← ClaudeAtlas

self-consistency-reasonerlisted

Internal reasoning technique invoked by systematic-debugging and verification-before-completion for high-stakes multi-step inference. Generates N independent reasoning paths and takes majority vote to surface confident-but-wrong single-chain failures. DO NOT invoke independently — this skill is embedded in the skills that need it.
brunob54/superpowers-orchestrator · ★ 3 · AI & Automation · score 76
Install: claude install-skill brunob54/superpowers-orchestrator
# Self-Consistency Reasoner A structured reasoning technique based on the Self-Consistency method (Wang et al., ICLR 2023). **Core idea**: Complex problems often have multiple valid paths to the correct answer. Incorrect reasoning, even when confident-sounding, tends to scatter across different wrong answers. By generating N independent reasoning paths and taking majority vote, we reliably surface the correct answer and get a built-in confidence signal for free. --- ## When This Fires This skill is invoked internally by: - **systematic-debugging** — during root cause hypothesis generation (Phase 3) - **verification-before-completion** — during evidence evaluation It fires when: - The reasoning requires 3+ non-trivial steps - A single reasoning chain could make a wrong assumption or logical error - The answer has a **fixed answer set** (a root cause, yes/no, a specific conclusion) - Being wrong has real cost (wrong diagnosis wastes edits; false "done" wastes review cycles) --- ## How Many Paths to Generate Scale paths to difficulty: | Problem Type | Paths | |---|---| | Binary verification (does this evidence prove the claim?) | 3 paths | | Root cause diagnosis with 2-3 candidates | 5 paths | | Complex multi-factor diagnosis or high-stakes verification | 7 paths | Default: **5 paths**. Research shows gains plateau quickly — 5 captures most of the benefit of 40. --- ## The Process ### Step 1: Generate N Independent Reasoning Paths Produce each path **independently