Files
gh-lyndonkl-claude/skills/decision-matrix/resources/evaluators/rubric_decision_matrix.json
2025-11-30 08:38:26 +08:00

219 lines
12 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"criteria": [
{
"name": "Decision Framing & Context",
"description": "Is the decision clearly defined with all viable alternatives identified?",
"scoring": {
"1": "Decision is vague or ill-defined. Alternatives are incomplete or include non-comparable options. No stakeholder identification.",
"3": "Decision is stated but lacks specificity. Most alternatives listed but may be missing key options. Stakeholders mentioned generally.",
"5": "Exemplary framing. Decision is specific and unambiguous. All viable alternatives identified (including 'do nothing' if relevant). Must-have requirements separated from criteria. Stakeholders clearly identified with their priorities noted."
}
},
{
"name": "Criteria Quality & Coverage",
"description": "Are criteria well-chosen, measurable, independent, and comprehensive?",
"scoring": {
"1": "Criteria are vague, redundant, or missing key factors. Too many (>10) or too few (<3). No clear definitions.",
"3": "Criteria cover main factors but may have some redundancy or gaps. 4-8 criteria with basic definitions. Some differentiation between options.",
"5": "Exemplary criteria selection. 4-7 criteria that are measurable, independent, relevant, and differentiate between options. Each criterion has clear definition and measurement approach. No redundancy. Captures all important trade-offs."
}
},
{
"name": "Weighting Appropriateness",
"description": "Do criterion weights reflect true priorities and sum to 100%?",
"scoring": {
"1": "Weights don't sum to 100%, are arbitrary, or clearly misaligned with stated priorities. No rationale provided.",
"3": "Weights sum to 100% and are reasonable but may lack explicit justification. Some alignment with priorities.",
"5": "Exemplary weighting. Weights sum to 100%, clearly reflect stakeholder priorities, and have documented rationale (pairwise comparison, swing weighting, or stakeholder averaging). Weight distribution makes sense for decision type."
}
},
{
"name": "Scoring Rigor & Data Quality",
"description": "Are scores based on data or defensible judgments with documented sources?",
"scoring": {
"1": "Scores appear to be wild guesses with no justification. No data sources. Inconsistent scale usage.",
"3": "Mix of data-driven and subjective scores. Some sources documented. Mostly consistent 1-10 scale. Some assumptions noted.",
"5": "Exemplary scoring rigor. Objective criteria backed by real data (quotes, benchmarks, measurements). Subjective criteria have clear anchors/definitions. All assumptions and data sources documented. Consistent 1-10 scale usage."
}
},
{
"name": "Calculation Accuracy",
"description": "Are weighted scores calculated correctly and presented clearly?",
"scoring": {
"1": "Calculation errors present. Weights don't match stated percentages. Formula mistakes. Unclear presentation.",
"3": "Calculations are mostly correct with minor issues. Weighted scores shown but presentation could be clearer.",
"5": "Perfect calculations. Weighted scores = Σ(score × weight) for each option. Table clearly shows raw scores, weights (as percentages), weighted scores, and totals. Ranking is correct."
}
},
{
"name": "Sensitivity Analysis",
"description": "Is decision robustness assessed (close calls, weight sensitivity, score uncertainty)?",
"scoring": {
"1": "No sensitivity analysis. Winner declared without checking if decision is robust.",
"3": "Basic sensitivity noted (e.g., 'close call' mentioned) but not systematically analyzed.",
"5": "Thorough sensitivity analysis. Identifies close calls (<10% margin). Tests weight sensitivity (would swapping weights flip decision?). Notes which scores are most uncertain. Assesses decision robustness and flags fragile decisions."
}
},
{
"name": "Recommendation Quality",
"description": "Is recommendation clear with rationale, trade-offs, and confidence level?",
"scoring": {
"1": "No clear recommendation or just states winner without rationale. No trade-off discussion.",
"3": "Recommendation stated with basic rationale. Some trade-offs mentioned. Confidence level implied but not stated.",
"5": "Exemplary recommendation. Clear winner with score. Explains WHY winner prevails (which criteria drive decision). Acknowledges trade-offs (where winner scores lower). States confidence level based on margin and sensitivity. Suggests next steps."
}
},
{
"name": "Assumption & Limitation Documentation",
"description": "Are key assumptions, uncertainties, and limitations explicitly stated?",
"scoring": {
"1": "No assumptions documented. Presents results as facts without acknowledging uncertainty or limitations.",
"3": "Some assumptions mentioned. Acknowledges uncertainty exists but not comprehensive.",
"5": "All key assumptions explicitly documented. Uncertainties flagged (which scores are guesses vs data). Limitations noted (e.g., 'cost estimates are preliminary', 'performance benchmarks unavailable'). Reader understands confidence bounds."
}
},
{
"name": "Stakeholder Alignment",
"description": "For group decisions, are different stakeholder priorities surfaced and addressed?",
"scoring": {
"1": "Single set of weights/scores presented as if universal. No acknowledgment of stakeholder differences.",
"3": "Stakeholder differences mentioned but not systematically addressed. Single averaged view presented.",
"5": "Stakeholder differences explicitly surfaced. If priorities diverge, shows impact (e.g., 'Under engineering priorities, A wins; under sales priorities, B wins'). Facilitates alignment or escalates decision appropriately."
}
},
{
"name": "Communication & Presentation",
"description": "Is matrix table clear, readable, and appropriately formatted?",
"scoring": {
"1": "Matrix is confusing, poorly formatted, or missing key elements (weights, totals). Hard to interpret.",
"3": "Matrix is readable with minor formatting issues. Weights and totals shown but could be clearer.",
"5": "Exemplary presentation. Table is clean and scannable. Column headers show criteria names AND weights (%). Weighted scores shown (not just raw scores). Winner visually highlighted. Assumptions and next steps clearly stated."
}
}
],
"minimum_score": 3.5,
"guidance_by_decision_type": {
"Technology Selection (tools, platforms, vendors)": {
"target_score": 4.0,
"focus_criteria": [
"Criteria Quality & Coverage",
"Scoring Rigor & Data Quality",
"Sensitivity Analysis"
],
"common_pitfalls": [
"Missing 'Total Cost of Ownership' as criterion (not just upfront cost)",
"Ignoring integration complexity or vendor lock-in risk",
"Not scoring 'do nothing / keep current solution' as baseline"
]
},
"Strategic Choices (market entry, partnerships, positioning)": {
"target_score": 4.0,
"focus_criteria": [
"Decision Framing & Context",
"Weighting Appropriateness",
"Stakeholder Alignment"
],
"common_pitfalls": [
"Weighting short-term metrics too heavily over strategic fit",
"Not including reversibility / optionality as criterion",
"Ignoring stakeholder misalignment on priorities"
]
},
"Vendor / Supplier Evaluation": {
"target_score": 3.8,
"focus_criteria": [
"Criteria Quality & Coverage",
"Scoring Rigor & Data Quality",
"Assumption & Limitation Documentation"
],
"common_pitfalls": [
"Relying on vendor-provided data without validation",
"Not including 'vendor financial health' or 'support SLA' criteria",
"Missing contract terms (pricing lock, exit clauses) as criterion"
]
},
"Feature Prioritization": {
"target_score": 3.5,
"focus_criteria": [
"Weighting Appropriateness",
"Scoring Rigor & Data Quality",
"Sensitivity Analysis"
],
"common_pitfalls": [
"Not including 'effort' or 'technical risk' as criteria",
"Scoring 'user impact' without user research data",
"Ignoring dependencies between features"
]
},
"Hiring Decisions": {
"target_score": 3.5,
"focus_criteria": [
"Criteria Quality & Coverage",
"Scoring Rigor & Data Quality",
"Assumption & Limitation Documentation"
],
"common_pitfalls": [
"Criteria too vague (e.g., 'culture fit' without definition)",
"Interviewer bias in scores (need calibration)",
"Not documenting what good vs poor looks like for each criterion"
]
}
},
"guidance_by_complexity": {
"Simple (3-4 alternatives, clear criteria, aligned stakeholders)": {
"target_score": 3.5,
"sufficient_rigor": "Basic weighting (direct allocation), data-driven scores where possible, simple sensitivity check (margin analysis)"
},
"Moderate (5-7 alternatives, some subjectivity, minor disagreement)": {
"target_score": 3.8,
"sufficient_rigor": "Structured weighting (rank-order or pairwise), documented scoring rationale, sensitivity analysis on close calls"
},
"Complex (8+ alternatives, high subjectivity, stakeholder conflict)": {
"target_score": 4.2,
"sufficient_rigor": "Advanced weighting (AHP, swing), score calibration/normalization, Monte Carlo or scenario sensitivity, stakeholder convergence process (Delphi, NGT)"
}
},
"common_failure_modes": {
"1. Post-Rationalization": {
"symptom": "Weights or scores appear engineered to justify pre-made decision",
"detection": "Oddly specific weights (37%), generous scores for preferred option, stakeholders admit 'we already know the answer'",
"prevention": "Assign weights BEFORE scoring alternatives. Use blind facilitation. Ask: 'If matrix contradicts gut, do we trust it?'"
},
"2. Garbage In, Garbage Out": {
"symptom": "All scores are guesses with no data backing",
"detection": "Cannot answer 'where did this score come from?', scores assigned in <5 min, all round numbers (5, 7, 8)",
"prevention": "Require data sources for objective criteria. Define scoring anchors for subjective criteria. Flag uncertainties."
},
"3. Analysis Paralysis": {
"symptom": "Endless refinement, never deciding",
"detection": ">10 criteria, winner changes 3+ times, 'just one more round' requests",
"prevention": "Set decision deadline. Cap criteria at 5-7. Use satisficing rule: 'Any option >7.0 is acceptable.'"
},
"4. Criterion Soup": {
"symptom": "Overlapping, redundant, or conflicting criteria",
"detection": "Two criteria always score the same, scorer confusion ('how is this different?')",
"prevention": "Independence test: Can option score high on A but low on B? If no, merge them. Write clear definitions."
},
"5. Ignoring Sensitivity": {
"symptom": "Winner declared without robustness check",
"detection": "No mention of margin, close calls, or what would flip decision",
"prevention": "Always report margin. Test: 'If we swapped top 2 weights, does winner change?' Flag fragile decisions."
},
"6. Stakeholder Misalignment": {
"symptom": "Different stakeholders have different priorities but single matrix presented",
"detection": "Engineering wants A, sales wants B, but matrix 'proves' one is right",
"prevention": "Surface weight differences. Show 'under X priorities, A wins; under Y priorities, B wins.' Escalate if needed."
},
"7. Missing 'Do Nothing'": {
"symptom": "Only evaluating new alternatives, forgetting status quo is an option",
"detection": "All alternatives are new changes, no baseline comparison",
"prevention": "Always include current state / do nothing as an option to evaluate if change is worth it."
},
"8. False Precision": {
"symptom": "Scores to 2 decimals when underlying data is rough guess",
"detection": "Weighted total: 7.342 but scores are subjective estimates",
"prevention": "Match precision to confidence. Rough guesses → round to 0.5. Data-driven → decimals OK."
}
}
}