skills/vibe-redundancy-audit/SKILL.md
Use when the user wants to find suspicious redundant business logic, repeated implementation patterns, stale compatibility paths, or low-quality code that should be reviewed for consolidation, reuse, or retirement. Do not use for automatic cleanup or direct code deletion.
npx skillsauth add jacobcy/vibe-coding-control-center vibe-redundancy-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
项目命令参考见
skills/vibe-instruction/SKILL.md
核心职责: 发现可疑的冗余业务逻辑、重复实现模式、迁移后残留路径和低质代码信号,并输出人工复核所需的报告与建议文档。
语义边界:
可疑点、证据、建议,不是自动下结论”这段代码必须删除”。vibe-review-code。本 skill 的目标不是机械地找死代码,而是尽可能提升代码质量,持续发现并暴露以下问题:
本 skill 体现的是 Vibe 项目自己的冗余逻辑审查方法,不是通用 dead code 教程。
本项目的理想结构是:
因此,本 skill 的审查重点是:
thin commands 是否真的变薄,而不是只“多加一层”本 skill 必须优先使用仓库真源里的 V3 CLI 能力做证据收集,默认使用兼容写法:
uv run python src/vibe3/cli.py <subcommand>
重点使用以下能力:
vibe3 inspect base --json
vibe3 inspect commit <sha> --json
vibe3 inspect files <file> --json
vibe3 inspect symbols <file>:<symbol> --json
vibe3 snapshot show <file> --json
补充说明:
inspect files / snapshot show 适合发现“形状异常”和“分层仍过厚”的嫌疑点。inspect symbols 更适合作为二次验证器,而不是唯一发现器。inspect base / inspect commit 用来回答“这次重构是否同时新增新路径但未回收旧路径”。inspect base 或 inspect commit 锁定本次改动范围与重点文件。inspect files 或 structure show,识别以下信号:
inspect symbols,确认调用面。# a. 将完整报告写入 .agent/reports/ 目录
# b. 记录审计事件
vibe3 handoff audit "<报告文件路径>" --actor "<actor标识>"
# c. 用 handoff append 记录关键发现和下一步
vibe3 handoff append "发现摘要: ..." --actor "<actor标识>" --kind finding
vibe3 handoff append "下一步: ..." --actor "<actor标识>" --kind next
不得跳过此步骤。handoff 是下游 agent(如 spec agent、执行 agent)获取审查结果的唯一标准通道。可疑点分类说明见 references/suspicion-signals.md。
输出必须分成三个层次:
每个可疑点必须包含:
locationsuspicion_typewhy_flaggedevidencemanual_check当用户要求落文档时,生成一份建议文档,归纳:
建议文档是审查建议,不是清理执行单。
审查完成后,必须使用标准 handoff 命令将结果写入 handoff:
# 记录审计事件(引用报告文件)
vibe3 handoff audit "<报告路径>" --actor "<actor标识>"
# 记录关键发现
vibe3 handoff append "发现摘要: ..." --actor "<actor标识>" --kind finding
# 记录下一步建议
vibe3 handoff append "下一步: ..." --actor "<actor标识>" --kind next
# 记录阻塞项(如有)
vibe3 handoff append "阻塞: ..." --actor "<actor标识>" --kind blocker
完整报告存入 .agent/reports/ 目录。不写 handoff 的审查结果视为未完成。
.git/vibe* 或其他共享状态真源inspect symbols 显示 0 引用就直接下结论,必须结合 CLI 入口、兼容性和分层语义人工判断development
Use after `vibe init` to verify project configuration completeness. Interactively prompts user to fill missing items. Orchestrates existing commands without adding Python code. Supports cross-project vibe3 readiness verification (Phase 5-8). Do not use for system-level installation issues (use vibe-onboard instead).
development
Use when the user wants a comprehensive review using the multi-agent team workflow. Applies to PRs, code changes, architecture decisions, and any task requiring team-based analysis.
development
Use when manager has signaled flow terminal state cleanup via handoff indicate. Reads cleanup instructions and executes FlowCleanupService. Do not use for code changes or PR creation.
testing
Use for handling blocked and RFC issues, making decisions that may form ADRs (Architecture Decision Records). Processes problem issues requiring human judgment, dependency resolution, and architectural decisions. Do not use for routine issue monitoring (use vibe-orchestra) or roadmap planning (use vibe-roadmap).