From ai-agents
完成声明前必须提供验证证据。铁律：没有验证证据就不宣称完成。触发短语："验证"、"确认完成"、"verify"。
npx claudepluginhub stringke/ai-agents --plugin ai-agentsThis skill is limited to using the following tools:
**没有验证证据就不宣称完成。**
Enforces running tests, linters, builds and confirming outputs before claiming completion, fixes, or test passes—requires evidence before commits/PRs.
Enforces running test suites, linters, and behavior checks before claiming code is complete, fixed, or passing. Shows outputs to confirm success and prevent regressions.
Enforces running verification commands (lint/test/build/typecheck) and checklists before claiming task completion, committing code, or creating PRs. Loops with reflection until all pass, checks git diff and code size.
Share bugs, ideas, or general feedback.
没有验证证据就不宣称完成。
在声称任何任务"已完成"之前，必须运行验证命令并展示输出。
在宣称完成之前，按顺序执行：
可接受的证据：
不可接受的证据：
# 示例验证序列
npm run lint && npm run build && npm test
./gradlew check
cargo clippy && cargo test
go vet ./... && go test ./...
如果任何验证步骤失败，修复后重新验证，直到全部通过。