python-async-patterns
Python asyncio patterns for concurrent programming. Triggers on: asyncio, async, await, coroutine, gather, semaphore, TaskGroup, event loop, aiohttp, concurrent.
Python asyncio patterns for concurrent programming. Triggers on: asyncio, async, await, coroutine, gather, semaphore, TaskGroup, event loop, aiohttp, concurrent.
Automate construction data processing using LLM (ChatGPT, Claude, LLaMA). Generate Python/Pandas scripts, extract data from documents, and create automated pipelines without deep programming knowledge.
Execute all plans in a phase with wave-based parallelization, running phase execution, or completing phase work. Triggers include "execute phase", "run phase", "execute plans", "run the phase", and "phase execution".
Automate as-built documentation and digital handover for construction. Compile project records, generate O&M manuals, create asset databases, and ensure complete project closeout.
Find and read multiple files in one operation (50-70% faster for exploration)
Find and read multiple files in one operation (50-70% faster for exploration)
Create and register hook scripts with proper error handling and settings
Execute implementation plans from .artifacts/plan/. Focus on EXECUTING ONLY - no planning, no fixes outside plan scope. Uses gated checks, atomic commits, and maintains a single execution log in .artifacts/execute/. Use when the user says "execute this plan" or provides a plan path.
Browser automation CLI for AI agents. Use when needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. TRIGGER when user requests to "open a website", "fill out a form", "click a button", "take a screenshot", "debug this in browser", "scrape data from a page", "test this web app", "login to a site", "frontend UI/UX aesthetics", "automate browser actions", or any task requiring programmatic web interaction.
Rapid task execution without hesitation or deterrence. Expert in overcoming blockers, making quick decisions, and maintaining forward momentum. Use for urgent tasks, breaking through impediments, decisive action. Activates on 'swift', 'execute quickly', 'undeterred', 'overcome blocker', 'just do it'. NOT for strategic planning, careful analysis, or research tasks.
myfy TasksModule for background job processing with SQL-based queue. Use when working with TasksModule, @task decorator, background jobs, task workers, TaskContext, task retries, or async task dispatch.
Write, review, debug, and improve bash/shell scripts for any context: CI/CD pipelines (GitHub Actions, GitLab CI, Bitrise), DevOps automation, macOS/Linux system tasks, file processing, and data transformation. Use this skill whenever the user asks to write a shell script, improve an existing one, debug a bash error, or automate any task via command line — even if they just say "make a script that does X" or paste a broken script without explanation. Also trigger for requests involving cron jobs, entrypoints, deploy scripts, migration scripts, or any .sh file.
Generate a small helper script for repetitive tasks. Use when a junior developer needs a quick automation snippet.
Use when: running an ad hoc Node.js script, using node -e for inspection or file transforms, creating a temporary .cjs helper, or avoiding Git Bash quoting and history-expansion issues on Windows. Keywords: node script, node -e, temporary script, .cjs, Git Bash, history expansion, JSON transform, one-off Node command.
This skill should be used when the user asks to "build web automation scripts", "check browser automation for detection", "generate web scraping code", "create form filling automation", or "build anti-detection browser scripts".
Use this skill for engineering tasks that require planning with write_todos, controlled file edits, and final verification.
This skill should be used when the user asks to "create an automation", "schedule a task", "set up a cron job", or mentions automations, scheduled tasks, or cron scheduling in OpenHands Cloud.
CHAIN multiple existing skills into custom multi-step workflows. Programmable skill combinations with automatic handoffs. Create composite skills from building blocks with conditional logic.
Delegate tasks to specialized subagents for parallel or sequential execution.
Trigger this skill whenever there is a written implementation plan ready to execute, or when the user says "execute", "run the plan", "implement the plan", "start building", or references a plan file. Also activate when using subagent-driven development with independent tasks, when the user wants automated execution with quality gates, or when picking up a previously written plan. If a plan document exists and no one is executing it yet, this is the skill to use.
Trigger this skill whenever working with Python files (.py), writing Python scripts or applications, or using Python frameworks like Django, FastAPI, or Flask. Activate for any Python-specific patterns including type hints, async/await with asyncio, dataclasses, Pydantic models, context managers, virtual environments, or PEP 8 style questions. Also use when the user references Python package management, pip, or pyproject.toml.
Moving mechanical computation from LLM prompts into tested CLI commands. Use when writing or reviewing slash commands with embedded bash, when a skill/command exceeds ~100 lines of procedural steps, when adding parsing/validation/transformation logic to markdown prompts, when debugging flaky embedded scripts, or when refactoring commands to reduce token overhead.