command-management
Use PROACTIVELY this skill when you need to create or update custom commands following best practices
Find the perfect capability for your agent.
Use PROACTIVELY this skill when you need to create or update custom commands following best practices
macOS-specific bash scripting patterns, compatibility considerations, and best practices. Use when writing or modifying shell scripts, especially for toolchain-2026 installation and configuration scripts. Includes bash version handling, POSIX compatibility, and macOS system gotchas.
Session-based file cleanup for privacy compliance. Use to delete temporary files, uploaded clinical notes, generated outputs, and expired logs to maintain HIPAA-friendly operations.
Build professional Python CLIs with modern UX patterns using pyfiglet (ASCII banners), typer (commands), questionary (interactions), and rich (formatting). Use when creating command-line tools, automation scripts with user interaction, data processing pipelines with CLI interfaces, or upgrading existing Python scripts to professional CLIs. Ideal for ETL workflows, GIS tools, data analysis utilities, and civic tech projects requiring reproducible, scriptable interfaces.
Monitor system health, detect errors, implement recovery procedures, restart failed processes, maintain audit logs. Use for system health checks, error recovery, process monitoring, or when user mentions "system status", "errors", "logs".
Run Python scripts with automatic dependency management using uv. Use this skill when you need to (1) run Python scripts with external dependencies without polluting system Python, (2) create standalone Python scripts with inline dependencies (PEP 723), (3) convert existing scripts to use uv with inline metadata, (4) handle ModuleNotFoundError by running scripts with uv run --with, or (5) create CLI tools, data processing scripts, or API clients that are self-contained and portable.
Run background agents and bash commands asynchronously for CircleTel development. Use when running dev servers, parallel tests, long builds, or multi-agent research tasks without blocking the main workflow.
Manage tasks and dependencies with Tracer CLI. Use for issue tracking, dependency management, finding ready work, and AI agent workflows.
Project organization expert - analyzes folder state, detects redundancy, moves files to proper locations, consolidates duplicate content, appends to accumulator files, removes obsolete content, and generates detailed operation reports. Maintains project structure integrity.
Parallelize operations across dynamic target lists using GitHub Actions matrix strategies with failure isolation, rate limiting, and conditional logic.
Windows system administration with PowerShell 7.x. Profile-aware - reads your preferences for package managers (scoop vs winget), paths, and installed tools. Use when: Windows-specific admin tasks, PowerShell automation, PATH configuration, package installation, bash-to-PowerShell translation.
Use when writing async code, using asyncio.gather, handling concurrent operations. Triggers on "asyncio", "async", "await", "gather", "concurrent", "parallel", "fail-fast", "timeout", "race condition", "cancellation", "coroutine", "task", "CancelledError", or when writing async functions.
Executes the next CLI-orchestrated action when a score step is requested.
Master Python asynchronous programming with asyncio, async/await, and concurrent.futures. Use for async code and concurrency patterns.
Automated scripts for common repository tasks including setup, cleanup, dependency updates, and maintenance.
This skill should be used when the user asks to "automate maintenance", "update dependencies", "security scanning", "automated backups", "system health monitoring", or needs comprehensive automated maintenance to reduce operational overhead and prevent technical debt.
Automatically troubleshoot unexpected results OR command/script errors without user request. Triggers when: (1) unexpected behavior - command succeeded but expected effect didn't happen, missing expected errors, wrong output, silent failures; (2) explicit failures - stderr, exceptions, non-zero exit, SDK/API errors. Applies systematic diagnosis using error templates, hypothesis testing, and web research for any Stack Overflow-worthy issue.
Set up and run the Ralph Loop autonomous coding loop across Windows (WSL2), macOS, and Linux. Use when asked to install or configure ralph-loop, prepare prd.json/prompt/progress files, choose or explain an agent CLI command, or run looped development tasks (long-running/overnight/by-tomorrow, "run the loop", "loop through issues"). Also trigger for Japanese asks like "明日まで進めて", "ループで開発して", "長時間のタスクをこなして" or similar.