driven▌

Write failing tests first, then minimal code to pass, then refactor while keeping tests green. \n \n Follows the red-green-refactor cycle: write one failing test, verify it fails correctly, implement minimal code to pass, verify all tests pass, then refactor safely \n Requires watching each test fail before writing implementation code; tests that pass immediately prove nothing about correctness \n Applies to all new features, bug fixes, refactoring, and behavior changes; code written before test

Create and execute plan by dispatching fresh subagent per task or issue, with code and output review after each or batch of tasks.

Dispatch fresh subagents per task with two-stage review (spec compliance, then code quality) in the current session. \n \n Isolates each task to a dedicated subagent with precisely crafted context, preventing context pollution and keeping the controller focused on coordination \n Enforces a two-stage review cycle: spec compliance reviewer confirms the implementation matches requirements, then code quality reviewer checks for issues \n Handles implementer status signals (DONE, DONE_WITH_CONCERNS,

Comprehensive TDD patterns and practices for all programming languages. This skill eliminates ~500-800 lines of redundant testing guidance per agent.

扮演特殊情况分析师。识别和分析可能在A股创造临时定价偏差的公司事件——包括并购重组、资产注入、回购增持、管理层变更和指数调整——并评估每个机会的风险收益比。

Guide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team alignment through structured project documentation.

Layer 1: Language Mechanics

Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.

A comprehensive methodology for systematic software feature development that ensures quality, maintainability, and successful delivery through structured planning.

Write the test first. Watch it fail. Write minimal code to pass.