From easywork
对仓库执行系统性 bug 巡查、代码审查或质量审计时使用——发现已确认缺陷、高置信度风险、缺失验证、错误处理问题、不安全假设和测试覆盖缺口。
How this skill is triggered — by the user, by Claude, or both
Slash command
/easywork:sweeping-bugsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
对整个仓库执行系统性 bug 巡查,通过并行代码审查发现已确认的缺陷和高置信度风险。
对整个仓库执行系统性 bug 巡查,通过并行代码审查发现已确认的缺陷和高置信度风险。
查找:功能性 bug、行为回归、契约不匹配、缺失验证、错误处理、不安全假设、测试覆盖缺口。
不负责:运行测试并报告结果、同步文档、仅审查最近变更的文件。
读取仓库结构,将代码划分为可并行审查的独立区域。区域划分应根据实际仓库调整,典型维度包括:入口层、核心逻辑、安全策略、持久化、边界集成。
划分决策树:
cmd/、internal/、pkg/)天然是一个候选区域internal/ → internal/handler + internal/service + internal/store)大仓库策略(文件数 > 150 或单区 > 50 文件):
每个区域启动一个子智能体(或主智能体顺序审查):
npx claudepluginhub caikiji/skills-lab --plugin easyworkRuns a structured 14-dimension bug hunt using Draft context (architecture, tech-stack, product) to eliminate false positives. Generates severity-ranked reports with code evidence, data flow traces, and optional regression tests.
Proactively hunts for bugs by analyzing codebase risk (complexity, coverage, structure), then spawns investigators that write reproducing tests to validate suspected bugs. Advisory only — produces findings and tickets, no fixes.
Audits the full codebase for security, quality, and reliability issues, creates GitHub issues for each finding, then fixes them in isolated git worktrees and submits PRs.