ZacharyZhang-NY

Comprehensive code review with security, performance, and style analysis

Smart git commit with conventional message generation and pre-commit safety

Systematic debugging workflow with root cause analysis and targeted fixes

Create structured implementation plans with architecture analysis and task breakdown

Safe code refactoring with behavior preservation, test verification, and incremental steps

Generate comprehensive test suites with unit, integration, and edge case coverage

Interactively create a new Kigi skill (SKILL.md + optional scripts/references). Use when the user wants to create a skill, scaffold a skill, or runs /create-skill.

Kigi documentation and configuration help. Use when users ask about setup, configuration, MCP servers, authentication, skills, slash commands, keyboard shortcuts, or any Kigi feature. Also use proactively when you detect a user is having trouble with setup or onboarding.

Implement a task N ways in parallel and pick the best. Spawns multiple subagents in isolated worktrees, evaluates all candidates, and applies the winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/best-of-n", or "/bon".

Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a deep code quality audit or an especially harsh maintainability review.

苹果前首席设计官 Jony Ive 的设计思维框架。基于 20+ 一手来源蒸馏，含 6 个核心心智模型、10 条决策启发式、完整表达 DNA，以及 Ferrari Luce / OpenAI io 等最新（2026年4月）动态。激活词：设计评审、产品方向、用户体验、审美决策、设计哲学、工业设计、极简主义、Apple 设计、why this shape、care about users

Linus Torvalds 的工程师思维操作系统。基于 11 个一手来源（LKML 原邮件、TED Talk、Tag1/IEEE/GitHub 专访、2024-2026 最新动态）与 50+ 交叉来源，提炼 6 个核心心智模型、12 条反模式识别器、7 步 Good Taste 代码审视清单、4 级表达强度。 用途：在代码审查、架构设计、技术选型、治理决策上作为思维顾问或角色扮演对象。比 v1 (linus-torvalds-perspective) 增加了可运行的 anti-pattern 库、分级表达档位、短路决策路由。 触发词： - 明确点名：「用 Linus 视角」「Linus 会怎么看」「torvalds mode」「#linus」 - 工程动作：「帮我 review 这段代码」「这设计有 good taste 吗」「LKML 风格审这个 PR」「像内核 maintainer 一样评价」 - 求直批：「骂我这段代码」「严厉模式」「别给我客气」「直接说 broken 还是 sane」 - 治理/选型：「这个技术选型怎么看」「开源治理怎么处理」「这是不是 bikeshedding」