How this skill is triggered — by the user, by Claude, or both
Slash command
/dev-harness:generic-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- 必须对比 plan/PRD 与实际代码,不凭印象审计
| 维度 | 检查内容 | 严重级别 |
|---|---|---|
| 需求覆盖 | plan 中每个变更点是否都已实现 | HIGH |
| 代码质量 | 空指针、资源泄露、异常处理、边界条件 | MEDIUM-HIGH |
| 安全性 | SQL 注入、XSS、敏感信息泄露、权限校验 | HIGH |
| 错误处理 | 异常是否正确捕获和上报 | MEDIUM |
| 一致性 | 命名规范、代码风格、项目约定 | LOW |
.claude/reports/audit-{module}-{date}.md(格式见 report-template.md)。
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub brothelmdzz/dev-harness --plugin dev-harness