build-coherencelisted
Install: claude install-skill pjt222/agent-almanac
# Build Coherence
Evaluate competing approaches through independent assessment, explicit reasoning-out-loud advocacy, confidence-calibrated commitment thresholds, and structured deadlock resolution — producing coherent decisions from multiple reasoning paths.
## When to Use
- `forage-solutions` has identified multiple valid approaches and a selection must be made
- Oscillating between two approaches without committing to either
- Needing to justify a decision with structured reasoning (architecture choice, tool selection, implementation strategy)
- When a previous decision was made by gut feeling and needs evidence-based validation
- When internal reasoning is producing contradictory conclusions and coherence must be restored
- Before an irreversible action (merging, deploying, deleting) where the cost of the wrong choice is high
## Inputs
- **Required**: Two or more competing approaches to evaluate
- **Optional**: Quality assessments from prior scouting (see `forage-solutions`)
- **Optional**: Decision stakes (reversible, moderate, irreversible) for threshold calibration
- **Optional**: Time budget for the decision
- **Optional**: Known failure mode (oscillation, premature commitment, groupthink)
## Procedure
### Step 1: Independent Evaluation
Assess each approach on its own merits before comparing them. The critical rule: do not let the assessment of approach A bias the assessment of approach B.
For each approach, evaluate independently:
```text
Approach Evaluatio