AI Agent Skills

Comprehensive code review methodology for evaluating code changes. Identifies bugs, logic errors, security issues, structural problems, performance concerns, and uninten…

Use when named or when the user requests additional context for code review. Review Bitbucket/GitHub PRs or local changes using TWG context, create JSON and Markdown, an…

The Midwit skill is the user’s ongoing anti-complexity gate for a conversation. It triggers on /midwit or requests to maintain an anti-overengineering mode, keep the use…

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility…

Multi-agent code review with parallel specialized reviewers, architecture validation, challenge validation, and durable handling of previously decided findings. Use `rq`…

Use when comparing non-trivial options or making a design/architecture/experiment/product/research/strategy decision with real tradeoffs, unclear criteria, or commitment…

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code…

审查自某个固定基点（commit、分支、tag 或 merge-base）以来的改动，沿两条轴进行——标准（代码是否遵循本仓库记录的编码规范？）和规格（代码是否符合源头工单/规格的要求？）。两项审查在并行子 agent 中运行，并把结果并排报告。当用户想审查一个分支、一个 PR、进行中的改动，或要求「审查自 X 以来」时使用。