From ai-agents
按 plan.md 逐任务执行实现。通过 Todo checkbox 追踪进度,每批改动后运行编译检查。触发短语:"执行计划"、"按计划实现"、"开始实现"。
npx claudepluginhub stringke/ai-agents --plugin ai-agentsThis skill is limited to using the following tools:
按照 plan.md 中的 Todo List 逐任务执行,确保每个改动可验证、可追踪。
Implements tasks from verified plan.md sequentially: writes code, verifies with TDD where applicable, updates plan progress, commits at checkpoints. For structured project execution.
Executes a development plan step-by-step: loads plan, breaks into atomic verifiable steps, implements with per-step verification (build/test), checkpoints progress, final full check.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Share bugs, ideas, or general feedback.
按照 plan.md 中的 Todo List 逐任务执行,确保每个改动可验证、可追踪。
docs/sdlc/ 下查找)按 Todo List 顺序执行每个任务:
[x]执行守卫:
每完成一批相关改动后运行编译检查:
# 根据项目类型选择
tsc --noEmit # TypeScript
./gradlew compileJava # Java/Gradle
cargo check # Rust
go build ./... # Go
python -m py_compile file.py # Python
编译失败时立即修复,不继续下一个任务。
所有任务完成后:
本技能适用于:
大型改动建议使用 /subagent-driven-development,每个任务派遣独立子代理并行执行。