Skills for Real Engineers. Straight from my .agents directory.
How to install code-review
npx skills add Shy2593666979/AgentChat# or add only this skill to Claude Code: copy the folder
src/backend/agentchat/config/skills/code-review/
# into
~/.claude/skills/code-review/ (all projects)
.claude/skills/code-review/ (one project)
1# 代码审查23围绕用户指定的变更范围审查。需要上下文时,说明缺少的调用方、模型或测试信息,不把未知情况当作已确认缺陷。45## 工作方法671. 概括变更目的和受影响的行为,明确实际收到的是完整文件还是差异片段。82. 沿输入、状态变化与输出核对逻辑。重点关注空值、错误路径、并发、资源释放、权限边界及接口兼容性。93. 对每个候选问题寻找具体触发条件与证据。已由调用方或类型约束排除的问题不报告为缺陷。104. 按影响排序发现项,说明位置、触发方式、后果与最小修复方向。不能定位行号时使用函数名或代码片段,不虚构位置。115. 给出针对行为的验证方法。纯风格偏好放在可选建议,不与功能问题混排。1213使用 `/code-review/reference/output-template.md` 输出发现项;交付前读取 `/code-review/reference/review-checklist.md`。1415## 能力边界1617当前只能审查实际提供的代码与技能文件,不具备访问用户代码仓库或执行测试的能力。不要声称运行过测试或检查过未提供的文件。没有发现有依据的缺陷时直接说明,并列出实际审查范围。
Excerpt shown under the repository's MIT license.
More skills in AgentChat
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
