Run Agent Skills as shell scripts. Integrates with Claude for automation. Useful for operations teams to execute tasks without manual intervention. Connects to existing shell environments and workflows.
git clone https://github.com/martinemde/skillet.gitSkillet transforms Claude agent skills into executable shell commands, enabling teams to automate tasks without manual intervention. It reads skill definitions directly, applies configured permissions and model settings, and formats Claude's output beautifully using the Charm library. Instead of managing separate scripts or dealing with raw JSON output, you run skills from the command line like standard shell utilities. Skillet supports local skills stored in `.claude/skills/` directories and remote skills via URL, making it ideal for operations teams integrating automation into existing workflows.
Install via Homebrew with `brew install martinemde/tap/skillet`. Run skills by name with `skillet skill-name` or from remote URLs with `skillet https://url/to/skill.md`. List available skills with `skillet --list` and view verbose output with `--verbose` flag.
Run code review skills from the command line as shell scripts
Automate transcript summarization across multiple files in parallel
Convert deprecated Claude commands to executable skills
Parse and browse Claude conversation history with formatted output
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/martinemde/skilletCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Run the 'System Monitoring' Agent Skill as a shell script for [COMPANY] in the [INDUSTRY] sector. Use the following [DATA] to monitor server health: CPU usage, memory consumption, and disk space. Provide the output in a structured format.
# System Monitoring Report ## CPU Usage - **Average Load**: 45% - **Peak Load**: 78% - **Idle Time**: 55% ## Memory Consumption - **Total RAM**: 32GB - **Used RAM**: 18GB (56%) - **Available RAM**: 14GB (44%) ## Disk Space - **Total Disk Space**: 1TB - **Used Space**: 650GB (65%) - **Available Space**: 350GB (35%) ### Recommendations - Consider optimizing processes to reduce CPU load during peak hours. - Monitor memory usage trends to anticipate potential upgrades. - Schedule a disk cleanup to free up additional space.
AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
ITIL-aligned IT service management platform
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan