Skip to content
ln-230-story-prioritizer logo

Story Prioritizer

ln-230-story-prioritizer

RICE prioritization per Story with market research. Generates consolidated prioritization table in docs/market/[epic-slug]/prioritization.md. L2 worker called after ln-220.

SKILL.md

Full skill instructions

Story Prioritizer

Evaluate Stories using RICE scoring with market research. Generate consolidated prioritization table for Epic.

Purpose & Scope

  • Prioritize Stories AFTER ln-220 creates them
  • Research market size and competition per Story
  • Calculate RICE score for each Story
  • Generate prioritization table (P0/​P1/​P2/​P3)
  • Output: docs/​market/[epic-slug]/​prioritization.md

When to Use

Use this skill when:

  • Stories created by ln-220, need business prioritization
  • Planning sprint with limited capacity (which Stories first?)
  • Stakeholder review requires data-driven priorities
  • Evaluating feature ROI before implementation

Do NOT use when:

  • Epic has no Stories yet (run ln-220 first)
  • Stories are purely technical (infrastructure, refactoring)
  • Prioritization already exists in docs/​market/

Who calls this skill:

  • User (manual) - after ln-220-story-coordinator
  • Future: ln-200-scope-decomposer (optional Phase)

Input Parameters

ParameterRequiredDescriptionDefault
epicYesEpic ID or "Epic N" format-
storiesNoSpecific Story IDs to prioritizeAll in Epic
depthNoResearch depth (quick/​standard/​deep)"standard"

depth options:

  • quick - 2-3 min/​Story, 1 WebSearch per type
  • standard - 5-7 min/​Story, 2-3 WebSearches per type
  • deep - 8-10 min/​Story, comprehensive research

Output Structure

docs/​market/[epic-slug]/
└── prioritization.md    # Consolidated table + RICE details + sources

Table columns (from user requirements):

PriorityCustomer ProblemFeatureSolutionRationaleImpactMarketSourcesCompetition
P0User pain pointStory titleTechnical approachWhy importantBusiness impact$XB[Link]Blue 1-3 / Red 4-5

Research Tools

ToolPurposeExample Query
WebSearchMarket size, competitors"[domain] market size 2025"
mcp__RefIndustry reports"[domain] market analysis report"
LinearLoad Storieslist_issues(project=Epic.id)
GlobCheck existing"docs/​market/[epic]/​*"

Workflow

Phase 1: Discovery (2 min)

Objective: Validate input and prepare context.

Process:

  1. Parse Epic input:

    • Accept: Epic ID, "Epic N", or Linear Project URL
    • Query: get_project(query=epic)
    • Extract: Epic ID, title, description
  2. Auto-discover configuration:

    • Read docs/​tasks/​kanban_board.md for Team ID
    • Slugify Epic title for output path
  3. Check existing prioritization:

    Glob: docs/​market/[epic-slug]/​prioritization.md
    
    • If exists: Ask "Update existing or create new?"
    • If new: Continue
  4. Create output directory:

    mkdir -p docs/​market/[epic-slug]/
    

Output: Epic metadata, output path, existing check result


Phase 2: Load Stories Metadata (3 min)

Objective: Build Story queue with metadata only (token efficiency).

Process:

  1. Query Stories from Epic:

    list_issues(project=Epic.id, label="user-story")
    
  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


Phase 3: Story-by-Story Analysis Loop (5-10 min/​Story)

Objective: For EACH Story: load description, research, score RICE.

Critical: Process Stories ONE BY ONE for token efficiency!

Per-Story Steps:
Step 3.1: Load Story Description
get_issue(id=storyId, includeRelations=false)

Extract from Story:

  • Feature: Story title
  • Customer Problem: From "So that [value]" + Context section
  • Solution: From Technical Notes (implementation approach)
  • Rationale: From AC + Success Criteria
Step 3.2: Research Market Size

WebSearch queries (based on depth):

"[customer problem domain] market size TAM 2025"
"[feature type] industry market forecast"

mcp__Ref query:

"[domain] market analysis Gartner Statista"

Extract:

  • Market size: $XB (with unit: B=Billion, M=Million)
  • Growth rate: X% CAGR
  • Sources: URL + date

Confidence mapping:

  • Industry report (Gartner, Statista) → Confidence 0.9-1.0
  • News article → Confidence 0.7-0.8
  • Blog/​Forum → Confidence 0.5-0.6
Step 3.3: Research Competition

WebSearch queries:

"[feature] competitors alternatives 2025"
"[solution approach] market leaders"

Count competitors and classify:

Competitors FoundCompetition IndexOcean Type
01Blue Ocean
1-22Emerging
3-53Growing
6-104Mature
>105Red Ocean
Step 3.4: Calculate RICE Score
RICE = (Reach x Impact x Confidence) / Effort

Reach (1-10): Users affected per quarter

ScoreUsersIndicators
1-2<500Niche, single persona
3-4500-2KDepartment-level
5-62K-5KOrganization-wide
7-85K-10KMulti-org
9-10>10KPlatform-wide

Impact (0.25-3.0): Business value

ScoreLevelIndicators
0.25MinimalNice-to-have
0.5LowQoL improvement
1.0MediumEfficiency gain
2.0HighRevenue driver
3.0MassiveStrategic differentiator

Confidence (0.5-1.0): Data quality (from Step 3.2)

Effort (1-10): Person-months

ScoreTimeStory Indicators
1-2<2 weeks3 AC, simple CRUD
3-42-4 weeks4 AC, integration
5-61-2 months5 AC, complex logic
7-82-3 monthsExternal dependencies
9-103+ monthsNew infrastructure
Step 3.5: Determine Priority
PriorityRICE ThresholdCompetition Override
P0 (Critical)>= 30OR Competition = 1 (Blue Ocean monopoly)
P1 (High)>= 15OR Competition <= 2 (Emerging market)
P2 (Medium)>= 5-
P3 (Low)< 5Competition = 5 (Red Ocean) forces P3
Step 3.6: Store and Clear
  • Append row to in-memory results table
  • Clear Story description from context
  • Move to next Story in queue

Output per Story: Complete row for prioritization table


Phase 4: Generate Prioritization Table (5 min)

Objective: Create consolidated markdown output.

Process:

  1. Sort results:

    • Primary: Priority (P0 → P3)
    • Secondary: RICE score (descending)
  2. Generate markdown:

    • Use template from references/​prioritization_template.md
    • Fill: Priority Summary, Main Table, RICE Details, Sources
  3. Save file:

    Write: docs/​market/[epic-slug]/​prioritization.md
    

Output: Saved prioritization.md


Phase 5: Summary & Next Steps (1 min)

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

Time-Box Constraints

DepthPer-StoryTotal (10 Stories)
quick2-3 min20-30 min
standard5-7 min50-70 min
deep8-10 min80-100 min

Time management rules:

  • If Story exceeds time budget: Skip deep research, use estimates (Confidence 0.5)
  • If total exceeds budget: Switch to "quick" depth for remaining Stories
  • Parallel WebSearch where possible (market + competition)

Token Efficiency

Loading pattern:

  • Phase 2: Metadata only (~50 tokens/​Story)
  • Phase 3: Full description ONE BY ONE (~3,000-5,000 tokens/​Story)
  • After each Story: Clear description, keep only result row (~100 tokens)

Memory management:

  • Sequential processing (not parallel)
  • Maximum context: 1 Story description at a time
  • Results accumulate as compact table rows

Integration with Ecosystem

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:

  • WebSearch, mcp__Ref (market research)
  • Linear MCP (load Epic, Stories)
  • Glob, Write, Bash (file operations)

Downstream usage:

  • Sprint planning uses P0/​P1 to select Stories
  • ln-300 processes Stories in priority order
  • Stakeholders review before implementation

Critical Rules

  1. Source all data - Every Market number needs source + date
  2. Prefer recent data - 2024-2025, warn if older
  3. Cross-reference - 2+ sources for Market size (reduce error)
  4. Time-box strictly - Skip depth for speed if needed
  5. Confidence levels - Mark High/​Medium/​Low for estimates
  6. No speculation - Only sourced claims, note "[No data]" gaps
  7. One Story at a time - Token efficiency critical
  8. Preserve language - If user asks in Russian, respond in Russian

Definition of Done

  • Epic validated in Linear
  • All Stories loaded (metadata, then descriptions per-Story)
  • Market research completed (2+ sources per Story)
  • RICE score calculated for each Story
  • Competition index assigned (1-5)
  • Priority assigned (P0/​P1/​P2/​P3)
  • Table sorted by Priority + RICE
  • File saved to docs/​market/[epic-slug]/​prioritization.md
  • Summary with top priorities and next steps
  • Total time within budget

Example 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):

PriorityCustomer ProblemFeatureSolutionRationaleImpactMarketSourcesCompetition
P0"Repeat translations cost GPU"Translation MemoryRedis cache, 5ms lookup70-90% GPU cost reductionHigh$2B+M&M3
P0"Can't translate PDF"PDF SupportPDF parsing + layoutEnterprise blockerHigh$10B+Eden5
P1"Need video subtitles"SRT/​VTT SupportTiming preservationBlue Ocean opportunityMedium$5.7BGMI2

Reference Files

FilePurpose
prioritization_template.mdOutput markdown template
rice_scoring_guide.mdRICE factor scales and examples
research_queries.mdWebSearch query templates by domain
competition_index.mdBlue/​Red Ocean classification rules

Version: 1.0.0 Last Updated: 2025-12-23

More DevOps & CI/CD skills

Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.

6K 472.6K
View

Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.

6K 472.6K
View

Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.

1.5K 454.3K
View
azure-kubernetes logo
DevOps & CI/CD

azure-kubernetes

Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.

1.5K 447.1K
View

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

92.7K 354.9K
View
just-scrape logo
DevOps & CI/CD

just-scrape

Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.

69 245K
View

Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.

462 159.7K
View

Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.

462 159.1K
View
deploy-to-vercel logo
DevOps & CI/CD

deploy-to-vercel

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

31.9K 146.6K
View
programmatic-seo logo
DevOps & CI/CD

programmatic-seo

Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.

53.3K 140.1K
View

Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.

63 123.5K
View

Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".

31.9K 116.1K
View

Coding & apps AI tools

Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View
Imagica logo
Coding & apps

Imagica

Build a no-code AI app in minutes.

Freemium
View
E
Coding & apps

Emergent.sh

An IDE for code migration from legacy to modern frameworks through coding agents.

Freemium
View
Wonder Dynamics logo
Coding & apps

Wonder Dynamics

Automate CGI animation in live-action scenes

Paid
View
M
Coding & apps

Mixo

Launch a website in seconds with AI.

Paid
View
AI Code Convert logo
Coding & apps

AI Code Convert

Streamline Your Coding Experience with AI Code Helper

Free
View