Large changes are difficult to test, review, and recover when problems appear late. This skill breaks work into complete increments with explicit tests, verification, and rollback points.

Long sessions can turn assumptions into accepted facts and hide costly failure modes. This skill applies bounded, fresh-context adversarial review before non-trivial decisions stand.

Debugging failures by guesswork wastes time and can hide the real cause. This skill provides a repeatable process for reproducing, isolating, fixing, and verifying problems.

Teams often lack measurable quality standards, allowing checks and thresholds to drift during development. This skill defines a shared contract and connects each constraint to practical enforcement.

Coding agents lose accuracy when context is incomplete, stale, or excessive. This skill provides practical structures for focused sessions, durable rules, and reliable handoffs.

Complex code slows reviews, maintenance, and debugging. This skill guides focused refactoring that improves clarity while preserving behavior, errors, side effects, and tests.

Unclear contracts, inconsistent errors, and unsafe retries make APIs difficult to use and evolve. This skill provides practical patterns for typed interfaces, validation boundaries, compatibility, pagination, and idempotency.

Browser bugs can hide behind static code and incomplete unit tests. This skill uses Chrome DevTools MCP to inspect live behavior and verify fixes with runtime evidence.

Manual test design and fragmented tools slow reliable releases. This skill plans, writes, runs, and reports automated, API, performance, and CI tests.

Complex systems require explicit boundaries, trade-offs, and operational constraints. This skill structures architecture analysis, diagrams, decisions, and documentation for review.

Search teams need reliable guidance across indexing, ranking, semantic retrieval, and evaluation. This skill provides practical workflows and examples for building and improving search systems.

Full-stack teams often lack a repeatable way to measure performance and locate bottlenecks. This skill provides testing workflows, diagnostic commands, optimization guidance, and report structures.

Payment teams need consistent designs for transactions, channels, reconciliation, security, and failure handling. This skill provides structured guidance, examples, and review checklists.

Mobile teams must coordinate platform architecture, tooling, testing, performance, and release requirements. This skill provides practical guidance and examples for native and cross-platform workflows.

Backend projects require consistent choices across APIs, databases, security, performance, and deployment. This skill provides structured workflows, checklists, commands, and FastAPI examples.

複雜的程式碼開發請求，常因後續步驟模糊而失敗。此技能會將需求轉換為清晰的計畫，包含檔案、測試、命令與執行交接。

Lighthouse 對比稽核失敗可能會隱藏可執行的 SEO 與無障礙結果。此技能針對 CSS 對比問題提供聚焦檢查與修復模式。

為 Next.js 網站新增語言可能會破壞路由、SEO 和翻譯檔案。此 skill 提供腳本、檢查清單和參考資料，用於結構化的 i18n 推出流程。

已完成的程式碼仍需要一條乾淨的路徑進入主要工作流程。此技能會引導測試檢查、合併或 pull request 選擇，以及在確認後清理分支。

含糊的 coding-agent 任務經常偏離方向、重複作業，或在沒有證據的情況下停止。這項技能會將請求轉換為有界限的迴圈規格，包含驗證器、停止規則與交接封包。