------------|\n| HIGH | Multiple authoritative sources (Gartner, Statista, SEC filings) | Factor used as-is |\n| MEDIUM | 1-2 sources, mixed quality (blog + report) | Factor ±25% range shown |\n| LOW | No sources, team estimate only | Factor ±50% range shown |\n\n**Output:** Show confidence per factor in prioritization table + RICE range (optimistic\u002Fpessimistic) to make uncertainty explicit.\n\n**Effort (1-10):** Person-months\n| Score | Time | Story Indicators |\n|-------|------|------------------|\n| 1-2 | \u003C2 weeks | 3 AC, simple CRUD |\n| 3-4 | 2-4 weeks | 4 AC, integration |\n| 5-6 | 1-2 months | 5 AC, complex logic |\n| 7-8 | 2-3 months | External dependencies |\n| 9-10 | 3+ months | New infrastructure |\n\n##### Step 3.5: Determine Priority\n\n| Priority | RICE Threshold | Competition Override |\n|----------|----------------|---------------------|\n| P0 (Critical) | >= 30 | OR Competition = 1 (Blue Ocean monopoly) |\n| P1 (High) | >= 15 | OR Competition \u003C= 2 (Emerging market) |\n| P2 (Medium) | >= 5 | - |\n| P3 (Low) | \u003C 5 | Competition = 5 (Red Ocean) forces P3 |\n\n##### Step 3.6: Store and Clear\n\n- Append row to in-memory results table\n- Clear Story description from context\n- Move to next Story in queue\n\n**Output per Story:** Complete row for prioritization table\n\n---\n\n### Phase 4: Generate Prioritization Table (5 min)\n\n**Objective:** Create consolidated markdown output.\n\n**Process:**\n\n1. **Sort results:**\n   - Primary: Priority (P0 → P3)\n   - Secondary: RICE score (descending)\n\n2. **Generate markdown:**\n   - Use template from references\u002Fprioritization_template.md\n   - Fill: Priority Summary, Main Table, RICE Details, Sources\n\n3. **Save file:**\n   ```\n   Write: docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n   ```\n\n**Output:** Saved prioritization.md\n\n---\n\n### Phase 5: Summary & Next Steps (1 min)\n\n**Objective:** Display results and recommendations.\n\n**Output format:**\n```\n## Prioritization Complete\n\n**Epic:** [Epic N - Name]\n**Stories analyzed:** X\n**Time elapsed:** Y minutes\n\n### Priority Distribution:\n- P0 (Critical): X Stories - Implement ASAP\n- P1 (High): X Stories - Next sprint\n- P2 (Medium): X Stories - Backlog\n- P3 (Low): X Stories - Consider deferring\n\n### Top 3 Priorities:\n1. [Story Title] - RICE: X, Market: $XB, Competition: Blue\u002FRed\n\n### Saved to:\ndocs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n\n### Next Steps:\n1. Review table with stakeholders\n2. Run ln-300 for P0\u002FP1 Stories first\n3. Consider cutting P3 Stories\n```\n\n---\n\n## Time-Box Constraints\n\n| Depth | Per-Story | Total (10 Stories) |\n|-------|-----------|-------------------|\n| quick | 2-3 min | 20-30 min |\n| standard | 5-7 min | 50-70 min |\n| deep | 8-10 min | 80-100 min |\n\n**Time management rules:**\n- If Story exceeds time budget: Skip deep research, use estimates (Confidence 0.5)\n- If total exceeds budget: Switch to \"quick\" depth for remaining Stories\n- Parallel WebSearch where possible (market + competition)\n\n---\n\n## Token Efficiency\n\n**Loading pattern:**\n- Phase 2: Metadata only (~50 tokens\u002FStory)\n- Phase 3: Full description ONE BY ONE (~3,000-5,000 tokens\u002FStory)\n- After each Story: Clear description, keep only result row (~100 tokens)\n\n**Memory management:**\n- Sequential processing (not parallel)\n- Maximum context: 1 Story description at a time\n- Results accumulate as compact table rows\n\n---\n\n## Integration with Ecosystem\n\n**Position in workflow:**\n```\nln-210 (Scope → Epics)\n     ↓\nln-220 (Epic → Stories)\n     ↓\nln-230 (RICE per Story → prioritization table) ← THIS SKILL\n     ↓\nln-300 (Story → Tasks)\n```\n\n**Dependencies:**\n- WebSearch, mcp__Ref (market research)\n- Task provider: Linear MCP or file mode (load Epic, Stories)\n- Glob, Write, Bash (file operations)\n\n**Downstream usage:**\n- Sprint planning uses P0\u002FP1 to select Stories\n- ln-300 processes Stories in priority order\n- Stakeholders review before implementation\n\n---\n\n## Critical Rules\n\n1. **Source all data** - Every Market number needs source + date\n2. **Prefer recent data** - last 2 years, warn if older\n3. **Cross-reference** - 2+ sources for Market size (reduce error)\n4. **Time-box strictly** - Skip depth for speed if needed\n5. **Confidence levels** - Mark High\u002FMedium\u002FLow for estimates\n6. **No speculation** - Only sourced claims, note \"[No data]\" gaps\n7. **One Story at a time** - Token efficiency critical\n8. **Preserve language** - If user asks in Russian, respond in Russian\n\n---\n\n## Definition of Done\n\n- [ ] Epic validated (Linear or file mode)\n- [ ] All Stories loaded (metadata, then descriptions per-Story)\n- [ ] Market research completed (2+ sources per Story)\n- [ ] RICE score calculated for each Story\n- [ ] Competition index assigned (1-5)\n- [ ] Priority assigned (P0\u002FP1\u002FP2\u002FP3)\n- [ ] Table sorted by Priority + RICE\n- [ ] File saved to docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n- [ ] Summary with top priorities and next steps\n- [ ] Total time within budget\n\n---\n\n## Example Usage\n\n**Basic usage:**\n```\nln-230-story-prioritizer epic=\"Epic 7\"\n```\n\n**With parameters:**\n```\nln-230-story-prioritizer epic=\"Epic 7: Translation API\" depth=\"deep\"\n```\n\n**Specific Stories:**\n```\nln-230-story-prioritizer epic=\"Epic 7\" stories=\"US001,US002,US003\"\n```\n\n**Example output (docs\u002Fmarket\u002Ftranslation-api\u002Fprioritization.md):**\n\n| Priority | Customer Problem | Feature | Solution | Rationale | Impact | Market | Sources | Competition |\n|----------|------------------|---------|----------|-----------|--------|--------|---------|-------------|\n| P0 | \"Repeat translations cost GPU\" | Translation Memory | Redis cache, 5ms lookup | 70-90% GPU cost reduction | High | $2B+ | [M&M](link) | 3 |\n| P0 | \"Can't translate PDF\" | PDF Support | PDF parsing + layout | Enterprise blocker | High | $10B+ | [Eden](link) | 5 |\n| P1 | \"Need video subtitles\" | SRT\u002FVTT Support | Timing preservation | Blue Ocean opportunity | Medium | $5.7B | [GMI](link) | 2 |\n\n---\n\n## Phase 6: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `planning-coordinator`. Run after all phases complete. Output to chat using the `planning-coordinator` format.\n\n## Reference Files\n\n- **MANDATORY READ:** `shared\u002Freferences\u002Ftools_config_guide.md`\n- **MANDATORY READ:** `shared\u002Freferences\u002Fstorage_mode_detection.md`\n- **MANDATORY READ:** `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n| File | Purpose |\n|------|---------|\n| [prioritization_template.md](references\u002Fprioritization_template.md) | Output markdown template |\n| [rice_scoring_guide.md](references\u002Frice_scoring_guide.md) | RICE factor scales and examples |\n| [research_queries.md](references\u002Fresearch_queries.md) | WebSearch query templates by domain |\n| [competition_index.md](references\u002Fcompetition_index.md) | Blue\u002FRed Ocean classification rules |\n\n---\n\n**Version:** 1.0.0\n**Last Updated:** 2025-12-23\n","> **Paths:** File paths (`shared\u002F`, `references\u002F`, `..\u002Fln-*`) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.\n\n# Story Prioritizer\n\nEvaluate Stories using RICE scoring with market research. Generate consolidated prioritization table for Epic.\n\n## Purpose & Scope\n\n- Prioritize Stories AFTER ln-220 creates them\n- Research market size and competition per Story\n- Calculate RICE score for each Story\n- Generate prioritization table (P0\u002FP1\u002FP2\u002FP3)\n- Output: docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n\n## When to Use\n\n**Use this skill when:**\n- Stories created by ln-220, need business prioritization\n- Planning sprint with limited capacity (which Stories first?)\n- Stakeholder review requires data-driven priorities\n- Evaluating feature ROI before implementation\n\n**Do NOT use when:**\n- Epic has no Stories yet (run ln-220 first)\n- Stories are purely technical (infrastructure, refactoring)\n- Prioritization already exists in docs\u002Fmarket\u002F\n\n**Who calls this skill:**\n- **ln-200-scope-decomposer** Phase 4 (optional, sequential per Epic)\n- **User (manual)** - standalone after ln-220-story-coordinator\n\n---\n\n## Input Parameters\n\n| Parameter | Required | Description | Default |\n|-----------|----------|-------------|---------|\n| epic | Yes | Epic ID or \"Epic N\" format | - |\n| stories | No | Specific Story IDs to prioritize | All in Epic |\n| depth | No | Research depth (quick\u002Fstandard\u002Fdeep) | \"standard\" |\n\n**depth options:**\n- `quick` - 2-3 min\u002FStory, 1 WebSearch per type\n- `standard` - 5-7 min\u002FStory, 2-3 WebSearches per type\n- `deep` - 8-10 min\u002FStory, comprehensive research\n\n---\n\n## Output Structure\n\n```\ndocs\u002Fmarket\u002F[epic-slug]\u002F\n└── prioritization.md    # Consolidated table + RICE details + sources\n```\n\n**Table columns (from user requirements):**\n\n| Priority | Customer Problem | Feature | Solution | Rationale | Impact | Market | Sources | Competition |\n|----------|------------------|---------|----------|-----------|--------|--------|---------|-------------|\n| P0 | User pain point | Story title | Technical approach | Why important | Business impact | $XB | [Link] | Blue 1-3 \u002F Red 4-5 |\n\n---\n\n## Inputs\n\n| Input | Required | Source | Description |\n|-------|----------|--------|-------------|\n| `epicId` | Yes | args, kanban, user | Epic to process |\n\n**Resolution:** Epic Resolution Chain.\n**Status filter:** Active (planned\u002Fstarted)\n\n## Tools Config\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Ftools_config_guide.md`, `shared\u002Freferences\u002Fstorage_mode_detection.md`, `shared\u002Freferences\u002Finput_resolution_pattern.md`\n\nExtract: `task_provider` = Task Management → Provider\n\n## Research Tools\n\n| Tool | Purpose | Example Query |\n|------|---------|---------------|\n| **WebSearch** | Market size, competitors | \"[domain] market size {current_year}\" |\n| **mcp__Ref** | Industry reports | \"[domain] market analysis report\" |\n| **Task provider** | Load Stories | IF linear: list_issues \u002F ELSE: Glob story.md |\n| **Glob** | Check existing | \"docs\u002Fmarket\u002F[epic]\u002F*\" |\n\n---\n\n## Workflow\n\n### Phase 1: Discovery (2 min)\n\n**Objective:** Validate input and prepare context.\n\n**Process:**\n\n1. **Resolve epicId:** Run Epic Resolution Chain per guide.\n\n2. **Load Epic details:**\n   - **IF task_provider == \"linear\":** `get_project(query=epicId)`\n   - **ELSE:** `Read(\"docs\u002Ftasks\u002Fepics\u002Fepic-{N}-*\u002Fepic.md\")`\n   - Extract: Epic ID, title, description\n\n3. **Auto-discover configuration:**\n   - Read `docs\u002Ftasks\u002Fkanban_board.md` for Team ID\n   - Slugify Epic title for output path\n\n4. **Check existing prioritization:**\n   ```\n   Glob: docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n   ```\n   - If exists: Ask \"Update existing or create new?\"\n   - If new: Continue\n\n5. **Create output directory:**\n   ```bash\n   mkdir -p docs\u002Fmarket\u002F[epic-slug]\u002F\n   ```\n\n**Output:** Epic metadata, output path, existing check result\n\n---\n\n### Phase 2: Load Stories Metadata (3 min)\n\n**Objective:** Build Story queue with metadata only (token efficiency).\n\n**Process:**\n\n1. **Query Stories from Epic:**\n   **IF task_provider == \"linear\":**\n   ```\n   list_issues(project=Epic.id, label=\"user-story\")\n   ```\n   **ELSE (file mode):**\n   ```\n   Glob(\"docs\u002Ftasks\u002Fepics\u002Fepic-{N}-*\u002Fstories\u002F*\u002Fstory.md\")\n   ```\n\n2. **Extract metadata only:**\n   - Story ID, title, status\n   - **DO NOT** load full descriptions yet\n\n3. **Filter Stories:**\n   - Exclude: Done, Cancelled, Archived\n   - Include: Backlog, Todo, In Progress\n\n4. **Build processing queue:**\n   - Order by: existing priority (if any), then by ID\n   - Count: N Stories to process\n\n**Output:** Story queue (ID + title), ~50 tokens\u002FStory\n\n---\n\n### Phase 3: Story-by-Story Analysis Loop (5-10 min\u002FStory)\n\n**Objective:** For EACH Story: load description, research, score RICE.\n\n**Critical:** Process Stories ONE BY ONE for token efficiency!\n\n#### Per-Story Steps:\n\n##### Step 3.1: Load Story Description\n\n**IF task_provider == \"linear\":**\n```\nget_issue(id=storyId, includeRelations=false)\n```\n\n**ELSE (file mode):**\n```\nRead(\"docs\u002Ftasks\u002Fepics\u002Fepic-{N}-*\u002Fstories\u002Fus{NNN}-*\u002Fstory.md\")\n```\n\n**Extract from Story:**\n- **Feature:** Story title\n- **Customer Problem:** From \"So that [value]\" + Context section\n- **Solution:** From Technical Notes (implementation approach)\n- **Rationale:** From AC + Success Criteria\n\n##### Step 3.2: Research Market Size\n\n**WebSearch queries (based on depth):**\n```\n\"[customer problem domain] market size TAM {current_year}\"\n\"[feature type] industry market forecast\"\n```\n\n**mcp__Ref query:**\n```\n\"[domain] market analysis Gartner Statista\"\n```\n\n**Extract:**\n- Market size: $XB (with unit: B=Billion, M=Million)\n- Growth rate: X% CAGR\n- Sources: URL + date\n\n**Confidence mapping:**\n- Industry report (Gartner, Statista) → Confidence 0.9-1.0\n- News article → Confidence 0.7-0.8\n- Blog\u002FForum → Confidence 0.5-0.6\n\n##### Step 3.3: Research Competition\n\n**WebSearch queries:**\n```\n\"[feature] competitors alternatives {current_year}\"\n\"[solution approach] market leaders\"\n```\n\n**Count competitors and classify:**\n\n| Competitors Found | Competition Index | Ocean Type |\n|-------------------|-------------------|------------|\n| 0 | 1 | Blue Ocean |\n| 1-2 | 2 | Emerging |\n| 3-5 | 3 | Growing |\n| 6-10 | 4 | Mature |\n| >10 | 5 | Red Ocean |\n\n##### Step 3.4: Calculate RICE Score\n\n```\nRICE = (Reach x Impact x Confidence) \u002F Effort\n```\n\n**Reach (1-10):** Users affected per quarter\n| Score | Users | Indicators |\n|-------|-------|------------|\n| 1-2 | \u003C500 | Niche, single persona |\n| 3-4 | 500-2K | Department-level |\n| 5-6 | 2K-5K | Organization-wide |\n| 7-8 | 5K-10K | Multi-org |\n| 9-10 | >10K | Platform-wide |\n\n**Impact (0.25-3.0):** Business value\n| Score | Level | Indicators |\n|-------|-------|------------|\n| 0.25 | Minimal | Nice-to-have |\n| 0.5 | Low | QoL improvement |\n| 1.0 | Medium | Efficiency gain |\n| 2.0 | High | Revenue driver |\n| 3.0 | Massive | Strategic differentiator |\n\n**Confidence (0.5-1.0):** Data quality (from Step 3.2)\n\n**Data Confidence Assessment:**\n\nFor each RICE factor, assess data confidence level:\n\n| Confidence | Criteria | Score Modifier |\n|------------|----------|----------------|\n| HIGH | Multiple authoritative sources (Gartner, Statista, SEC filings) | Factor used as-is |\n| MEDIUM | 1-2 sources, mixed quality (blog + report) | Factor ±25% range shown |\n| LOW | No sources, team estimate only | Factor ±50% range shown |\n\n**Output:** Show confidence per factor in prioritization table + RICE range (optimistic\u002Fpessimistic) to make uncertainty explicit.\n\n**Effort (1-10):** Person-months\n| Score | Time | Story Indicators |\n|-------|------|------------------|\n| 1-2 | \u003C2 weeks | 3 AC, simple CRUD |\n| 3-4 | 2-4 weeks | 4 AC, integration |\n| 5-6 | 1-2 months | 5 AC, complex logic |\n| 7-8 | 2-3 months | External dependencies |\n| 9-10 | 3+ months | New infrastructure |\n\n##### Step 3.5: Determine Priority\n\n| Priority | RICE Threshold | Competition Override |\n|----------|----------------|---------------------|\n| P0 (Critical) | >= 30 | OR Competition = 1 (Blue Ocean monopoly) |\n| P1 (High) | >= 15 | OR Competition \u003C= 2 (Emerging market) |\n| P2 (Medium) | >= 5 | - |\n| P3 (Low) | \u003C 5 | Competition = 5 (Red Ocean) forces P3 |\n\n##### Step 3.6: Store and Clear\n\n- Append row to in-memory results table\n- Clear Story description from context\n- Move to next Story in queue\n\n**Output per Story:** Complete row for prioritization table\n\n---\n\n### Phase 4: Generate Prioritization Table (5 min)\n\n**Objective:** Create consolidated markdown output.\n\n**Process:**\n\n1. **Sort results:**\n   - Primary: Priority (P0 → P3)\n   - Secondary: RICE score (descending)\n\n2. **Generate markdown:**\n   - Use template from references\u002Fprioritization_template.md\n   - Fill: Priority Summary, Main Table, RICE Details, Sources\n\n3. **Save file:**\n   ```\n   Write: docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n   ```\n\n**Output:** Saved prioritization.md\n\n---\n\n### Phase 5: Summary & Next Steps (1 min)\n\n**Objective:** Display results and recommendations.\n\n**Output format:**\n```\n## Prioritization Complete\n\n**Epic:** [Epic N - Name]\n**Stories analyzed:** X\n**Time elapsed:** Y minutes\n\n### Priority Distribution:\n- P0 (Critical): X Stories - Implement ASAP\n- P1 (High): X Stories - Next sprint\n- P2 (Medium): X Stories - Backlog\n- P3 (Low): X Stories - Consider deferring\n\n### Top 3 Priorities:\n1. [Story Title] - RICE: X, Market: $XB, Competition: Blue\u002FRed\n\n### Saved to:\ndocs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n\n### Next Steps:\n1. Review table with stakeholders\n2. Run ln-300 for P0\u002FP1 Stories first\n3. Consider cutting P3 Stories\n```\n\n---\n\n## Time-Box Constraints\n\n| Depth | Per-Story | Total (10 Stories) |\n|-------|-----------|-------------------|\n| quick | 2-3 min | 20-30 min |\n| standard | 5-7 min | 50-70 min |\n| deep | 8-10 min | 80-100 min |\n\n**Time management rules:**\n- If Story exceeds time budget: Skip deep research, use estimates (Confidence 0.5)\n- If total exceeds budget: Switch to \"quick\" depth for remaining Stories\n- Parallel WebSearch where possible (market + competition)\n\n---\n\n## Token Efficiency\n\n**Loading pattern:**\n- Phase 2: Metadata only (~50 tokens\u002FStory)\n- Phase 3: Full description ONE BY ONE (~3,000-5,000 tokens\u002FStory)\n- After each Story: Clear description, keep only result row (~100 tokens)\n\n**Memory management:**\n- Sequential processing (not parallel)\n- Maximum context: 1 Story description at a time\n- Results accumulate as compact table rows\n\n---\n\n## Integration with Ecosystem\n\n**Position in workflow:**\n```\nln-210 (Scope → Epics)\n     ↓\nln-220 (Epic → Stories)\n     ↓\nln-230 (RICE per Story → prioritization table) ← THIS SKILL\n     ↓\nln-300 (Story → Tasks)\n```\n\n**Dependencies:**\n- WebSearch, mcp__Ref (market research)\n- Task provider: Linear MCP or file mode (load Epic, Stories)\n- Glob, Write, Bash (file operations)\n\n**Downstream usage:**\n- Sprint planning uses P0\u002FP1 to select Stories\n- ln-300 processes Stories in priority order\n- Stakeholders review before implementation\n\n---\n\n## Critical Rules\n\n1. **Source all data** - Every Market number needs source + date\n2. **Prefer recent data** - last 2 years, warn if older\n3. **Cross-reference** - 2+ sources for Market size (reduce error)\n4. **Time-box strictly** - Skip depth for speed if needed\n5. **Confidence levels** - Mark High\u002FMedium\u002FLow for estimates\n6. **No speculation** - Only sourced claims, note \"[No data]\" gaps\n7. **One Story at a time** - Token efficiency critical\n8. **Preserve language** - If user asks in Russian, respond in Russian\n\n---\n\n## Definition of Done\n\n- [ ] Epic validated (Linear or file mode)\n- [ ] All Stories loaded (metadata, then descriptions per-Story)\n- [ ] Market research completed (2+ sources per Story)\n- [ ] RICE score calculated for each Story\n- [ ] Competition index assigned (1-5)\n- [ ] Priority assigned (P0\u002FP1\u002FP2\u002FP3)\n- [ ] Table sorted by Priority + RICE\n- [ ] File saved to docs\u002Fmarket\u002F[epic-slug]\u002Fprioritization.md\n- [ ] Summary with top priorities and next steps\n- [ ] Total time within budget\n\n---\n\n## Example Usage\n\n**Basic usage:**\n```\nln-230-story-prioritizer epic=\"Epic 7\"\n```\n\n**With parameters:**\n```\nln-230-story-prioritizer epic=\"Epic 7: Translation API\" depth=\"deep\"\n```\n\n**Specific Stories:**\n```\nln-230-story-prioritizer epic=\"Epic 7\" stories=\"US001,US002,US003\"\n```\n\n**Example output (docs\u002Fmarket\u002Ftranslation-api\u002Fprioritization.md):**\n\n| Priority | Customer Problem | Feature | Solution | Rationale | Impact | Market | Sources | Competition |\n|----------|------------------|---------|----------|-----------|--------|--------|---------|-------------|\n| P0 | \"Repeat translations cost GPU\" | Translation Memory | Redis cache, 5ms lookup | 70-90% GPU cost reduction | High | $2B+ | [M&M](link) | 3 |\n| P0 | \"Can't translate PDF\" | PDF Support | PDF parsing + layout | Enterprise blocker | High | $10B+ | [Eden](link) | 5 |\n| P1 | \"Need video subtitles\" | SRT\u002FVTT Support | Timing preservation | Blue Ocean opportunity | Medium | $5.7B | [GMI](link) | 2 |\n\n---\n\n## Phase 6: Meta-Analysis\n\n**MANDATORY READ:** Load `shared\u002Freferences\u002Fmeta_analysis_protocol.md`\n\nSkill type: `planning-coordinator`. Run after all phases complete. Output to chat using the `planning-coordinator` format.\n\n## Reference Files\n\n- **MANDATORY READ:** `shared\u002Freferences\u002Ftools_config_guide.md`\n- **MANDATORY READ:** `shared\u002Freferences\u002Fstorage_mode_detection.md`\n- **MANDATORY READ:** `shared\u002Freferences\u002Fresearch_tool_fallback.md`\n\n| File | Purpose |\n|------|---------|\n| [prioritization_template.md](references\u002Fprioritization_template.md) | Output markdown template |\n| [rice_scoring_guide.md](references\u002Frice_scoring_guide.md) | RICE factor scales and examples |\n| [research_queries.md](references\u002Fresearch_queries.md) | WebSearch query templates by domain |\n| [competition_index.md](references\u002Fcompetition_index.md) | Blue\u002FRed Ocean classification rules |\n\n---\n\n**Version:** 1.0.0\n**Last Updated:** 2025-12-23\n",{"name":5,"license":15,"description":7},"main","fa638b97a18ff6d9f26cf0eaf3dfa123531bcc87","organized-skills\u002Fln-230-story-prioritizer",1,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode","https:\u002F\u002Fgithub.com\u002Flevalencia","https:\u002F\u002Fmedium.com\u002F@luisevalencia","Microsoft MVP - Artificial Intelligence\r\nMachine Learning Enthusiast\r\n","2026-05-02 06:55:36",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add levalencia\u002Fagent-god-mode --skill ln-230-story-prioritizer",{"tool":54,"command":55},"bunx","bunx skills add levalencia\u002Fagent-god-mode --skill ln-230-story-prioritizer",{"tool":57,"command":58},"pnpm","pnpm dlx skills add levalencia\u002Fagent-god-mode --skill ln-230-story-prioritizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-230-story-prioritizer\u002FSKILL.md",true,[62,68,72,76,80,84,88],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fcompetition_index.md","REFERENCE","参考文档",6072,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-230-story-prioritizer\u002Freferences\u002Fcompetition_index.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fprioritization_template.md",4016,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-230-story-prioritizer\u002Freferences\u002Fprioritization_template.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fquality-criteria.md",2617,"https:\u002F\u002Fgithub.com\u002Fzaka33333-hash\u002Fclaude-skills\u002Fblob\u002Fmain\u002Floose-skills\u002Fclaude-md-improver\u002Freferences\u002Fquality-criteria.md",{"path":77,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fresearch_queries.md",7347,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-230-story-prioritizer\u002Freferences\u002Fresearch_queries.md",{"path":81,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Frice_scoring_guide.md",6784,"https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fln-230-story-prioritizer\u002Freferences\u002Frice_scoring_guide.md",{"path":85,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Ftemplates.md",3687,"https:\u002F\u002Fgithub.com\u002Fzaka33333-hash\u002Fclaude-skills\u002Fblob\u002Fmain\u002Floose-skills\u002Fclaude-md-improver\u002Freferences\u002Ftemplates.md",{"path":89,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fupdate-guidelines.md",3197,"https:\u002F\u002Fgithub.com\u002Fzaka33333-hash\u002Fclaude-skills\u002Fblob\u002Fmain\u002Floose-skills\u002Fclaude-md-improver\u002Freferences\u002Fupdate-guidelines.md",[93,115,151,178,204,232],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":34},"01M6EM8ES5M9J4S8N78NJST0YC","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzarr-python\u002FSKILL.md",[],[100,101,102,103,104,105,106,107,108,109,110,111,112,113,114],"python","zarr python","storage","integration","s3","gcs","cloud","dask","parallel","pipelines","arrays","numpy","scientific computing","scale","scientific",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":132,"publishedAt":34},"01M6EM8AR6ZFKZ9YVW8TTG850Z","zabbix","Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper\u002Fsender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User\u002Fpermission management","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fzabbix-api-skill\u002FSKILL.md",[121,124,127],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":128,"categoryName":129,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[117,100,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150],"automation","window management","monitoring","data","templates","api","system","operations","use","maintenance","objects","permission","bulk operations","triggers","host","events","via","bulk",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":34},"01M6EM6Q9JG846ECQY9A210A26","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fx-twitter-growth\u002FSKILL.md",[],[158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177],"twitter","x twitter growth","growth","competitive intelligence","search","analyzing","plan","marketing","web search","competitors","analyze","write","optimize","social","intelligence","viral","growth engine","mechanics","grow","competitive",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":34},"01M6EM3FQNPYNKPC4CV9TCVNGD","what-if-oracle","Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like \"what if...\", \"what would happen if...\", \"what are the possibilities\", \"explore scenarios\", \"scenario analysis\", \"possibility space\", \"what could go wrong\", \"best case \u002F worst case\", \"risk analysis\", \"contingency planning\", \"strategic options\", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fwhat-if-oracle\u002FSKILL.md",[],[185,186,187,188,189,190,191,192,193,194,195,196,141,197,198,199,200,201,202,203],"oracle","what if oracle","test","planning","ux","futures","risk","analysis","explore","decision","branch","question","exploration","options","stress-test","strategies","trigger","case","multi",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":213,"publishedAt":34},"01M6EM08C06RGDYCJ86HAPK0FF","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvercel-react-best-practices\u002FSKILL.md",[210],{"categoryNo":211,"categoryName":212,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[214,215,216,217,218,219,220,221,222,223,224,225,226,136,227,228,229,230,231,146],"react","vercel react best practices","best practices","react best practices","vercel","writing","performance","components","react components","guidelines","tasks","code","Optimization","Next.js","refactoring","performance optimization","next","pages",{"skillNo":233,"name":234,"nameZh":6,"description":235,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":236,"categories":237,"keywords":246,"publishedAt":34},"01M6EM00S13326QM08DTM94J6Z","venue-templates","Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.","https:\u002F\u002Fgithub.com\u002Flevalencia\u002Fagent-god-mode\u002Fblob\u002Fmain\u002Forganized-skills\u002Fvenue-templates\u002FSKILL.md",[238,241,242,243],{"categoryNo":239,"categoryName":240,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":244,"categoryName":245,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000036","内容创作者",[137,247,27,223,248,249,250,251,252,253,254,169,255,256,257,258,259,260,114,261],"venue templates","NeurIPS","ICML","LaTeX","science","Bash","access","read","edit","proposals","Academic","requirements","formatting","journal","chi"]