Data & AI

Guide for using Repomix - a powerful tool that packs entire repositories into single, AI-friendly files. Use when packaging codebases for AI analysis, generating context for LLMs, creating codebase snapshots, analyzing third-party libraries, or preparing repositories for security audits.

Guide for implementing Google Cloud SDK (gcloud CLI) - a command-line tool for managing Google Cloud resources. Use when installing/configuring gcloud, authenticating with Google Cloud, managing projects/configurations, deploying applications, working with Compute Engine/GKE/App Engine/Cloud Storage, scripting gcloud operations, implementing CI/CD pipelines, or troubleshooting Google Cloud deployments.

将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求，生成符合 OpenAI/Google Deep Research 标准的结构化提示词。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研究提示词时使用此技能。

Operate E2B agent sandboxes using the CLI. Use when user needs to run code in isolation, test packages, execute commands safely, or work with binary files in a sandbox environment. Keywords: sandbox, e2b, isolated environment, run code, test code, safe execution.

Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations

SvelteKit data flow guidance. Use for load functions, form actions, and server/client data. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error().

Run the project's formatter, linters, and mypy checks in the required order, fixing issues and managing any needed stub dependencies via uv.

Add purposeful debug logging to improve observability without changing behavior.

Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.

Write focused pytest tests as standalone functions (one test per function), avoiding test classes.

Write Python docstrings following the Google Python Style Guide, using clear sections and examples.

Perform structured, actionable code reviews for Python code with clear findings and suggestions.

Generate high-quality conventional git commit messages and, with user approval, run the commit. Use when drafting or refining commit messages, validating commit quality, or committing staged work while avoiding noisy histories.

python's package managing

Deep technical documentation generation workflow using zen mcp's clink and docgen tools. First uses clink to launch gemini CLI in WSL for code analysis, then uses docgen for structured document generation with complexity analysis. Specializes in documents requiring deep understanding of code logic, model architecture, or performance bottleneck analysis. Use when user requests "use gemini for deep analysis", "generate architecture analysis document", "analyze performance bottlenecks", "deeply understand code logic", or similar deep analysis tasks. Default output is .md format.

Collaborative documentation and test code writing workflow using zen mcp's clink to launch gemini CLI session in WSL (via 'gemini' command) where all writing operations are executed. Use this skill when the user requests "use gemini to write test files", "use gemini to write documentation", "generate related test files", "generate an explanatory document", or similar document/test writing tasks. The gemini CLI session acts as the specialist writer, working with the main Claude model for context gathering, outline approval, and final review. For test code, codex CLI (also launched via clink) validates quality after gemini completes writing.

Get Unity project information via uloop CLI. Use when you need to check project settings, Unity version, platform, or other project metadata.

Intelligent skill router that analyzes user requests and automatically dispatches to the most appropriate skill(s) or zen-mcp tools. Routes to zen-chat for Q&A, zen-thinkdeep for deep problem investigation, codex-code-reviewer for code quality, simple-gemini for standard docs/tests, deep-gemini for deep analysis, or plan-down for planning. Use this skill proactively to interpret all user requests and determine the optimal execution path.

Get Unity project information via uloop CLI. Use when you need to: (1) Check Unity Editor version, (2) Get project settings and platform info, (3) Retrieve project metadata for diagnostics.

Systematic code review workflow using zen mcp's codex tool. Use this skill when the user explicitly requests "use codex to check the code", "check if the recently generated code has any issues", or "check the code after each generation". The skill performs iterative review cycles - checking code quality, presenting issues to the user for approval, applying fixes, and re-checking until no issues remain or maximum iterations (5) are reached.