Delegate independent tasks to specialized agents working concurrently with isolated context.
uni CLI
uni-cli
uni CLI overview and meta commands. Use for general uni questions, multi-command execution (uni run), saved flows, natural language (uni ask), plugins, config, aliases, history. For specific services, use their dedicated skills (uni-wa, uni-telegram, uni-google, etc.)
SKILL.md
Full skill instructions
uni CLI
Universal CLI wrapping 25+ services into one interface.
Pattern
uni <service> <command> [args] [--options]
uni list # All services
uni <service> --help # Service commands
uni doctor # Health check
Multi-Command (run)
uni run "gcal list" "gtasks list" # Sequential
uni run -p "cmd1" "cmd2" "cmd3" # Parallel
uni run --dry-run "cmd1" "cmd2" # Preview
uni run "wa send me hello{1..5}" # Brace expansion
uni run --file batch.txt # From file
uni run --retry 3 "flaky-cmd" # Retry
uni run "cmd1 && cmd2" # On success
uni run "cmd1 || cmd2" # On failure
uni run "cmd1 | cmd2" # Pipe output
Natural Language (ask)
uni ask "show my calendar tomorrow"
uni ask "search for React tutorials"
uni ask -i # Interactive
uni ask "query" --dry-run # Preview
uni ask providers # List LLM providers
uni ask models --provider anthropic # List models
Saved Flows
uni flow add standup "gcal list" "gtasks list"
uni flow list
uni flow run standup
uni standup # Shorthand
uni flow remove standup
Plugins
uni plugins list # Installed
uni plugins available # Official
uni plugins search google # Search npm
uni plugins install gkeep # Install
uni plugins uninstall gkeep # Remove
uni plugins update # Update all
Config
uni config show # All config
uni config get global.color # Get value
uni config set global.color false # Set value
uni config edit # Open editor
uni config path # Config path
Aliases
uni alias add inbox "gmail list --unread"
uni alias list
uni alias remove inbox
uni inbox # Use alias
History
uni history # Recent
uni history --limit 50
uni history --search "gcal"
uni history run 42 # Re-run #42
uni history clear
Output
- Default: Human-readable
--json: Machine-readable JSON
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
