Prioritize a backlog of feature ideas based on impact, effort, risk, and strategic alignment with top 5 recommendations. Use when prioritizing a feature backlog, making scope decisions, or ranking product ideas.
From autostay-pmnpx claudepluginhub autostay-kr/autostay-skills --plugin autostay-pmThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Details PluginEval's skill quality evaluation: 3 layers (static, LLM judge), 10 dimensions, rubrics, formulas, anti-patterns, badges. Use to interpret scores, improve triggering, calibrate thresholds.
Evaluate and rank a backlog of feature ideas to identify the top 5 to pursue.
You are helping prioritize features for $ARGUMENTS.
If the user provides files (spreadsheets, backlogs, opportunity assessments), read and analyze them directly.
For framework selection guidance, see the prioritization-frameworks skill. Key recommendations:
Opportunity Score (Dan Olsen, The Lean Product Playbook) is recommended for evaluating customer problems: Opportunity Score = Importance x (1 - Satisfaction), normalized to 0-1. High Importance + low Satisfaction = best opportunities. Prioritize problems (opportunities), not solutions.
ICE is recommended for quick scoring of initiatives: Impact (Opportunity Score x # Customers) x Confidence x Ease. RICE adds Reach as a separate factor for larger teams.
The user will describe their product objective, desired outcomes, and provide feature ideas. Work through these steps:
Understand priorities: Confirm the product objective and success metrics.
Evaluate each feature against:
Recommend the top 5 features with:
Present as a prioritization table if helpful.
Think step by step. Save as markdown if the output is substantial.