Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Stay current with how OpenCode, OpenAI Codex, and Claude Code implement extensibility features (skills, slash commands, subagents, custom prompts). Use when comparing implementations across AI...
Generate hierarchical AGENTS.md structures for codebases. Use when user asks to create AGENTS.md files, analyze codebase for AI agent documentation, set up AI-friendly project documentation, or...
Generate or update an ESLint plugin that exports rule configs compatible with ESLint v8 (eslintrc) and ESLint v9 (flat config).
Performs comprehensive code reviews focusing on correctness, maintainability, performance, security, and best practices. Trigger keywords: review, code review, PR review, pull request, check code,...
Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches...
Generate AGENTS.md and AI configuration files for your project. Use when the user wants to create agent instructions, set up AI configs, or says "create AGENTS.md", "configure my AI assistant", or...
AI coding agent that plans, implements, and verifies code changes with human approval gates. Built on FlatAgents.
Rewrites changelog entries with cheeky, narrative flair following project conventions. Use this when asked to rewrite or update CHANGELOG.md entries.
Generate nested AGENTS.md coding guidelines per module (monorepo-aware), detect languages/tooling, ask architecture preferences, and set up missing formatters/linters (Spotless for JVM). Use when...
Create GitHub pull requests directly via API from code changes. Analyzes branch commits, generates PR titles and descriptions, and creates PRs on GitHub by default. Use when user wants to create...
This skill should be used when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents,...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
Guide for multi-platform skill compatibility across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and other AI coding agents.
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world...
AI Agent 协作团队系统 - 基于 newtype-profile 架构。模拟编辑团队模型，通过多个专业 Agent 协作完成复杂任务。适用于内容创作、研究分析、知识管理等场景。核心 Agent: chief(主编/协调者), researcher(研究员), writer(作者), editor(编辑), fact-checker(核查员),...
Use when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.