菜单
Instructions for the agent on how to run python scripts correctly in this environment.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyzes code quality, complexity, and technical debt using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - User mentions "code quality", "complexity", "technical debt", "grades", or "health score" - Reviewing code, refactoring, or conducting root cause analysis (Five Whys) - Creating pull requests or preparing commits - Investigating performance or quality issues Supports 25+ languages including Rust, Python, TypeScript, JavaScript, Go, C++, Java, etc. Provides Technical Debt Grading (TDG), Repo Health Scores, 5-Whys debugging, cyclomatic/cognitive complexity, and dead code detection.
Run a quick smoke test to verify the RL framework is working end-to-end. Use when checking basic functionality after changes or before committing.
Locates and reads configuration files for agents (e.g., MuZero, PPO) or games (e.g., CartPole, Atari). Use this to check hyperparameters or network settings.
Runs static analysis (pylint) on Python files to ensure code quality standards are met. Use this before finalizing any code changes or when the user asks to "check the code".
Generates comprehensive, LLM-optimized codebase context using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - Starting work on unfamiliar codebases - Onboarding to new projects or repositories - Need quick understanding of project architecture - Preparing for refactoring or feature implementation - Creating documentation or technical specifications Outputs highly compressed markdown (60-80% reduction) optimized for LLM consumption. Supports 25+ languages with architecture visualization, complexity heatmaps, and dependency graphs.
Analyzes polyglot codebases with multiple programming languages using PMAT (Pragmatic AI Labs MCP Agent Toolkit). Use this skill when: - Working with projects containing multiple programming languages - Assessing cross-language integration patterns and quality - Understanding language distribution and architectural boundaries - Comparing quality metrics across language ecosystems - Identifying language-specific best practices violations Supports 25+ languages including Rust, Python, TypeScript, JavaScript, Go, C++, Java, Ruby, PHP, Swift, Kotlin, C, C#, Scala, Haskell, Elixir, Clojure, Dart, Lua, R, and more. Provides unified quality assessment across heterogeneous codebases.
| name | agent-setup |
| description | Instructions for the agent on how to run python scripts correctly in this environment. |
When running Python scripts that involve PyTorch, Ray, or Compilation in this workspace, you MUST set the ANTIGRAVITY_AGENT environment variable to 1.
This ensures that:
torch.compile artifacts.When using run_command or similar tools, prepend the variable:
ANTIGRAVITY_AGENT=1 python my_script.py
Do NOT set this permanently in a .rc file; just apply it to your runtime commands.