Use when executing implementation plans with independent tasks in the current session

Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool...

Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesizing findings into a detailed report via mandatory report-writer agent delegation

Conduct comprehensive research on any topic by coordinating 2-4 specialized researcher agents in parallel, then synthesizing findings into a detailed report via mandatory report-writer agent...

Ensure accurate calendar and date calculations in responses. Use for ANY query involving dates, days of week, date arithmetic, scheduling, holidays, time periods, countdowns, or relative date...

MANDATORY for code review - must use Codex CLI for all code reviews, then apply fixes based on Codex feedback. Also use for cross-verification, debugging, and getting alternative implementations.

Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared...

Interactive spec-driven development workflow with phase-by-phase confirmation. Each phase waits for user confirmation before proceeding. Trigger phrases include "spec-flow", "spec mode", "need a...

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Analyze Claude Code session logs - extract thinking blocks, tool usage stats, error patterns, debug trajectories. Triggers on: introspect, session logs, trajectory, analyze sessions, what went...

Creates and maintains technical documentation including API docs, README files, architecture docs, changelogs, ADRs, and inline code comments. Handles all documentation needs from code-level...

Provides the complete Swift Concurrency Migration Guide. Use when migrating to Swift 6, resolving data-race safety errors, understanding Sendable and actor isolation, or incrementally adopting async/await.

Provides the complete Swift Concurrency Migration Guide. Use when migrating to Swift 6, resolving data-race safety errors, understanding Sendable and actor isolation, or incrementally adopting async/await.

深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 +...

Create MATLAB plain text Live Scripts (.m files) following specific formatting rules. Use when generating MATLAB scripts, educational MATLAB content, Live Scripts, or when the user requests .m...

Provides the complete content of 'The Swift Programming Language (6.2.1)' book by Apple. Use this skill when you need to verify Swift syntax, look up language features, understand concurrency,...

Designs and validates digital filters in MATLAB. Use when cleaning up noisy signals, removing interference, filtering signals, designing FIR/IIR filters (lowpass/highpass/bandpass/bandstop/notch),...

Review code for quality, security, accessibility, and best practices in Next.js and TypeScript projects. Use when the user asks for a code review, review of a PR, or feedback on code changes....

Initialize a repository by analyzing its structure and generating `AGENTS.md` and structured `docs/`, enabling AI coding agents (Claude Code, Codex, Cursor, etc.) to operate safely,...

Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality