Decision Frameworks
Decision-making methodologies, scoring frameworks, and planning strategies for Group 2 agents in four-tier architecture
npx skills add majiayu000/claude-skill-registry --skill decision-frameworks --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
This skill offers structured decision-making frameworks and scoring methodologies for Group 2 (Decision Making & Planning) agents. It covers evaluating Group 1 recommendations, aligning with user preferences, and generating execution plans for Group 3. It includes multiple frameworks for scoring, multicriteria analysis, risk-benefit evaluation, prioritization, and user-preference integration, plus trade-off analysis and planning adjustments.
How it works
The skill instructs agents to:
- Evaluate Group 1 recommendations using a Recommendation Evaluation Matrix, computing a total score from confidence, user-preference alignment, historical success, and risk, with explicit 0-100 scoring and weighted contributions.
- Apply a Multi-Criteria Decision Analysis (MCDA) by assigning weights to criteria (e.g., quality impact, effort, risk, user alignment, maintainability), scoring options, normalizing to 0-100, and selecting the highest-scoring option.
- Perform a Risk-Benefit Analysis using a matrix to categorize decisions (quick win, high value, avoid, never do) based on benefit and risk scores.
- Use a Prioritization Matrix (Eisenhower) to sort recommendations into Do First, Schedule, Quick Wins, or Eliminate using urgency and importance signals.
- Integrate User Preferences via a Preference Alignment Scoring method that combines coding style, quality priorities, workflow automation thresholds, and communication detail, returning a score 0-100.
- Adjust execution plans to match user preferences, modifying style instructions, quality targets, and risk-related constraints in the plan.
- Analyze trade-offs across speed vs quality, risk vs benefit, and other axes, returning trade-off items with gains, costs, and mitigations, and provide a decision rule to accept or reject based on user preferences.
When to use it
Use when:
- Evaluating recommendations from Group 1
- Creating execution plans for Group 3
- Prioritizing competing recommendations
- Incorporating user preferences into decisions
- Balancing trade-offs and optimizing for objectives like quality, speed, or cost
- Deciding between multiple valid approaches
- Adjusting plans based on user risk tolerance or workflow preferences
What it can touch
The skill references and uses tools such as:
- claude-code It provides code-style examples, Python snippets, and structured decision logic to implement within an agent's workflow.
Caveats
- The material is described in procedural form with explicit scoring formulas and example code; outcomes depend on real data inputs (confidence, historical data, user prefs).
- No guarantees of specific performance or results are stated beyond the scoring and decision rules defined within each framework.
- License: MIT
# Decision Frameworks Skill ## Overview This skill provides decision-making frameworks, scoring methodologies, and planning strategies specifically for **Group 2 (Decision Making & Planning)** agents in the four-tier architecture. It covers how to evaluate Group 1 recommendations, incorporate user preferences, create execution plans, and make optimal decisions that balance multiple factors. ## When to Apply This Skill **Use this skill when:** - Evaluating recommendations from Group 1 (Strategic Analysis & Intelligence) - Creating execution plans for Group 3 (Execution & Implementation) - Prioritizing competing recommendations - Incorporating user preferences into decisions - Balancing trade-offs (speed vs quality, risk vs benefit) - Deciding between multiple valid approaches - Optimizing for specific objectives (quality, speed, cost) **Required for:** - strategic-planner (master decision-maker) - preference-coordinator (user preference specialist) - Any Group 2 agent making planning decisions ## Group 2 Role Recap **Group 2: Decision Making & Planning (The "Council")** - **Input**: Recommendations from Group 1 with confidence scores - **Process**: Evaluate, prioritize, decide, plan
- Overview
- When to Apply This Skill
- Group 2 Role Recap
- Decision-Making Frameworks
- Framework 1: Recommendation Evaluation Matrix
- Framework 2: Multi-Criteria Decision Analysis (MCDA)
- Framework 3: Risk-Benefit Analysis
- Framework 4: Prioritization Matrix (Eisenhower Matrix)
- User Preference Integration
- Preference Alignment Scoring
- Preference-Based Plan Adjustment
- Trade-Off Analysis
- Framework: Balanced Trade-Off Evaluation
- Planning Strategies
What does the Decision Frameworks skill do?
Decision-making methodologies, scoring frameworks, and planning strategies for Group 2 agents in four-tier architecture
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill decision-frameworks --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.