“coding”

Use when implementation, bug fixing, refactoring, or code review exposes a small, transferable coding skill whose result can be verified and whose…

Use for non-trivial implementation, debugging, refactoring or code review in any project: requirement drift, speculative complexity, agent-facing interfaces.

Explains code snippets in plain English, breaking down what the code does step by step.

Plan, implement, and verify coding tasks in this repository.

Explains code, system behavior, and code changes with plain technical prose, before and after diagrams, pseudocode, call trees, and diffs.

Upcoming and ongoing competitive coding contests (Codeforces, LeetCode, HackerRank).

Connects Figma design components to code components using Code Connect mapping tools.

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE calling the `get_design_context` Figma MCP tool.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding…

Engineering guardrails for writing, editing or reviewing source code, so an edit leaves no residue, keeps every type and reads like the code around it.

React 19 and TypeScript coding standards for Portfolio Buddy 2.

Claude Code 懶人包全集 — 環境建置、MCP 串接、技能安裝。說「Claude Code 懶人包」「安裝懶人包」時載入。

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires…

Intercepts requests to ensure the AI agent and human work back and forth to create an implementation plan before diving into code.

Suede AI code review and A-F ship grade for a diff, PR, branch, or commit range: findings ranked P0-P3 with file:line evidence and a fix path, an A-F grade…

Write automated tests for features, validate functionality against acceptance criteria, and ensure code coverage.

Automated code review with checklist and quality gates

Ejecutar agentes de codificación autónomos como Codex CLI, Claude Code, OpenCode o Aider como sub-agentes.

복합 기능이나 여러 계약을 바꾸는 작업의 범위·완료 조건을 정한다.

복합 코딩 작업에서 주 에이전트가 팀장으로 담당·모델·파일 소유권을 배정하고 결과를 통합한다.

Delegate boilerplate code generation to AiKA.

Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases.

Review code changes for bugs, security issues, and code quality using OpenAI Codex CLI as an external adversarial reviewer.

Use when writing or modifying Python code in workspace/.