From arete
Synthesizes options from explore phase into technical/conceptual decision matrices, forces prioritization of trade-offs, challenges choices, and commits to reversible bets.
npx claudepluginhub jesgarram/arete --plugin areteThis skill uses the workspace's default tool permissions.
**System 2** | Goal: Select one clear path with full awareness of trade-offs
Generates 5 probability-weighted alternative options, including at least one unconventional, with trade-offs to challenge default thinking and expose assumptions in decision points.
Generates exactly 5 probability-weighted alternative options for decisions, forcing at least one unconventional idea with pros/cons trade-offs to expose assumptions.
Evaluates competing approaches via independent assessments, reasoning-out-loud advocacy, confidence thresholds, and deadlock resolution for coherent decisions. Use when selecting among multiple options or justifying high-stakes choices.
Share bugs, ideas, or general feedback.
System 2 | Goal: Select one clear path with full awareness of trade-offs
Pull the distinct approaches from explore phase (typically 2-5).
Display each option with these dimensions:
Technical:
| Option | Effort | Risk | Reversibility | Ops Burden |
|---|---|---|---|---|
| A | ... | ... | ... | ... |
| B | ... | ... | ... | ... |
Conceptual:
| Option | Impact | Effort | Resistance | Reversibility |
|---|---|---|---|---|
| A | ... | ... | ... | ... |
Reversibility is consistently the most undervalued axis in tech decisions. Always include it. A reversible bad decision costs far less than an irreversible one.
Then prompt ranking:
Technical trade-offs: Consistency vs Availability | Throughput vs Latency | Simplicity vs Flexibility | Read vs Write | Guarantees vs Operational simplicity
Conceptual trade-offs: Inspiration vs Detail vs Fear
Never accept without justification: "Why this over [Alternative]?" / "Truly willing to sacrifice [X]?"
Frame the choice as a provisional bet, not a final commitment: "What evidence would change your mind?" This prevents both analysis paralysis and sunk-cost lock-in. The decision is real but reversible if stress-testing reveals problems.
4-6 lines, 50% questions. One question per response. Objective, analytical, skeptical. Acknowledge the user's reasoning before challenging it.
Coverage: Trade-offs explicitly weighed for selected option Saturation: User stops wavering; preference is stable Gate: "Any trade-offs we haven't weighed?"
When criteria met → announce gate → user confirms → call Skill(skill: "arete:stress") to load the stress phase. Do NOT continue inline.