Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control. Use when the agent needs to spawn, monitor, or orchestrate coding agents in a terminal session, delegate programming tasks to a sub-agent, review pull requests with an external CLI tool, or run parallel background coding workflows across git worktrees.
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns). Use when the developer needs to send a one-shot prompt with file context to another model, bundle repository files for external LLM review, run oracle browser or API queries, manage oracle sessions, attach or exclude files with glob patterns, or preview token costs with dry-run mode.
Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
Shell scripting expert for Bash, POSIX compliance, error handling, and automation
MUST use when writing Bun Native scripts.
MUST use when writing PowerShell scripts.
Registers functions and triggers on the iii engine across TypeScript, Python, and Rust. Use when creating workers, registering function handlers, binding triggers, or invoking functions across languages.
Python SDK for the iii engine. Use when building workers, registering functions, or invoking triggers in Python.
Registers a boolean condition function and attaches it to triggers via condition_function_id so handlers only fire when the condition passes. Use when gating triggers on business rules, checking user permissions, validating data before processing, filtering high-value orders, rate-limiting events, or conditionally skipping handlers based on payload content.
Automatic code splitting (autoCodeSplitting), .lazy.tsx convention, createLazyFileRoute, createLazyRoute, lazyRouteComponent, getRouteApi for typed hooks in split files, codeSplitGroupings per-route override, splitBehavior programmatic config, critical vs non-critical properties.
Describes how to correctly use 'process' tool
Use this skill when the user's intent is to execute a system or plugin function. Applicable scenarios include: 1) The user sends a slash command starting with / (e.g. /cookiecloud, /sites, /subscribes, etc.); 2) The user describes an action in natural language that can be fulfilled by a system or plugin command (e.g. "sync sites", "show subscriptions", "refresh subscriptions", "check downloads", etc.). This skill helps you identify the user's intent, find the matching command, extract necessary parameters, and execute the corresponding command.
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing large outputs. Triggers: "analyze logs", "summarize output", "process data", "parse JSON", "filter results", "extract errors", "check build output", "analyze dependencies", "process API response", "large file analysis", "page snapshot", "browser snapshot", "DOM structure", "inspect page", "accessibility tree", "Playwright snapshot", "run tests", "test output", "coverage report", "git log", "recent commits", "diff between branches", "list containers", "pod status", "disk usage", "fetch docs", "API reference", "index documentation", "call API", "check response", "query results", "find TODOs", "count lines", "codebase statistics", "security audit", "outdated packages", "dependency tree", "cloud resources", "CI/CD output". Also triggers on ANY MCP tool output that may exceed 20 lines. Subagent routing is handled automatically via PreToolUse hook.
