oh-my-snow

Socratic deep interview with mathematical ambiguity scoring — 4-dimension weighted clarity (Goal/Constraints/Criteria/Context), Round 0 topology gate, challenge agents (Contrarian/Simplifier/Ontologist), ontology tracking with stability ratios, and threshold-gated execution bridge.

2 阶段流水线：先 trace 查因果根因（3 道并行调查），再用 3 点注入机制把结果喂给 interview 定需求，最后桥接执行

Strategic planning through consensus — analyzes codebase, drives a Planner→Architect→Critic loop, produces a RALPLAN-DR + ADR decision artifact, and gates execution behind explicit user approval before any code is written.

Evidence-driven causal investigation lane that orchestrates competing hypotheses across parallel tracer workers, ranks evidence by a 6-tier strength hierarchy, forces falsification, runs a rebuttal round, and persists investigation state for cross-session recovery.

截图驱动的视觉 QA 判定器——把当前截图与参考图对比，返回严格 JSON 裁决，驱动下一轮编辑直到通过 90 分阈值

持久化 markdown 知识库，跨会话累积项目知识（ingest/query/lint/add/delete + 交叉引用 + 自动捕获）

Detect and clean up AI-generated redundant or low-quality code.

PRD-driven persistence loop that keeps working on a task until every user story passes acceptance criteria and is reviewer-verified

Extract a repeatable workflow from the current session into a skill draft, then run the evolution pipeline (reflect → explore → evaluate) to optimize it

Conduct autonomous multi-step research combining web search and code analysis.