decision-synthesis
Decision Synthesis
Core principle: Analysis produces options and criteria. Synthesis produces a decision. Most frameworks diverge — generate possibilities, map complexity. This skill converges: makes a defensible, traceable choice. A good decision process maximizes reasoning quality given available information and is transparent enough to learn from.
When to Use
After other frameworks have done their work — Systems Thinking mapped structure, 5 Whys found root causes, Scenario Planning produced futures, Red Teaming attacked options, Stakeholder Mapping identified alignment needs. Now: a rich picture, multiple options, time to land.
The Core Process
Step 1: Clarify What's Being Decided
- Exact choice?
- Decision horizon (reversible 3 months? irreversible?)?
- Final authority?
- Cost of delay?
Many processes fail because people are evaluating different questions without realizing it.
Step 2: Surface All Options
List every viable option, including:
- Status quo (always an option)
- Hybrid approaches
- Sequenced approaches (do A now, revisit B in 6 months)
- Options dismissed early but worth a formal look
Step 3: Define Criteria
- Must-haves (binary — failing = eliminated)
- Want-to-haves (graded — options compared)
Good criteria: specific enough to score ("error rate < 1%"), independent (no double-counting), tied to actual goal not proxies.
Step 4: Weight the Criteria
Distribute 100 points. The allocation is the conversation — exposes hidden disagreements between stakeholders.
Step 5: Score the Options
Score each option × criterion 1–5 (or 1–10) with explicit reasoning. Scores without reasoning can't be challenged.
Step 6: Compute and Challenge
Weighted scores = signal, not verdict:
- Top scorer match intuition? If not, why?
- Which criteria drive the result? Right ones?
- Swap top-two weights — does the answer change?
- Comfortable defending this to a critic?
Output Format
Decision Statement
- Decision: [Exact choice]
- Horizon: [Reversible / Partially / Irreversible]
- Decider: [Authority]
- Deadline: [When resolved]
Options
| # | Option | Brief description |
|---|---|---|
| 1 | [Name] | [One line] |
Criteria & Weights
| Criterion | Type | Weight | Rationale |
|---|---|---|---|
| [C1] | Must-have | — | [Why binary] |
| [C2] | Want-to-have | 35 | [Why this weight] |
| [C3] | Want-to-have | 25 | |
| 100 |
Scoring Matrix
| Option | C1 | C2 (×35) | C3 (×25) | Weighted Total |
|---|---|---|---|---|
| A | Pass | 4 → 140 | 3 → 75 | X |
| B | Pass | 2 → 70 | 5 → 125 | Y |
| C | Fail | — | — | Eliminated |
Recommendation
- Recommended: [Name]
- Primary reason: [1–2 criteria driving result]
- Main trade-off: [What it sacrifices]
- Confidence: [High/Med/Low — based on info quality, not preference strength]
Sensitivity Check
- If [top criterion] changes weight, does answer change?
- Which assumption, if wrong, most undermines this?
- What new info would re-open the decision?
Reversibility & Regret
- Can it be undone? At what cost?
- Regret minimization: which choice produces least regret if situation shifts?
- Low confidence + irreversible → flag explicitly before committing.
Decision Traps
- False consensus: Everyone nods but criteria weights were never explicit — different people solving different things.
- Analysis paralysis: More analysis rarely resolves value disagreements. Name the disagreement and call it.
- Criteria inflation: More criteria adds noise, not signal. Keep the list short and honest.
- Anchoring on first option: Evaluate all options in parallel, not sequentially.
- Score laundering: Working backwards from a preferred conclusion. The matrix is a thinking tool, not a legitimacy machine.
Thinking Triggers
- "If I decided alone, no politics, what would I choose?"
- "Are we weighting what matters or what's easy to measure?"
- "Is there a hybrid we haven't named?"
- "What would a regret minimizer choose? A risk minimizer? A maximizer?"
- "Are we delaying because we need information, or because we don't want to own the decision?"
More from andurilcode/skills
causal-inference
Apply causal inference whenever the user is interpreting metrics, debugging system behavior, reading A/B test results, or trying to understand whether an observed change was caused by an action or by something else. Triggers on phrases like "X caused Y", "since we deployed this, metrics changed", "the A/B test showed a lift", "why did this metric move?", "is this correlation or causation?", "we changed X and Y improved", "how do we know this worked?", "the data shows…", or any situation where conclusions are being drawn from observational data. Also trigger before any decision based on metric interpretation — confusing correlation with causation leads to interventions that don't work and misattribution of credit. Never assume causation without applying this skill.
30probabilistic-thinking
Apply probabilistic and Bayesian thinking whenever the user needs to reason under uncertainty, compare risks, prioritize between options, update beliefs based on new evidence, or make decisions without complete information. Triggers on phrases like "what are the odds?", "how likely is this?", "should I be worried about X?", "which risk is bigger?", "does this data change anything?", "is this a signal or noise?", "what's the probability?", "how confident are we?", or any situation where decisions are being made based on incomplete or ambiguous evidence. Also trigger when someone is treating uncertain outcomes as certainties, or when probability language is being used loosely ("probably", "unlikely", "very likely") without quantification. Don't leave uncertainty unexamined.
27cognitive-bias-detection
Apply cognitive bias detection whenever the user (or Claude itself) is making an evaluation, recommendation, or decision that could be silently distorted by systematic thinking errors. Triggers on phrases like "I'm pretty sure", "obviously", "everyone agrees", "we already invested so much", "this has always worked", "just one more try", "I knew it", "the data confirms what we thought", "we can't go back now", or when analysis feels suspiciously aligned with what someone wanted to hear. Also trigger proactively when evaluating high-stakes decisions, plans with significant sunk costs, or conclusions that conveniently support the evaluator's existing position. The goal is not to paralyze — it's to flag where reasoning may be compromised so it can be corrected.
24inversion-premortem
Apply inversion and pre-mortem thinking whenever the user asks to evaluate a plan, strategy, architecture, feature, or decision before execution — or when they want to stress-test something that already exists. Triggers on phrases like "is this a good idea?", "what could go wrong?", "review this plan", "should we do this?", "are we missing anything?", "stress-test this", "what are the risks?", or any request to validate a decision or design. Use this skill proactively — if the user is about to commit to something, this skill should be consulted even if they don't ask for it explicitly.
23analogical-thinking
Apply analogical thinking whenever the user is designing a system, architecture, or process and would benefit from structural patterns that already exist in other domains — or when a problem feels novel but may have been solved elsewhere under a different name. Triggers on phrases like "how should we structure this?", "has anyone solved this before?", "we're designing from scratch", "what's a good model for this?", "I keep feeling like this resembles something", "what patterns apply here?", or when facing architecture, organizational, or process design decisions. Also trigger when a problem has been analyzed thoroughly but no good solution has emerged — the answer may exist in an adjacent domain. Don't reinvent what's been solved. Recognize the shape of the problem first.
22first-principles-thinking
Apply first principles thinking whenever the user is questioning whether a design, strategy, or solution is fundamentally right — not just well-executed. Triggers on phrases like "are we solving the right problem?", "why do we do it this way?", "is this the best approach?", "everyone does X but should we?", "we've always done it this way", "challenge our assumptions", "start from scratch", "is there a better way?", or when the user seems to be iterating on a flawed premise rather than questioning the premise itself. Also trigger when a proposed solution feels like an incremental improvement on something that may be fundamentally broken. Don't optimize a flawed foundation — question it first.
21